kynix/machine-learning-atoz
1
0
Fork 0
Code Issues Pull Requests Actions Packages repo.project_board Releases Wiki Activity

機器學習

Browse Source
This commit is contained in:
KynixInHK 2024-10-25 19:48:10 +08:00
commit e21eb40033
44 changed files with 33245 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.idea/.gitignore vendored Normal file
View File

@ -0,0 +1,8 @@
# Default ignored files
/shelf/
/workspace.xml
# Editor-based HTTP Client requests
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

66
.idea/inspectionProfiles/Project_Default.xml Normal file
View File

@ -0,0 +1,66 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="HttpUrlsUsage" enabled="true" level="WEAK WARNING" enabled_by_default="true">
<option name="ignoredUrls">
<list>
<option value="http://0.0.0.0" />
<option value="http://127.0.0.1" />
<option value="http://activemq.apache.org/schema/" />
<option value="http://cxf.apache.org/schemas/" />
<option value="http://java.sun.com/" />
<option value="http://javafx.com/fxml" />
<option value="http://javafx.com/javafx/" />
<option value="http://json-schema.org/draft" />
<option value="http://localhost" />
<option value="http://maven.apache.org/POM/" />
<option value="http://maven.apache.org/xsd/" />
<option value="http://primefaces.org/ui" />
<option value="http://schema.cloudfoundry.org/spring/" />
<option value="http://schemas.xmlsoap.org/" />
<option value="http://tiles.apache.org/" />
<option value="http://www.dda5.com" />
<option value="http://www.ibm.com/webservices/xsd" />
<option value="http://www.jboss.com/xml/ns/" />
<option value="http://www.jboss.org/j2ee/schema/" />
<option value="http://www.springframework.org/schema/" />
<option value="http://www.springframework.org/security/tags" />
<option value="http://www.springframework.org/tags" />
<option value="http://www.thymeleaf.org" />
<option value="http://www.w3.org/" />
<option value="http://xmlns.jcp.org/" />
</list>
</option>
</inspection_tool>
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredPackages">
<value>
<list size="22">
<item index="0" class="java.lang.String" itemvalue="clyent" />
<item index="1" class="java.lang.String" itemvalue="protobuf" />
<item index="2" class="java.lang.String" itemvalue="python-lsp-jsonrpc" />
<item index="3" class="java.lang.String" itemvalue="atomicwrites" />
<item index="4" class="java.lang.String" itemvalue="jsonpointer" />
<item index="5" class="java.lang.String" itemvalue="et-xmlfile" />
<item index="6" class="java.lang.String" itemvalue="PyQtWebEngine" />
<item index="7" class="java.lang.String" itemvalue="pyasn1-modules" />
<item index="8" class="java.lang.String" itemvalue="fonttools" />
<item index="9" class="java.lang.String" itemvalue="patsy" />
<item index="10" class="java.lang.String" itemvalue="pyls-spyder" />
<item index="11" class="java.lang.String" itemvalue="appdirs" />
<item index="12" class="java.lang.String" itemvalue="conda-repo-cli" />
<item index="13" class="java.lang.String" itemvalue="munkres" />
<item index="14" class="java.lang.String" itemvalue="backports.weakref" />
<item index="15" class="java.lang.String" itemvalue="conda-verify" />
<item index="16" class="java.lang.String" itemvalue="PyQt5" />
<item index="17" class="java.lang.String" itemvalue="PyDispatcher" />
<item index="18" class="java.lang.String" itemvalue="ply" />
<item index="19" class="java.lang.String" itemvalue="webencodings" />
<item index="20" class="java.lang.String" itemvalue="inflection" />
<item index="21" class="java.lang.String" itemvalue="openpyxl" />
</list>
</value>
</option>
</inspection_tool>
</profile>
</component>

6
.idea/inspectionProfiles/profiles_settings.xml Normal file
View File

@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

10
.idea/machineLeaningAtoZ.iml Normal file
View File

@ -0,0 +1,10 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$">
<excludeFolder url="file://$MODULE_DIR$/.venv" />
</content>
<orderEntry type="inheritedJdk" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

7
.idea/misc.xml Normal file
View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="Python 3.9 (machineLeaningAtoZ)" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (machineLeaningAtoZ)" project-jdk-type="Python SDK" />
</project>

8
.idea/modules.xml Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/machineLeaningAtoZ.iml" filepath="$PROJECT_DIR$/.idea/machineLeaningAtoZ.iml" />
</modules>
</component>
</project>

6
.idea/other.xml Normal file
View File

@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="PySciProjectComponent">
<option name="PY_INTERACTIVE_PLOTS_SUGGESTED" value="true" />
</component>
</project>

6
.idea/vcs.xml Normal file
View File

@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>

401
section_10_model_selection/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

82
section_10_model_selection/main.py Normal file
View File

@ -0,0 +1,82 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.svm import SVC
classifier = SVC(kernel='rbf', random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, Y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
# 交叉驗證
from sklearn.model_selection import cross_val_predict
accuracies = cross_val_predict(classifier, X_set, y_set, cv=10)
means = accuracies.mean()
stds = accuracies.std()
# 網格檢索
from sklearn.model_selection import GridSearchCV
parameters = [{'C': [1, 10, 100, 1000], 'kernel': ['linear']}, {'C': [1, 10, 100, 1000], 'kernel': ['rbf'], 'gamma': [0.5, 0.1, 0.01, 0.001, 0.0001]}] # 超參數的範圍
grid_search = GridSearchCV(estimator = classifier, param_grid = parameters, scoring = 'accuracy', cv = 10, n_jobs = -1) # n_jobs 是使用的 CPU 核心數，-1 表示使用所有核心
grid_search = grid_search.fit(X_train, Y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
# 視覺化
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

11
section_1_data_processing/Data.csv Normal file
View File

@ -0,0 +1,11 @@
Country,Age,Salary,Purchased
France,44,72000,No
Spain,27,48000,Yes
Germany,30,54000,No
Spain,38,61000,No
Germany,40,,Yes
France,35,58000,Yes
Spain,,52000,No
France,48,79000,Yes
Germany,50,83000,No
France,37,67000,Yes
1 Country Age Salary Purchased
2 France 44 72000 No
3 Spain 27 48000 Yes
4 Germany 30 54000 No
5 Spain 38 61000 No
6 Germany 40 Yes
7 France 35 58000 Yes
8 Spain 52000 No
9 France 48 79000 Yes
10 Germany 50 83000 No
11 France 37 67000 Yes

43
section_1_data_processing/main.py Normal file
View File

@ -0,0 +1,43 @@
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# 引入資料集
dataset = pd.read_csv("Data.csv")
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 3].values
# 缺損資料處理
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
X[:, 1: 3] = imputer.fit_transform(X[:, 1:3])
# 分類資料的處理
from sklearn.preprocessing import LabelEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer(transformers=[
('col-0', OneHotEncoder(), [0])
], remainder='passthrough')
X = np.array(ct.fit_transform(X), dtype=float)
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
# 將資料集分為訓練集和測試集
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)
# 特徵縮放
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)

31
section_2_regression/section_2_1_simple_linear_regression/Salary_Data.csv Normal file
View File

@ -0,0 +1,31 @@
YearsExperience,Salary
1.1,39343.00
1.3,46205.00
1.5,37731.00
2.0,43525.00
2.2,39891.00
2.9,56642.00
3.0,60150.00
3.2,54445.00
3.2,64445.00
3.7,57189.00
3.9,63218.00
4.0,55794.00
4.0,56957.00
4.1,57081.00
4.5,61111.00
4.9,67938.00
5.1,66029.00
5.3,83088.00
5.9,81363.00
6.0,93940.00
6.8,91738.00
7.1,98273.00
7.9,101302.00
8.2,113812.00
8.7,109431.00
9.0,105582.00
9.5,116969.00
9.6,112635.00
10.3,122391.00
10.5,121872.00
1 YearsExperience Salary
2 1.1 39343.00
3 1.3 46205.00
4 1.5 37731.00
5 2.0 43525.00
6 2.2 39891.00
7 2.9 56642.00
8 3.0 60150.00
9 3.2 54445.00
10 3.2 64445.00
11 3.7 57189.00
12 3.9 63218.00
13 4.0 55794.00
14 4.0 56957.00
15 4.1 57081.00
16 4.5 61111.00
17 4.9 67938.00
18 5.1 66029.00
19 5.3 83088.00
20 5.9 81363.00
21 6.0 93940.00
22 6.8 91738.00
23 7.1 98273.00
24 7.9 101302.00
25 8.2 113812.00
26 8.7 109431.00
27 9.0 105582.00
28 9.5 116969.00
29 9.6 112635.00
30 10.3 122391.00
31 10.5 121872.00

31
section_2_regression/section_2_1_simple_linear_regression/main.py Normal file
View File

@ -0,0 +1,31 @@
# 資料預處理
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
dataset = pd.read_csv("Salary_Data.csv")
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 1].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)
# 開始擬合
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, Y_train)
Y_pred = regressor.predict(X_test)
plt.scatter(X_train, Y_train, color="red")
plt.scatter(X_test, Y_test, color="green")
plt.plot(X_train, regressor.predict(X_train), color="blue")
plt.title("Salary vs Experience (Training set)")
plt.xlabel("Years of Experience")
plt.ylabel("Salary")
plt.show()

51
section_2_regression/section_2_2_multiple_linear_regression/50_Startups.csv Normal file
View File

@ -0,0 +1,51 @@
R&D Spend,Administration,Marketing Spend,State,Profit
165349.2,136897.8,471784.1,New York,192261.83
162597.7,151377.59,443898.53,California,191792.06
153441.51,101145.55,407934.54,Florida,191050.39
144372.41,118671.85,383199.62,New York,182901.99
142107.34,91391.77,366168.42,Florida,166187.94
131876.9,99814.71,362861.36,New York,156991.12
134615.46,147198.87,127716.82,California,156122.51
130298.13,145530.06,323876.68,Florida,155752.6
120542.52,148718.95,311613.29,New York,152211.77
123334.88,108679.17,304981.62,California,149759.96
101913.08,110594.11,229160.95,Florida,146121.95
100671.96,91790.61,249744.55,California,144259.4
93863.75,127320.38,249839.44,Florida,141585.52
91992.39,135495.07,252664.93,California,134307.35
119943.24,156547.42,256512.92,Florida,132602.65
114523.61,122616.84,261776.23,New York,129917.04
78013.11,121597.55,264346.06,California,126992.93
94657.16,145077.58,282574.31,New York,125370.37
91749.16,114175.79,294919.57,Florida,124266.9
86419.7,153514.11,0,New York,122776.86
76253.86,113867.3,298664.47,California,118474.03
78389.47,153773.43,299737.29,New York,111313.02
73994.56,122782.75,303319.26,Florida,110352.25
67532.53,105751.03,304768.73,Florida,108733.99
77044.01,99281.34,140574.81,New York,108552.04
64664.71,139553.16,137962.62,California,107404.34
75328.87,144135.98,134050.07,Florida,105733.54
72107.6,127864.55,353183.81,New York,105008.31
66051.52,182645.56,118148.2,Florida,103282.38
65605.48,153032.06,107138.38,New York,101004.64
61994.48,115641.28,91131.24,Florida,99937.59
61136.38,152701.92,88218.23,New York,97483.56
63408.86,129219.61,46085.25,California,97427.84
55493.95,103057.49,214634.81,Florida,96778.92
46426.07,157693.92,210797.67,California,96712.8
46014.02,85047.44,205517.64,New York,96479.51
28663.76,127056.21,201126.82,Florida,90708.19
44069.95,51283.14,197029.42,California,89949.14
20229.59,65947.93,185265.1,New York,81229.06
38558.51,82982.09,174999.3,California,81005.76
28754.33,118546.05,172795.67,California,78239.91
27892.92,84710.77,164470.71,Florida,77798.83
23640.93,96189.63,148001.11,California,71498.49
15505.73,127382.3,35534.17,New York,69758.98
22177.74,154806.14,28334.72,California,65200.33
1000.23,124153.04,1903.93,New York,64926.08
1315.46,115816.21,297114.46,Florida,49490.75
0,135426.92,0,California,42559.73
542.05,51743.15,0,New York,35673.41
0,116983.8,45173.06,California,14681.4
1 R&D Spend Administration Marketing Spend State Profit
2 165349.2 136897.8 471784.1 New York 192261.83
3 162597.7 151377.59 443898.53 California 191792.06
4 153441.51 101145.55 407934.54 Florida 191050.39
5 144372.41 118671.85 383199.62 New York 182901.99
6 142107.34 91391.77 366168.42 Florida 166187.94
7 131876.9 99814.71 362861.36 New York 156991.12
8 134615.46 147198.87 127716.82 California 156122.51
9 130298.13 145530.06 323876.68 Florida 155752.6
10 120542.52 148718.95 311613.29 New York 152211.77
11 123334.88 108679.17 304981.62 California 149759.96
12 101913.08 110594.11 229160.95 Florida 146121.95
13 100671.96 91790.61 249744.55 California 144259.4
14 93863.75 127320.38 249839.44 Florida 141585.52
15 91992.39 135495.07 252664.93 California 134307.35
16 119943.24 156547.42 256512.92 Florida 132602.65
17 114523.61 122616.84 261776.23 New York 129917.04
18 78013.11 121597.55 264346.06 California 126992.93
19 94657.16 145077.58 282574.31 New York 125370.37
20 91749.16 114175.79 294919.57 Florida 124266.9
21 86419.7 153514.11 0 New York 122776.86
22 76253.86 113867.3 298664.47 California 118474.03
23 78389.47 153773.43 299737.29 New York 111313.02
24 73994.56 122782.75 303319.26 Florida 110352.25
25 67532.53 105751.03 304768.73 Florida 108733.99
26 77044.01 99281.34 140574.81 New York 108552.04
27 64664.71 139553.16 137962.62 California 107404.34
28 75328.87 144135.98 134050.07 Florida 105733.54
29 72107.6 127864.55 353183.81 New York 105008.31
30 66051.52 182645.56 118148.2 Florida 103282.38
31 65605.48 153032.06 107138.38 New York 101004.64
32 61994.48 115641.28 91131.24 Florida 99937.59
33 61136.38 152701.92 88218.23 New York 97483.56
34 63408.86 129219.61 46085.25 California 97427.84
35 55493.95 103057.49 214634.81 Florida 96778.92
36 46426.07 157693.92 210797.67 California 96712.8
37 46014.02 85047.44 205517.64 New York 96479.51
38 28663.76 127056.21 201126.82 Florida 90708.19
39 44069.95 51283.14 197029.42 California 89949.14
40 20229.59 65947.93 185265.1 New York 81229.06
41 38558.51 82982.09 174999.3 California 81005.76
42 28754.33 118546.05 172795.67 California 78239.91
43 27892.92 84710.77 164470.71 Florida 77798.83
44 23640.93 96189.63 148001.11 California 71498.49
45 15505.73 127382.3 35534.17 New York 69758.98
46 22177.74 154806.14 28334.72 California 65200.33
47 1000.23 124153.04 1903.93 New York 64926.08
48 1315.46 115816.21 297114.46 Florida 49490.75
49 0 135426.92 0 California 42559.73
50 542.05 51743.15 0 New York 35673.41
51 0 116983.8 45173.06 California 14681.4

42
section_2_regression/section_2_2_multiple_linear_regression/main.py Normal file
View File

@ -0,0 +1,42 @@
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
# 資料預處理
dataset = pd.read_csv("50_Startups.csv")
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 4].values
labelencoder_X = LabelEncoder()
X[:, 3] = labelencoder_X.fit_transform(X[:, 3])
ct = ColumnTransformer(transformers=[
('col-0', OneHotEncoder(), [3])
], remainder='passthrough')
X = np.array(ct.fit_transform(X), dtype=float)
X = X[:, 1:]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)
# 創Create the regressor
# regressor = LinearRegression()
# regressor.fit(X_train, Y_train)
# Y_pred = regressor.predict(X_test)
# 即反向淘汰Using the backward elimination to update the model
import statsmodels.api as sm
X_train = np.append(arr=np.ones((40, 1)).astype(int), values=X_train, axis=1)
## Get the variables from x_train
X_opt = X_train[:, [0, 3, 5]]
regressor_ols = sm.OLS(endog=Y_train, exog=X_opt).fit()
print(regressor_ols.summary())

11
section_2_regression/section_2_3_polynomial_regression/Position_Salaries.csv Normal file
View File

@ -0,0 +1,11 @@
Position,Level,Salary
Business Analyst,1,45000
Junior Consultant,2,50000
Senior Consultant,3,60000
Manager,4,80000
Country Manager,5,110000
Region Manager,6,150000
Partner,7,200000
Senior Partner,8,300000
C-level,9,500000
CEO,10,1000000
1 Position Level Salary
2 Business Analyst 1 45000
3 Junior Consultant 2 50000
4 Senior Consultant 3 60000
5 Manager 4 80000
6 Country Manager 5 110000
7 Region Manager 6 150000
8 Partner 7 200000
9 Senior Partner 8 300000
10 C-level 9 500000
11 CEO 10 1000000

38
section_2_regression/section_2_3_polynomial_regression/main.py Normal file
View File

@ -0,0 +1,38 @@
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
dataset = pd.read_csv("Position_Salaries.csv")
X = dataset.iloc[:, 1:2].values # 1:2 取出的是 matrix
Y = dataset.iloc[:, 2].values
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=4)
X_poly = poly.fit_transform(X)
lin_reg = LinearRegression()
lin_reg.fit(X_poly, Y)
# 避免線段
X_grid = np.arange(min(X), max(X), 0.1)
X_grid = X_grid.reshape((len(X_grid), 1))
plt.scatter(X, Y, color='red')
plt.plot(X_grid, lin_reg.predict(poly.fit_transform(X_grid)), color='blue')
plt.title('Truth or Bluf')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()
X_pred = np.array(6.5).reshape(1, 1)
print(lin_reg.predict(poly.fit_transform(X_pred)))

401
section_3_classification/section_3_1_logical_regression/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

62
section_3_classification/section_3_1_logical_regression/main.py Normal file
View File

@ -0,0 +1,62 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
print(Y_test)
print(Y_pred)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, Y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

401
section_3_classification/section_3_2_svm/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

59
section_3_classification/section_3_2_svm/main.py Normal file
View File

@ -0,0 +1,59 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.svm import SVC
classifier = SVC(kernel='linear', random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, Y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

401
section_3_classification/section_3_3_kernel_svm/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

59
section_3_classification/section_3_3_kernel_svm/main.py Normal file
View File

@ -0,0 +1,59 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.svm import SVC
classifier = SVC(kernel='rbf', random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, Y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

401
section_3_classification/section_3_4_naive_bayes/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

59
section_3_classification/section_3_4_naive_bayes/main.py Normal file
View File

@ -0,0 +1,59 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, Y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Naive Bayes (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

401
section_3_classification/section_3_5_decision_tree/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

56
section_3_classification/section_3_5_decision_tree/main.py Normal file
View File

@ -0,0 +1,56 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier(criterion='gini', random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, Y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Decision Tree (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

401
section_3_classification/section_3_6_random_forest/Social_Network_Ads.csv Normal file
View File

@ -0,0 +1,401 @@
User ID,Gender,Age,EstimatedSalary,Purchased
15624510,Male,19,19000,0
15810944,Male,35,20000,0
15668575,Female,26,43000,0
15603246,Female,27,57000,0
15804002,Male,19,76000,0
15728773,Male,27,58000,0
15598044,Female,27,84000,0
15694829,Female,32,150000,1
15600575,Male,25,33000,0
15727311,Female,35,65000,0
15570769,Female,26,80000,0
15606274,Female,26,52000,0
15746139,Male,20,86000,0
15704987,Male,32,18000,0
15628972,Male,18,82000,0
15697686,Male,29,80000,0
15733883,Male,47,25000,1
15617482,Male,45,26000,1
15704583,Male,46,28000,1
15621083,Female,48,29000,1
15649487,Male,45,22000,1
15736760,Female,47,49000,1
15714658,Male,48,41000,1
15599081,Female,45,22000,1
15705113,Male,46,23000,1
15631159,Male,47,20000,1
15792818,Male,49,28000,1
15633531,Female,47,30000,1
15744529,Male,29,43000,0
15669656,Male,31,18000,0
15581198,Male,31,74000,0
15729054,Female,27,137000,1
15573452,Female,21,16000,0
15776733,Female,28,44000,0
15724858,Male,27,90000,0
15713144,Male,35,27000,0
15690188,Female,33,28000,0
15689425,Male,30,49000,0
15671766,Female,26,72000,0
15782806,Female,27,31000,0
15764419,Female,27,17000,0
15591915,Female,33,51000,0
15772798,Male,35,108000,0
15792008,Male,30,15000,0
15715541,Female,28,84000,0
15639277,Male,23,20000,0
15798850,Male,25,79000,0
15776348,Female,27,54000,0
15727696,Male,30,135000,1
15793813,Female,31,89000,0
15694395,Female,24,32000,0
15764195,Female,18,44000,0
15744919,Female,29,83000,0
15671655,Female,35,23000,0
15654901,Female,27,58000,0
15649136,Female,24,55000,0
15775562,Female,23,48000,0
15807481,Male,28,79000,0
15642885,Male,22,18000,0
15789109,Female,32,117000,0
15814004,Male,27,20000,0
15673619,Male,25,87000,0
15595135,Female,23,66000,0
15583681,Male,32,120000,1
15605000,Female,59,83000,0
15718071,Male,24,58000,0
15679760,Male,24,19000,0
15654574,Female,23,82000,0
15577178,Female,22,63000,0
15595324,Female,31,68000,0
15756932,Male,25,80000,0
15726358,Female,24,27000,0
15595228,Female,20,23000,0
15782530,Female,33,113000,0
15592877,Male,32,18000,0
15651983,Male,34,112000,1
15746737,Male,18,52000,0
15774179,Female,22,27000,0
15667265,Female,28,87000,0
15655123,Female,26,17000,0
15595917,Male,30,80000,0
15668385,Male,39,42000,0
15709476,Male,20,49000,0
15711218,Male,35,88000,0
15798659,Female,30,62000,0
15663939,Female,31,118000,1
15694946,Male,24,55000,0
15631912,Female,28,85000,0
15768816,Male,26,81000,0
15682268,Male,35,50000,0
15684801,Male,22,81000,0
15636428,Female,30,116000,0
15809823,Male,26,15000,0
15699284,Female,29,28000,0
15786993,Female,29,83000,0
15709441,Female,35,44000,0
15710257,Female,35,25000,0
15582492,Male,28,123000,1
15575694,Male,35,73000,0
15756820,Female,28,37000,0
15766289,Male,27,88000,0
15593014,Male,28,59000,0
15584545,Female,32,86000,0
15675949,Female,33,149000,1
15672091,Female,19,21000,0
15801658,Male,21,72000,0
15706185,Female,26,35000,0
15789863,Male,27,89000,0
15720943,Male,26,86000,0
15697997,Female,38,80000,0
15665416,Female,39,71000,0
15660200,Female,37,71000,0
15619653,Male,38,61000,0
15773447,Male,37,55000,0
15739160,Male,42,80000,0
15689237,Male,40,57000,0
15679297,Male,35,75000,0
15591433,Male,36,52000,0
15642725,Male,40,59000,0
15701962,Male,41,59000,0
15811613,Female,36,75000,0
15741049,Male,37,72000,0
15724423,Female,40,75000,0
15574305,Male,35,53000,0
15678168,Female,41,51000,0
15697020,Female,39,61000,0
15610801,Male,42,65000,0
15745232,Male,26,32000,0
15722758,Male,30,17000,0
15792102,Female,26,84000,0
15675185,Male,31,58000,0
15801247,Male,33,31000,0
15725660,Male,30,87000,0
15638963,Female,21,68000,0
15800061,Female,28,55000,0
15578006,Male,23,63000,0
15668504,Female,20,82000,0
15687491,Male,30,107000,1
15610403,Female,28,59000,0
15741094,Male,19,25000,0
15807909,Male,19,85000,0
15666141,Female,18,68000,0
15617134,Male,35,59000,0
15783029,Male,30,89000,0
15622833,Female,34,25000,0
15746422,Female,24,89000,0
15750839,Female,27,96000,1
15749130,Female,41,30000,0
15779862,Male,29,61000,0
15767871,Male,20,74000,0
15679651,Female,26,15000,0
15576219,Male,41,45000,0
15699247,Male,31,76000,0
15619087,Female,36,50000,0
15605327,Male,40,47000,0
15610140,Female,31,15000,0
15791174,Male,46,59000,0
15602373,Male,29,75000,0
15762605,Male,26,30000,0
15598840,Female,32,135000,1
15744279,Male,32,100000,1
15670619,Male,25,90000,0
15599533,Female,37,33000,0
15757837,Male,35,38000,0
15697574,Female,33,69000,0
15578738,Female,18,86000,0
15762228,Female,22,55000,0
15614827,Female,35,71000,0
15789815,Male,29,148000,1
15579781,Female,29,47000,0
15587013,Male,21,88000,0
15570932,Male,34,115000,0
15794661,Female,26,118000,0
15581654,Female,34,43000,0
15644296,Female,34,72000,0
15614420,Female,23,28000,0
15609653,Female,35,47000,0
15594577,Male,25,22000,0
15584114,Male,24,23000,0
15673367,Female,31,34000,0
15685576,Male,26,16000,0
15774727,Female,31,71000,0
15694288,Female,32,117000,1
15603319,Male,33,43000,0
15759066,Female,33,60000,0
15814816,Male,31,66000,0
15724402,Female,20,82000,0
15571059,Female,33,41000,0
15674206,Male,35,72000,0
15715160,Male,28,32000,0
15730448,Male,24,84000,0
15662067,Female,19,26000,0
15779581,Male,29,43000,0
15662901,Male,19,70000,0
15689751,Male,28,89000,0
15667742,Male,34,43000,0
15738448,Female,30,79000,0
15680243,Female,20,36000,0
15745083,Male,26,80000,0
15708228,Male,35,22000,0
15628523,Male,35,39000,0
15708196,Male,49,74000,0
15735549,Female,39,134000,1
15809347,Female,41,71000,0
15660866,Female,58,101000,1
15766609,Female,47,47000,0
15654230,Female,55,130000,1
15794566,Female,52,114000,0
15800890,Female,40,142000,1
15697424,Female,46,22000,0
15724536,Female,48,96000,1
15735878,Male,52,150000,1
15707596,Female,59,42000,0
15657163,Male,35,58000.0,0
15622478,Male,47.0,43000,0
15779529,Female,60,108000,1
15636023,Male,49,65000,0
15582066,Male,40,78000,0
15666675,Female,46,96000,0
15732987,Male,59,143000,1
15789432,Female,41,80000,0
15663161,Male,35,91000,1
15694879,Male,37,144000,1
15593715,Male,60,102000,1
15575002,Female,35,60000,0
15622171,Male,37,53000,0
15795224,Female,36,126000,1
15685346,Male,56,133000,1
15691808,Female,40,72000,0
15721007,Female,42,80000,1
15794253,Female,35,147000,1
15694453,Male,39,42000,0
15813113,Male,40,107000,1
15614187,Male,49,86000,1
15619407,Female,38,112000,0
15646227,Male,46,79000,1
15660541,Male,40,57000,0
15753874,Female,37,80000,0
15617877,Female,46,82000,0
15772073,Female,53,143000,1
15701537,Male,42,149000,1
15736228,Male,38,59000,0
15780572,Female,50,88000,1
15769596,Female,56,104000,1
15586996,Female,41,72000,0
15722061,Female,51,146000,1
15638003,Female,35,50000,0
15775590,Female,57,122000,1
15730688,Male,41,52000,0
15753102,Female,35,97000,1
15810075,Female,44,39000,0
15723373,Male,37,52000,0
15795298,Female,48,134000,1
15584320,Female,37,146000,1
15724161,Female,50,44000,0
15750056,Female,52,90000,1
15609637,Female,41,72000,0
15794493,Male,40,57000,0
15569641,Female,58,95000,1
15815236,Female,45,131000,1
15811177,Female,35,77000,0
15680587,Male,36,144000,1
15672821,Female,55,125000,1
15767681,Female,35,72000,0
15600379,Male,48,90000,1
15801336,Female,42,108000,1
15721592,Male,40,75000,0
15581282,Male,37,74000,0
15746203,Female,47,144000,1
15583137,Male,40,61000,0
15680752,Female,43,133000,0
15688172,Female,59,76000,1
15791373,Male,60,42000,1
15589449,Male,39,106000,1
15692819,Female,57,26000,1
15727467,Male,57,74000,1
15734312,Male,38,71000,0
15764604,Male,49,88000,1
15613014,Female,52,38000,1
15759684,Female,50,36000,1
15609669,Female,59,88000,1
15685536,Male,35,61000,0
15750447,Male,37,70000,1
15663249,Female,52,21000,1
15638646,Male,48,141000,0
15734161,Female,37,93000,1
15631070,Female,37,62000,0
15761950,Female,48,138000,1
15649668,Male,41,79000,0
15713912,Female,37,78000,1
15586757,Male,39,134000,1
15596522,Male,49,89000,1
15625395,Male,55,39000,1
15760570,Male,37,77000,0
15566689,Female,35,57000,0
15725794,Female,36,63000,0
15673539,Male,42,73000,1
15705298,Female,43,112000,1
15675791,Male,45,79000,0
15747043,Male,46,117000,1
15736397,Female,58,38000,1
15678201,Male,48,74000,1
15720745,Female,37,137000,1
15637593,Male,37,79000,1
15598070,Female,40,60000,0
15787550,Male,42,54000,0
15603942,Female,51,134000,0
15733973,Female,47,113000,1
15596761,Male,36,125000,1
15652400,Female,38,50000,0
15717893,Female,42,70000,0
15622585,Male,39,96000,1
15733964,Female,38,50000,0
15753861,Female,49,141000,1
15747097,Female,39,79000,0
15594762,Female,39,75000,1
15667417,Female,54,104000,1
15684861,Male,35,55000,0
15742204,Male,45,32000,1
15623502,Male,36,60000,0
15774872,Female,52,138000,1
15611191,Female,53,82000,1
15674331,Male,41,52000,0
15619465,Female,48,30000,1
15575247,Female,48,131000,1
15695679,Female,41,60000,0
15713463,Male,41,72000,0
15785170,Female,42,75000,0
15796351,Male,36,118000,1
15639576,Female,47,107000,1
15693264,Male,38,51000,0
15589715,Female,48,119000,1
15769902,Male,42,65000,0
15587177,Male,40,65000,0
15814553,Male,57,60000,1
15601550,Female,36,54000,0
15664907,Male,58,144000,1
15612465,Male,35,79000,0
15810800,Female,38,55000,0
15665760,Male,39,122000,1
15588080,Female,53,104000,1
15776844,Male,35,75000,0
15717560,Female,38,65000,0
15629739,Female,47,51000,1
15729908,Male,47,105000,1
15716781,Female,41,63000,0
15646936,Male,53,72000,1
15768151,Female,54,108000,1
15579212,Male,39,77000,0
15721835,Male,38,61000,0
15800515,Female,38,113000,1
15591279,Male,37,75000,0
15587419,Female,42,90000,1
15750335,Female,37,57000,0
15699619,Male,36,99000,1
15606472,Male,60,34000,1
15778368,Male,54,70000,1
15671387,Female,41,72000,0
15573926,Male,40,71000,1
15709183,Male,42,54000,0
15577514,Male,43,129000,1
15778830,Female,53,34000,1
15768072,Female,47,50000,1
15768293,Female,42,79000,0
15654456,Male,42,104000,1
15807525,Female,59,29000,1
15574372,Female,58,47000,1
15671249,Male,46,88000,1
15779744,Male,38,71000,0
15624755,Female,54,26000,1
15611430,Female,60,46000,1
15774744,Male,60,83000,1
15629885,Female,39,73000,0
15708791,Male,59,130000,1
15793890,Female,37,80000,0
15646091,Female,46,32000,1
15596984,Female,46,74000,0
15800215,Female,42,53000,0
15577806,Male,41,87000,1
15749381,Female,58,23000,1
15683758,Male,42,64000,0
15670615,Male,48,33000,1
15715622,Female,44,139000,1
15707634,Male,49,28000,1
15806901,Female,57,33000,1
15775335,Male,56,60000,1
15724150,Female,49,39000,1
15627220,Male,39,71000,0
15672330,Male,47,34000,1
15668521,Female,48,35000,1
15807837,Male,48,33000,1
15592570,Male,47,23000,1
15748589,Female,45,45000,1
15635893,Male,60,42000,1
15757632,Female,39,59000,0
15691863,Female,46,41000,1
15706071,Male,51,23000,1
15654296,Female,50,20000,1
15755018,Male,36,33000,0
15594041,Female,49,36000,1
1 User ID Gender Age EstimatedSalary Purchased
2 15624510 Male 19 19000 0
3 15810944 Male 35 20000 0
4 15668575 Female 26 43000 0
5 15603246 Female 27 57000 0
6 15804002 Male 19 76000 0
7 15728773 Male 27 58000 0
8 15598044 Female 27 84000 0
9 15694829 Female 32 150000 1
10 15600575 Male 25 33000 0
11 15727311 Female 35 65000 0
12 15570769 Female 26 80000 0
13 15606274 Female 26 52000 0
14 15746139 Male 20 86000 0
15 15704987 Male 32 18000 0
16 15628972 Male 18 82000 0
17 15697686 Male 29 80000 0
18 15733883 Male 47 25000 1
19 15617482 Male 45 26000 1
20 15704583 Male 46 28000 1
21 15621083 Female 48 29000 1
22 15649487 Male 45 22000 1
23 15736760 Female 47 49000 1
24 15714658 Male 48 41000 1
25 15599081 Female 45 22000 1
26 15705113 Male 46 23000 1
27 15631159 Male 47 20000 1
28 15792818 Male 49 28000 1
29 15633531 Female 47 30000 1
30 15744529 Male 29 43000 0
31 15669656 Male 31 18000 0
32 15581198 Male 31 74000 0
33 15729054 Female 27 137000 1
34 15573452 Female 21 16000 0
35 15776733 Female 28 44000 0
36 15724858 Male 27 90000 0
37 15713144 Male 35 27000 0
38 15690188 Female 33 28000 0
39 15689425 Male 30 49000 0
40 15671766 Female 26 72000 0
41 15782806 Female 27 31000 0
42 15764419 Female 27 17000 0
43 15591915 Female 33 51000 0
44 15772798 Male 35 108000 0
45 15792008 Male 30 15000 0
46 15715541 Female 28 84000 0
47 15639277 Male 23 20000 0
48 15798850 Male 25 79000 0
49 15776348 Female 27 54000 0
50 15727696 Male 30 135000 1
51 15793813 Female 31 89000 0
52 15694395 Female 24 32000 0
53 15764195 Female 18 44000 0
54 15744919 Female 29 83000 0
55 15671655 Female 35 23000 0
56 15654901 Female 27 58000 0
57 15649136 Female 24 55000 0
58 15775562 Female 23 48000 0
59 15807481 Male 28 79000 0
60 15642885 Male 22 18000 0
61 15789109 Female 32 117000 0
62 15814004 Male 27 20000 0
63 15673619 Male 25 87000 0
64 15595135 Female 23 66000 0
65 15583681 Male 32 120000 1
66 15605000 Female 59 83000 0
67 15718071 Male 24 58000 0
68 15679760 Male 24 19000 0
69 15654574 Female 23 82000 0
70 15577178 Female 22 63000 0
71 15595324 Female 31 68000 0
72 15756932 Male 25 80000 0
73 15726358 Female 24 27000 0
74 15595228 Female 20 23000 0
75 15782530 Female 33 113000 0
76 15592877 Male 32 18000 0
77 15651983 Male 34 112000 1
78 15746737 Male 18 52000 0
79 15774179 Female 22 27000 0
80 15667265 Female 28 87000 0
81 15655123 Female 26 17000 0
82 15595917 Male 30 80000 0
83 15668385 Male 39 42000 0
84 15709476 Male 20 49000 0
85 15711218 Male 35 88000 0
86 15798659 Female 30 62000 0
87 15663939 Female 31 118000 1
88 15694946 Male 24 55000 0
89 15631912 Female 28 85000 0
90 15768816 Male 26 81000 0
91 15682268 Male 35 50000 0
92 15684801 Male 22 81000 0
93 15636428 Female 30 116000 0
94 15809823 Male 26 15000 0
95 15699284 Female 29 28000 0
96 15786993 Female 29 83000 0
97 15709441 Female 35 44000 0
98 15710257 Female 35 25000 0
99 15582492 Male 28 123000 1
100 15575694 Male 35 73000 0
101 15756820 Female 28 37000 0
102 15766289 Male 27 88000 0
103 15593014 Male 28 59000 0
104 15584545 Female 32 86000 0
105 15675949 Female 33 149000 1
106 15672091 Female 19 21000 0
107 15801658 Male 21 72000 0
108 15706185 Female 26 35000 0
109 15789863 Male 27 89000 0
110 15720943 Male 26 86000 0
111 15697997 Female 38 80000 0
112 15665416 Female 39 71000 0
113 15660200 Female 37 71000 0
114 15619653 Male 38 61000 0
115 15773447 Male 37 55000 0
116 15739160 Male 42 80000 0
117 15689237 Male 40 57000 0
118 15679297 Male 35 75000 0
119 15591433 Male 36 52000 0
120 15642725 Male 40 59000 0
121 15701962 Male 41 59000 0
122 15811613 Female 36 75000 0
123 15741049 Male 37 72000 0
124 15724423 Female 40 75000 0
125 15574305 Male 35 53000 0
126 15678168 Female 41 51000 0
127 15697020 Female 39 61000 0
128 15610801 Male 42 65000 0
129 15745232 Male 26 32000 0
130 15722758 Male 30 17000 0
131 15792102 Female 26 84000 0
132 15675185 Male 31 58000 0
133 15801247 Male 33 31000 0
134 15725660 Male 30 87000 0
135 15638963 Female 21 68000 0
136 15800061 Female 28 55000 0
137 15578006 Male 23 63000 0
138 15668504 Female 20 82000 0
139 15687491 Male 30 107000 1
140 15610403 Female 28 59000 0
141 15741094 Male 19 25000 0
142 15807909 Male 19 85000 0
143 15666141 Female 18 68000 0
144 15617134 Male 35 59000 0
145 15783029 Male 30 89000 0
146 15622833 Female 34 25000 0
147 15746422 Female 24 89000 0
148 15750839 Female 27 96000 1
149 15749130 Female 41 30000 0
150 15779862 Male 29 61000 0
151 15767871 Male 20 74000 0
152 15679651 Female 26 15000 0
153 15576219 Male 41 45000 0
154 15699247 Male 31 76000 0
155 15619087 Female 36 50000 0
156 15605327 Male 40 47000 0
157 15610140 Female 31 15000 0
158 15791174 Male 46 59000 0
159 15602373 Male 29 75000 0
160 15762605 Male 26 30000 0
161 15598840 Female 32 135000 1
162 15744279 Male 32 100000 1
163 15670619 Male 25 90000 0
164 15599533 Female 37 33000 0
165 15757837 Male 35 38000 0
166 15697574 Female 33 69000 0
167 15578738 Female 18 86000 0
168 15762228 Female 22 55000 0
169 15614827 Female 35 71000 0
170 15789815 Male 29 148000 1
171 15579781 Female 29 47000 0
172 15587013 Male 21 88000 0
173 15570932 Male 34 115000 0
174 15794661 Female 26 118000 0
175 15581654 Female 34 43000 0
176 15644296 Female 34 72000 0
177 15614420 Female 23 28000 0
178 15609653 Female 35 47000 0
179 15594577 Male 25 22000 0
180 15584114 Male 24 23000 0
181 15673367 Female 31 34000 0
182 15685576 Male 26 16000 0
183 15774727 Female 31 71000 0
184 15694288 Female 32 117000 1
185 15603319 Male 33 43000 0
186 15759066 Female 33 60000 0
187 15814816 Male 31 66000 0
188 15724402 Female 20 82000 0
189 15571059 Female 33 41000 0
190 15674206 Male 35 72000 0
191 15715160 Male 28 32000 0
192 15730448 Male 24 84000 0
193 15662067 Female 19 26000 0
194 15779581 Male 29 43000 0
195 15662901 Male 19 70000 0
196 15689751 Male 28 89000 0
197 15667742 Male 34 43000 0
198 15738448 Female 30 79000 0
199 15680243 Female 20 36000 0
200 15745083 Male 26 80000 0
201 15708228 Male 35 22000 0
202 15628523 Male 35 39000 0
203 15708196 Male 49 74000 0
204 15735549 Female 39 134000 1
205 15809347 Female 41 71000 0
206 15660866 Female 58 101000 1
207 15766609 Female 47 47000 0
208 15654230 Female 55 130000 1
209 15794566 Female 52 114000 0
210 15800890 Female 40 142000 1
211 15697424 Female 46 22000 0
212 15724536 Female 48 96000 1
213 15735878 Male 52 150000 1
214 15707596 Female 59 42000 0
215 15657163 Male 35 58000.0 0
216 15622478 Male 47.0 43000 0
217 15779529 Female 60 108000 1
218 15636023 Male 49 65000 0
219 15582066 Male 40 78000 0
220 15666675 Female 46 96000 0
221 15732987 Male 59 143000 1
222 15789432 Female 41 80000 0
223 15663161 Male 35 91000 1
224 15694879 Male 37 144000 1
225 15593715 Male 60 102000 1
226 15575002 Female 35 60000 0
227 15622171 Male 37 53000 0
228 15795224 Female 36 126000 1
229 15685346 Male 56 133000 1
230 15691808 Female 40 72000 0
231 15721007 Female 42 80000 1
232 15794253 Female 35 147000 1
233 15694453 Male 39 42000 0
234 15813113 Male 40 107000 1
235 15614187 Male 49 86000 1
236 15619407 Female 38 112000 0
237 15646227 Male 46 79000 1
238 15660541 Male 40 57000 0
239 15753874 Female 37 80000 0
240 15617877 Female 46 82000 0
241 15772073 Female 53 143000 1
242 15701537 Male 42 149000 1
243 15736228 Male 38 59000 0
244 15780572 Female 50 88000 1
245 15769596 Female 56 104000 1
246 15586996 Female 41 72000 0
247 15722061 Female 51 146000 1
248 15638003 Female 35 50000 0
249 15775590 Female 57 122000 1
250 15730688 Male 41 52000 0
251 15753102 Female 35 97000 1
252 15810075 Female 44 39000 0
253 15723373 Male 37 52000 0
254 15795298 Female 48 134000 1
255 15584320 Female 37 146000 1
256 15724161 Female 50 44000 0
257 15750056 Female 52 90000 1
258 15609637 Female 41 72000 0
259 15794493 Male 40 57000 0
260 15569641 Female 58 95000 1
261 15815236 Female 45 131000 1
262 15811177 Female 35 77000 0
263 15680587 Male 36 144000 1
264 15672821 Female 55 125000 1
265 15767681 Female 35 72000 0
266 15600379 Male 48 90000 1
267 15801336 Female 42 108000 1
268 15721592 Male 40 75000 0
269 15581282 Male 37 74000 0
270 15746203 Female 47 144000 1
271 15583137 Male 40 61000 0
272 15680752 Female 43 133000 0
273 15688172 Female 59 76000 1
274 15791373 Male 60 42000 1
275 15589449 Male 39 106000 1
276 15692819 Female 57 26000 1
277 15727467 Male 57 74000 1
278 15734312 Male 38 71000 0
279 15764604 Male 49 88000 1
280 15613014 Female 52 38000 1
281 15759684 Female 50 36000 1
282 15609669 Female 59 88000 1
283 15685536 Male 35 61000 0
284 15750447 Male 37 70000 1
285 15663249 Female 52 21000 1
286 15638646 Male 48 141000 0
287 15734161 Female 37 93000 1
288 15631070 Female 37 62000 0
289 15761950 Female 48 138000 1
290 15649668 Male 41 79000 0
291 15713912 Female 37 78000 1
292 15586757 Male 39 134000 1
293 15596522 Male 49 89000 1
294 15625395 Male 55 39000 1
295 15760570 Male 37 77000 0
296 15566689 Female 35 57000 0
297 15725794 Female 36 63000 0
298 15673539 Male 42 73000 1
299 15705298 Female 43 112000 1
300 15675791 Male 45 79000 0
301 15747043 Male 46 117000 1
302 15736397 Female 58 38000 1
303 15678201 Male 48 74000 1
304 15720745 Female 37 137000 1
305 15637593 Male 37 79000 1
306 15598070 Female 40 60000 0
307 15787550 Male 42 54000 0
308 15603942 Female 51 134000 0
309 15733973 Female 47 113000 1
310 15596761 Male 36 125000 1
311 15652400 Female 38 50000 0
312 15717893 Female 42 70000 0
313 15622585 Male 39 96000 1
314 15733964 Female 38 50000 0
315 15753861 Female 49 141000 1
316 15747097 Female 39 79000 0
317 15594762 Female 39 75000 1
318 15667417 Female 54 104000 1
319 15684861 Male 35 55000 0
320 15742204 Male 45 32000 1
321 15623502 Male 36 60000 0
322 15774872 Female 52 138000 1
323 15611191 Female 53 82000 1
324 15674331 Male 41 52000 0
325 15619465 Female 48 30000 1
326 15575247 Female 48 131000 1
327 15695679 Female 41 60000 0
328 15713463 Male 41 72000 0
329 15785170 Female 42 75000 0
330 15796351 Male 36 118000 1
331 15639576 Female 47 107000 1
332 15693264 Male 38 51000 0
333 15589715 Female 48 119000 1
334 15769902 Male 42 65000 0
335 15587177 Male 40 65000 0
336 15814553 Male 57 60000 1
337 15601550 Female 36 54000 0
338 15664907 Male 58 144000 1
339 15612465 Male 35 79000 0
340 15810800 Female 38 55000 0
341 15665760 Male 39 122000 1
342 15588080 Female 53 104000 1
343 15776844 Male 35 75000 0
344 15717560 Female 38 65000 0
345 15629739 Female 47 51000 1
346 15729908 Male 47 105000 1
347 15716781 Female 41 63000 0
348 15646936 Male 53 72000 1
349 15768151 Female 54 108000 1
350 15579212 Male 39 77000 0
351 15721835 Male 38 61000 0
352 15800515 Female 38 113000 1
353 15591279 Male 37 75000 0
354 15587419 Female 42 90000 1
355 15750335 Female 37 57000 0
356 15699619 Male 36 99000 1
357 15606472 Male 60 34000 1
358 15778368 Male 54 70000 1
359 15671387 Female 41 72000 0
360 15573926 Male 40 71000 1
361 15709183 Male 42 54000 0
362 15577514 Male 43 129000 1
363 15778830 Female 53 34000 1
364 15768072 Female 47 50000 1
365 15768293 Female 42 79000 0
366 15654456 Male 42 104000 1
367 15807525 Female 59 29000 1
368 15574372 Female 58 47000 1
369 15671249 Male 46 88000 1
370 15779744 Male 38 71000 0
371 15624755 Female 54 26000 1
372 15611430 Female 60 46000 1
373 15774744 Male 60 83000 1
374 15629885 Female 39 73000 0
375 15708791 Male 59 130000 1
376 15793890 Female 37 80000 0
377 15646091 Female 46 32000 1
378 15596984 Female 46 74000 0
379 15800215 Female 42 53000 0
380 15577806 Male 41 87000 1
381 15749381 Female 58 23000 1
382 15683758 Male 42 64000 0
383 15670615 Male 48 33000 1
384 15715622 Female 44 139000 1
385 15707634 Male 49 28000 1
386 15806901 Female 57 33000 1
387 15775335 Male 56 60000 1
388 15724150 Female 49 39000 1
389 15627220 Male 39 71000 0
390 15672330 Male 47 34000 1
391 15668521 Female 48 35000 1
392 15807837 Male 48 33000 1
393 15592570 Male 47 23000 1
394 15748589 Female 45 45000 1
395 15635893 Male 60 42000 1
396 15757632 Female 39 59000 0
397 15691863 Female 46 41000 1
398 15706071 Male 51 23000 1
399 15654296 Female 50 20000 1
400 15755018 Male 36 33000 0
401 15594041 Female 49 36000 1

56
section_3_classification/section_3_6_random_forest/main.py Normal file
View File

@ -0,0 +1,56 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Social_Network_Ads.csv")
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, 4].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# 擬合和預測
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators=10, random_state=0, criterion='entropy')
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, Y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue'))(i), label = j)
plt.title('Random Forest (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

201
section_4_K-means_clustering/Mall_Customers.csv Normal file
View File

@ -0,0 +1,201 @@
CustomerID,Genre,Age,Annual Income (k$),Spending Score (1-100)
0001,Male,19,15,39
0002,Male,21,15,81
0003,Female,20,16,6
0004,Female,23,16,77
0005,Female,31,17,40
0006,Female,22,17,76
0007,Female,35,18,6
0008,Female,23,18,94
0009,Male,64,19,3
0010,Female,30,19,72
0011,Male,67,19,14
0012,Female,35,19,99
0013,Female,58,20,15
0014,Female,24,20,77
0015,Male,37,20,13
0016,Male,22,20,79
0017,Female,35,21,35
0018,Male,20,21,66
0019,Male,52,23,29
0020,Female,35,23,98
0021,Male,35,24,35
0022,Male,25,24,73
0023,Female,46,25,5
0024,Male,31,25,73
0025,Female,54,28,14
0026,Male,29,28,82
0027,Female,45,28,32
0028,Male,35,28,61
0029,Female,40,29,31
0030,Female,23,29,87
0031,Male,60,30,4
0032,Female,21,30,73
0033,Male,53,33,4
0034,Male,18,33,92
0035,Female,49,33,14
0036,Female,21,33,81
0037,Female,42,34,17
0038,Female,30,34,73
0039,Female,36,37,26
0040,Female,20,37,75
0041,Female,65,38,35
0042,Male,24,38,92
0043,Male,48,39,36
0044,Female,31,39,61
0045,Female,49,39,28
0046,Female,24,39,65
0047,Female,50,40,55
0048,Female,27,40,47
0049,Female,29,40,42
0050,Female,31,40,42
0051,Female,49,42,52
0052,Male,33,42,60
0053,Female,31,43,54
0054,Male,59,43,60
0055,Female,50,43,45
0056,Male,47,43,41
0057,Female,51,44,50
0058,Male,69,44,46
0059,Female,27,46,51
0060,Male,53,46,46
0061,Male,70,46,56
0062,Male,19,46,55
0063,Female,67,47,52
0064,Female,54,47,59
0065,Male,63,48,51
0066,Male,18,48,59
0067,Female,43,48,50
0068,Female,68,48,48
0069,Male,19,48,59
0070,Female,32,48,47
0071,Male,70,49,55
0072,Female,47,49,42
0073,Female,60,50,49
0074,Female,60,50,56
0075,Male,59,54,47
0076,Male,26,54,54
0077,Female,45,54,53
0078,Male,40,54,48
0079,Female,23,54,52
0080,Female,49,54,42
0081,Male,57,54,51
0082,Male,38,54,55
0083,Male,67,54,41
0084,Female,46,54,44
0085,Female,21,54,57
0086,Male,48,54,46
0087,Female,55,57,58
0088,Female,22,57,55
0089,Female,34,58,60
0090,Female,50,58,46
0091,Female,68,59,55
0092,Male,18,59,41
0093,Male,48,60,49
0094,Female,40,60,40
0095,Female,32,60,42
0096,Male,24,60,52
0097,Female,47,60,47
0098,Female,27,60,50
0099,Male,48,61,42
0100,Male,20,61,49
0101,Female,23,62,41
0102,Female,49,62,48
0103,Male,67,62,59
0104,Male,26,62,55
0105,Male,49,62,56
0106,Female,21,62,42
0107,Female,66,63,50
0108,Male,54,63,46
0109,Male,68,63,43
0110,Male,66,63,48
0111,Male,65,63,52
0112,Female,19,63,54
0113,Female,38,64,42
0114,Male,19,64,46
0115,Female,18,65,48
0116,Female,19,65,50
0117,Female,63,65,43
0118,Female,49,65,59
0119,Female,51,67,43
0120,Female,50,67,57
0121,Male,27,67,56
0122,Female,38,67,40
0123,Female,40,69,58
0124,Male,39,69,91
0125,Female,23,70,29
0126,Female,31,70,77
0127,Male,43,71,35
0128,Male,40,71,95
0129,Male,59,71,11
0130,Male,38,71,75
0131,Male,47,71,9
0132,Male,39,71,75
0133,Female,25,72,34
0134,Female,31,72,71
0135,Male,20,73,5
0136,Female,29,73,88
0137,Female,44,73,7
0138,Male,32,73,73
0139,Male,19,74,10
0140,Female,35,74,72
0141,Female,57,75,5
0142,Male,32,75,93
0143,Female,28,76,40
0144,Female,32,76,87
0145,Male,25,77,12
0146,Male,28,77,97
0147,Male,48,77,36
0148,Female,32,77,74
0149,Female,34,78,22
0150,Male,34,78,90
0151,Male,43,78,17
0152,Male,39,78,88
0153,Female,44,78,20
0154,Female,38,78,76
0155,Female,47,78,16
0156,Female,27,78,89
0157,Male,37,78,1
0158,Female,30,78,78
0159,Male,34,78,1
0160,Female,30,78,73
0161,Female,56,79,35
0162,Female,29,79,83
0163,Male,19,81,5
0164,Female,31,81,93
0165,Male,50,85,26
0166,Female,36,85,75
0167,Male,42,86,20
0168,Female,33,86,95
0169,Female,36,87,27
0170,Male,32,87,63
0171,Male,40,87,13
0172,Male,28,87,75
0173,Male,36,87,10
0174,Male,36,87,92
0175,Female,52,88,13
0176,Female,30,88,86
0177,Male,58,88,15
0178,Male,27,88,69
0179,Male,59,93,14
0180,Male,35,93,90
0181,Female,37,97,32
0182,Female,32,97,86
0183,Male,46,98,15
0184,Female,29,98,88
0185,Female,41,99,39
0186,Male,30,99,97
0187,Female,54,101,24
0188,Male,28,101,68
0189,Female,41,103,17
0190,Female,36,103,85
0191,Female,34,103,23
0192,Female,32,103,69
0193,Male,33,113,8
0194,Female,38,113,91
0195,Female,47,120,16
0196,Female,35,120,79
0197,Female,45,126,28
0198,Male,32,126,74
0199,Male,32,137,18
0200,Male,30,137,83
1 CustomerID Genre Age Annual Income (k$) Spending Score (1-100)
2 0001 Male 19 15 39
3 0002 Male 21 15 81
4 0003 Female 20 16 6
5 0004 Female 23 16 77
6 0005 Female 31 17 40
7 0006 Female 22 17 76
8 0007 Female 35 18 6
9 0008 Female 23 18 94
10 0009 Male 64 19 3
11 0010 Female 30 19 72
12 0011 Male 67 19 14
13 0012 Female 35 19 99
14 0013 Female 58 20 15
15 0014 Female 24 20 77
16 0015 Male 37 20 13
17 0016 Male 22 20 79
18 0017 Female 35 21 35
19 0018 Male 20 21 66
20 0019 Male 52 23 29
21 0020 Female 35 23 98
22 0021 Male 35 24 35
23 0022 Male 25 24 73
24 0023 Female 46 25 5
25 0024 Male 31 25 73
26 0025 Female 54 28 14
27 0026 Male 29 28 82
28 0027 Female 45 28 32
29 0028 Male 35 28 61
30 0029 Female 40 29 31
31 0030 Female 23 29 87
32 0031 Male 60 30 4
33 0032 Female 21 30 73
34 0033 Male 53 33 4
35 0034 Male 18 33 92
36 0035 Female 49 33 14
37 0036 Female 21 33 81
38 0037 Female 42 34 17
39 0038 Female 30 34 73
40 0039 Female 36 37 26
41 0040 Female 20 37 75
42 0041 Female 65 38 35
43 0042 Male 24 38 92
44 0043 Male 48 39 36
45 0044 Female 31 39 61
46 0045 Female 49 39 28
47 0046 Female 24 39 65
48 0047 Female 50 40 55
49 0048 Female 27 40 47
50 0049 Female 29 40 42
51 0050 Female 31 40 42
52 0051 Female 49 42 52
53 0052 Male 33 42 60
54 0053 Female 31 43 54
55 0054 Male 59 43 60
56 0055 Female 50 43 45
57 0056 Male 47 43 41
58 0057 Female 51 44 50
59 0058 Male 69 44 46
60 0059 Female 27 46 51
61 0060 Male 53 46 46
62 0061 Male 70 46 56
63 0062 Male 19 46 55
64 0063 Female 67 47 52
65 0064 Female 54 47 59
66 0065 Male 63 48 51
67 0066 Male 18 48 59
68 0067 Female 43 48 50
69 0068 Female 68 48 48
70 0069 Male 19 48 59
71 0070 Female 32 48 47
72 0071 Male 70 49 55
73 0072 Female 47 49 42
74 0073 Female 60 50 49
75 0074 Female 60 50 56
76 0075 Male 59 54 47
77 0076 Male 26 54 54
78 0077 Female 45 54 53
79 0078 Male 40 54 48
80 0079 Female 23 54 52
81 0080 Female 49 54 42
82 0081 Male 57 54 51
83 0082 Male 38 54 55
84 0083 Male 67 54 41
85 0084 Female 46 54 44
86 0085 Female 21 54 57
87 0086 Male 48 54 46
88 0087 Female 55 57 58
89 0088 Female 22 57 55
90 0089 Female 34 58 60
91 0090 Female 50 58 46
92 0091 Female 68 59 55
93 0092 Male 18 59 41
94 0093 Male 48 60 49
95 0094 Female 40 60 40
96 0095 Female 32 60 42
97 0096 Male 24 60 52
98 0097 Female 47 60 47
99 0098 Female 27 60 50
100 0099 Male 48 61 42
101 0100 Male 20 61 49
102 0101 Female 23 62 41
103 0102 Female 49 62 48
104 0103 Male 67 62 59
105 0104 Male 26 62 55
106 0105 Male 49 62 56
107 0106 Female 21 62 42
108 0107 Female 66 63 50
109 0108 Male 54 63 46
110 0109 Male 68 63 43
111 0110 Male 66 63 48
112 0111 Male 65 63 52
113 0112 Female 19 63 54
114 0113 Female 38 64 42
115 0114 Male 19 64 46
116 0115 Female 18 65 48
117 0116 Female 19 65 50
118 0117 Female 63 65 43
119 0118 Female 49 65 59
120 0119 Female 51 67 43
121 0120 Female 50 67 57
122 0121 Male 27 67 56
123 0122 Female 38 67 40
124 0123 Female 40 69 58
125 0124 Male 39 69 91
126 0125 Female 23 70 29
127 0126 Female 31 70 77
128 0127 Male 43 71 35
129 0128 Male 40 71 95
130 0129 Male 59 71 11
131 0130 Male 38 71 75
132 0131 Male 47 71 9
133 0132 Male 39 71 75
134 0133 Female 25 72 34
135 0134 Female 31 72 71
136 0135 Male 20 73 5
137 0136 Female 29 73 88
138 0137 Female 44 73 7
139 0138 Male 32 73 73
140 0139 Male 19 74 10
141 0140 Female 35 74 72
142 0141 Female 57 75 5
143 0142 Male 32 75 93
144 0143 Female 28 76 40
145 0144 Female 32 76 87
146 0145 Male 25 77 12
147 0146 Male 28 77 97
148 0147 Male 48 77 36
149 0148 Female 32 77 74
150 0149 Female 34 78 22
151 0150 Male 34 78 90
152 0151 Male 43 78 17
153 0152 Male 39 78 88
154 0153 Female 44 78 20
155 0154 Female 38 78 76
156 0155 Female 47 78 16
157 0156 Female 27 78 89
158 0157 Male 37 78 1
159 0158 Female 30 78 78
160 0159 Male 34 78 1
161 0160 Female 30 78 73
162 0161 Female 56 79 35
163 0162 Female 29 79 83
164 0163 Male 19 81 5
165 0164 Female 31 81 93
166 0165 Male 50 85 26
167 0166 Female 36 85 75
168 0167 Male 42 86 20
169 0168 Female 33 86 95
170 0169 Female 36 87 27
171 0170 Male 32 87 63
172 0171 Male 40 87 13
173 0172 Male 28 87 75
174 0173 Male 36 87 10
175 0174 Male 36 87 92
176 0175 Female 52 88 13
177 0176 Female 30 88 86
178 0177 Male 58 88 15
179 0178 Male 27 88 69
180 0179 Male 59 93 14
181 0180 Male 35 93 90
182 0181 Female 37 97 32
183 0182 Female 32 97 86
184 0183 Male 46 98 15
185 0184 Female 29 98 88
186 0185 Female 41 99 39
187 0186 Male 30 99 97
188 0187 Female 54 101 24
189 0188 Male 28 101 68
190 0189 Female 41 103 17
191 0190 Female 36 103 85
192 0191 Female 34 103 23
193 0192 Female 32 103 69
194 0193 Male 33 113 8
195 0194 Female 38 113 91
196 0195 Female 47 120 16
197 0196 Female 35 120 79
198 0197 Female 45 126 28
199 0198 Male 32 126 74
200 0199 Male 32 137 18
201 0200 Male 30 137 83

52
section_4_K-means_clustering/main.py Normal file
View File

@ -0,0 +1,52 @@
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# 資料預處理
dataset = pd.read_csv("Mall_Customers.csv")
X = dataset.iloc[:, 3:5].values # 無監督學習，無需應變數
# 獲取 K，得到結果 K = 5
from sklearn.cluster import KMeans
# wcss = []
#
# for i in range(1, 11):
# kmeans = KMeans(n_clusters=i, max_iter=300, n_init=10, init='k-means++', random_state=0)
# kmeans.fit(X)
# wcss.append(kmeans.inertia_)
#
# plt.plot(range(1, 11), wcss)
# plt.title('The Elbow Method')
# plt.xlabel('Number of clusters')
# plt.ylabel('WCSS')
# plt.show()
# 開始分析
kmeans = KMeans(n_clusters=5, max_iter=300, n_init=10, init='k-means++', random_state=0)
Y_kmeans = kmeans.fit_predict(X)
print(Y_kmeans)
# 視覺化
plt.scatter(X[Y_kmeans == 0, 0], X[Y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[Y_kmeans == 1, 0], X[Y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[Y_kmeans == 2, 0], X[Y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[Y_kmeans == 3, 0], X[Y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[Y_kmeans == 4, 0], X[Y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()

7501
section_5_apriori/Market_Basket_Optimisation.csv Normal file
View File

File diff suppressed because it is too large Load Diff

441
section_5_apriori/apyori.py Executable file
View File

@ -0,0 +1,441 @@
#!/usr/bin/env python
"""
a simple implementation of Apriori algorithm by Python.
"""
import sys
import csv
import argparse
import json
import os
from collections import namedtuple
from itertools import combinations
from itertools import chain
# Meta informations.
__version__ = '1.1.1'
__author__ = 'Yu Mochizuki'
__author_email__ = 'ymoch.dev@gmail.com'
################################################################################
# Data structures.
################################################################################
class TransactionManager(object):
"""
Transaction managers.
"""
def __init__(self, transactions):
"""
Initialize.
Arguments:
transactions -- A transaction iterable object
(eg. [['A', 'B'], ['B', 'C']]).
"""
self.__num_transaction = 0
self.__items = []
self.__transaction_index_map = {}
for transaction in transactions:
self.add_transaction(transaction)
def add_transaction(self, transaction):
"""
Add a transaction.
Arguments:
transaction -- A transaction as an iterable object (eg. ['A', 'B']).
"""
for item in transaction:
if item not in self.__transaction_index_map:
self.__items.append(item)
self.__transaction_index_map[item] = set()
self.__transaction_index_map[item].add(self.__num_transaction)
self.__num_transaction += 1
def calc_support(self, items):
"""
Returns a support for items.
Arguments:
items -- Items as an iterable object (eg. ['A', 'B']).
"""
# Empty items is supported by all transactions.
if not items:
return 1.0
# Empty transactions supports no items.
if not self.num_transaction:
return 0.0
# Create the transaction index intersection.
sum_indexes = None
for item in items:
indexes = self.__transaction_index_map.get(item)
if indexes is None:
# No support for any set that contains a not existing item.
return 0.0
if sum_indexes is None:
# Assign the indexes on the first time.
sum_indexes = indexes
else:
# Calculate the intersection on not the first time.
sum_indexes = sum_indexes.intersection(indexes)
# Calculate and return the support.
return float(len(sum_indexes)) / self.__num_transaction
def initial_candidates(self):
"""
Returns the initial candidates.
"""
return [frozenset([item]) for item in self.items]
@property
def num_transaction(self):
"""
Returns the number of transactions.
"""
return self.__num_transaction
@property
def items(self):
"""
Returns the item list that the transaction is consisted of.
"""
return sorted(self.__items)
@staticmethod
def create(transactions):
"""
Create the TransactionManager with a transaction instance.
If the given instance is a TransactionManager, this returns itself.
"""
if isinstance(transactions, TransactionManager):
return transactions
return TransactionManager(transactions)
# Ignore name errors because these names are namedtuples.
SupportRecord = namedtuple( # pylint: disable=C0103
'SupportRecord', ('items', 'support'))
RelationRecord = namedtuple( # pylint: disable=C0103
'RelationRecord', SupportRecord._fields + ('ordered_statistics',))
OrderedStatistic = namedtuple( # pylint: disable=C0103
'OrderedStatistic', ('items_base', 'items_add', 'confidence', 'lift',))
################################################################################
# Inner functions.
################################################################################
def create_next_candidates(prev_candidates, length):
"""
Returns the apriori candidates as a list.
Arguments:
prev_candidates -- Previous candidates as a list.
length -- The lengths of the next candidates.
"""
# Solve the items.
item_set = set()
for candidate in prev_candidates:
for item in candidate:
item_set.add(item)
items = sorted(item_set)
# Create the temporary candidates. These will be filtered below.
tmp_next_candidates = (frozenset(x) for x in combinations(items, length))
# Return all the candidates if the length of the next candidates is 2
# because their subsets are the same as items.
if length < 3:
return list(tmp_next_candidates)
# Filter candidates that all of their subsets are
# in the previous candidates.
next_candidates = [
candidate for candidate in tmp_next_candidates
if all(
True if frozenset(x) in prev_candidates else False
for x in combinations(candidate, length - 1))
]
return next_candidates
def gen_support_records(transaction_manager, min_support, **kwargs):
"""
Returns a generator of support records with given transactions.
Arguments:
transaction_manager -- Transactions as a TransactionManager instance.
min_support -- A minimum support (float).
Keyword arguments:
max_length -- The maximum length of relations (integer).
"""
# Parse arguments.
max_length = kwargs.get('max_length')
# For testing.
_create_next_candidates = kwargs.get(
'_create_next_candidates', create_next_candidates)
# Process.
candidates = transaction_manager.initial_candidates()
length = 1
while candidates:
relations = set()
for relation_candidate in candidates:
support = transaction_manager.calc_support(relation_candidate)
if support < min_support:
continue
candidate_set = frozenset(relation_candidate)
relations.add(candidate_set)
yield SupportRecord(candidate_set, support)
length += 1
if max_length and length > max_length:
break
candidates = _create_next_candidates(relations, length)
def gen_ordered_statistics(transaction_manager, record):
"""
Returns a generator of ordered statistics as OrderedStatistic instances.
Arguments:
transaction_manager -- Transactions as a TransactionManager instance.
record -- A support record as a SupportRecord instance.
"""
items = record.items
for combination_set in combinations(sorted(items), len(items) - 1):
items_base = frozenset(combination_set)
items_add = frozenset(items.difference(items_base))
confidence = (
record.support / transaction_manager.calc_support(items_base))
lift = confidence / transaction_manager.calc_support(items_add)
yield OrderedStatistic(
frozenset(items_base), frozenset(items_add), confidence, lift)
def filter_ordered_statistics(ordered_statistics, **kwargs):
"""
Filter OrderedStatistic objects.
Arguments:
ordered_statistics -- A OrderedStatistic iterable object.
Keyword arguments:
min_confidence -- The minimum confidence of relations (float).
min_lift -- The minimum lift of relations (float).
"""
min_confidence = kwargs.get('min_confidence', 0.0)
min_lift = kwargs.get('min_lift', 0.0)
for ordered_statistic in ordered_statistics:
if ordered_statistic.confidence < min_confidence:
continue
if ordered_statistic.lift < min_lift:
continue
yield ordered_statistic
################################################################################
# API function.
################################################################################
def apriori(transactions, **kwargs):
"""
Executes Apriori algorithm and returns a RelationRecord generator.
Arguments:
transactions -- A transaction iterable object
(eg. [['A', 'B'], ['B', 'C']]).
Keyword arguments:
min_support -- The minimum support of relations (float).
min_confidence -- The minimum confidence of relations (float).
min_lift -- The minimum lift of relations (float).
max_length -- The maximum length of the relation (integer).
"""
# Parse the arguments.
min_support = kwargs.get('min_support', 0.1)
min_confidence = kwargs.get('min_confidence', 0.0)
min_lift = kwargs.get('min_lift', 0.0)
max_length = kwargs.get('max_length', None)
# Check arguments.
if min_support <= 0:
raise ValueError('minimum support must be > 0')
# For testing.
_gen_support_records = kwargs.get(
'_gen_support_records', gen_support_records)
_gen_ordered_statistics = kwargs.get(
'_gen_ordered_statistics', gen_ordered_statistics)
_filter_ordered_statistics = kwargs.get(
'_filter_ordered_statistics', filter_ordered_statistics)
# Calculate supports.
transaction_manager = TransactionManager.create(transactions)
support_records = _gen_support_records(
transaction_manager, min_support, max_length=max_length)
# Calculate ordered stats.
for support_record in support_records:
ordered_statistics = list(
_filter_ordered_statistics(
_gen_ordered_statistics(transaction_manager, support_record),
min_confidence=min_confidence,
min_lift=min_lift,
)
)
if not ordered_statistics:
continue
yield RelationRecord(
support_record.items, support_record.support, ordered_statistics)
################################################################################
# Application functions.
################################################################################
def parse_args(argv):
"""
Parse commandline arguments.
Arguments:
argv -- An argument list without the program name.
"""
output_funcs = {
'json': dump_as_json,
'tsv': dump_as_two_item_tsv,
}
default_output_func_key = 'json'
parser = argparse.ArgumentParser()
parser.add_argument(
'-v', '--version', action='version',
version='%(prog)s {0}'.format(__version__))
parser.add_argument(
'input', metavar='inpath', nargs='*',
help='Input transaction file (default: stdin).',
type=argparse.FileType('r'), default=[sys.stdin])
parser.add_argument(
'-o', '--output', metavar='outpath',
help='Output file (default: stdout).',
type=argparse.FileType('w'), default=sys.stdout)
parser.add_argument(
'-l', '--max-length', metavar='int',
help='Max length of relations (default: infinite).',
type=int, default=None)
parser.add_argument(
'-s', '--min-support', metavar='float',
help='Minimum support ratio (must be > 0, default: 0.1).',
type=float, default=0.1)
parser.add_argument(
'-c', '--min-confidence', metavar='float',
help='Minimum confidence (default: 0.5).',
type=float, default=0.5)
parser.add_argument(
'-t', '--min-lift', metavar='float',
help='Minimum lift (default: 0.0).',
type=float, default=0.0)
parser.add_argument(
'-d', '--delimiter', metavar='str',
help='Delimiter for items of transactions (default: tab).',
type=str, default='\t')
parser.add_argument(
'-f', '--out-format', metavar='str',
help='Output format ({0}; default: {1}).'.format(
', '.join(output_funcs.keys()), default_output_func_key),
type=str, choices=output_funcs.keys(), default=default_output_func_key)
args = parser.parse_args(argv)
args.output_func = output_funcs[args.out_format]
return args
def load_transactions(input_file, **kwargs):
"""
Load transactions and returns a generator for transactions.
Arguments:
input_file -- An input file.
Keyword arguments:
delimiter -- The delimiter of the transaction.
"""
delimiter = kwargs.get('delimiter', '\t')
for transaction in csv.reader(input_file, delimiter=delimiter):
yield transaction if transaction else ['']
def dump_as_json(record, output_file):
"""
Dump an relation record as a json value.
Arguments:
record -- A RelationRecord instance to dump.
output_file -- A file to output.
"""
def default_func(value):
"""
Default conversion for JSON value.
"""
if isinstance(value, frozenset):
return sorted(value)
raise TypeError(repr(value) + " is not JSON serializable")
converted_record = record._replace(
ordered_statistics=[x._asdict() for x in record.ordered_statistics])
json.dump(
converted_record._asdict(), output_file,
default=default_func, ensure_ascii=False)
output_file.write(os.linesep)
def dump_as_two_item_tsv(record, output_file):
"""
Dump a relation record as TSV only for 2 item relations.
Arguments:
record -- A RelationRecord instance to dump.
output_file -- A file to output.
"""
for ordered_stats in record.ordered_statistics:
if len(ordered_stats.items_base) != 1:
continue
if len(ordered_stats.items_add) != 1:
continue
output_file.write('{0}\t{1}\t{2:.8f}\t{3:.8f}\t{4:.8f}{5}'.format(
list(ordered_stats.items_base)[0], list(ordered_stats.items_add)[0],
record.support, ordered_stats.confidence, ordered_stats.lift,
os.linesep))
def main(**kwargs):
"""
Executes Apriori algorithm and print its result.
"""
# For tests.
_parse_args = kwargs.get('_parse_args', parse_args)
_load_transactions = kwargs.get('_load_transactions', load_transactions)
_apriori = kwargs.get('_apriori', apriori)
args = _parse_args(sys.argv[1:])
transactions = _load_transactions(
chain(*args.input), delimiter=args.delimiter)
result = _apriori(
transactions,
max_length=args.max_length,
min_support=args.min_support,
min_confidence=args.min_confidence)
for record in result:
args.output_func(record, args.output)
if __name__ == '__main__':
main()

18
section_5_apriori/main.py Normal file
View File

@ -0,0 +1,18 @@
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
dataset = pd.read_csv('Market_Basket_Optimisation.csv', header=None)
transactions = []
for i in range(0, 7501):
transactions.append([str(dataset.values[i, j]) for j in range(0, 20)])
from apyori import apriori
rules = apriori(transactions, min_lengt = 2, min_support=0.003, min_confidence=0.2, min_lift=3)
results = list(rules)
print(results)

10001
section_6_ucb/Ads_CTR_Optimisation.csv Normal file
View File

File diff suppressed because it is too large Load Diff

42
section_6_ucb/main.py Normal file
View File

@ -0,0 +1,42 @@
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import math
dataset = pd.read_csv('Ads_CTR_Optimisation.csv')
# 第一步，計算 N_i(n) 和 R_i(n)
N = 10000 # 輪數
d = 10 # 廣告數
numbers_of_selections = [0] * d # 每個廣告被選中的次數
sums_of_rewards = [0] * d # 每個廣告的獎勵總和
ads_selected = [] # 選擇的廣告
total_reward = 0 # 總獎勵
# 第二步
for n in range(0, N):
ad = 0 # 最大 UCB 的廣告
max_upper_bound = 0 # 最大 UCB
for i in range(0, d):
if numbers_of_selections[i] > 0:
average_award = sums_of_rewards[i] / numbers_of_selections[i] # 平均獎勵
delta_i = math.sqrt(3/2 * math.log(n + 1) / numbers_of_selections[i]) # Delta_i(n)
upper_bound = average_award + delta_i # UCB
else:
upper_bound = 1e400
if upper_bound > max_upper_bound:
max_upper_bound = upper_bound
ad = i # 選擇擁有最大 UCB 的廣告 i
ads_selected.append(ad)
reward = dataset.values[n, ad] # 獎勵
numbers_of_selections[ad] = numbers_of_selections[ad] + 1
sums_of_rewards[ad] = sums_of_rewards[ad] + reward
total_reward = total_reward + reward
print(total_reward)
plt.hist(ads_selected)
plt.title('Histogram of ads selections')
plt.xlabel('Ads')
plt.ylabel('Number of times each ad was selected')
plt.show()

28
section_6_ucb/random_selection.py Normal file
View File

@ -0,0 +1,28 @@
# Random Selection
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Ads_CTR_Optimisation.csv')
# Implementing Random Selection
import random
N = 10000
d = 10
ads_selected = []
total_reward = 0
for n in range(0, N):
ad = random.randrange(d)
ads_selected.append(ad)
reward = dataset.values[n, ad]
total_reward = total_reward + reward
# Visualising the results
plt.hist(ads_selected)
plt.title('Histogram of ads selections')
plt.xlabel('Ads')
plt.ylabel('Number of times each ad was selected')
plt.show()

10001
section_7_thompson_sampling/Ads_CTR_Optimisation.csv Normal file
View File

File diff suppressed because it is too large Load Diff

44
section_7_thompson_sampling/main.py Normal file
View File

@ -0,0 +1,44 @@
import random
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Ads_CTR_Optimisation.csv')
# 第一步，計算 N_i(n) 和 R_i(n)
N = 10000 # 輪數
d = 10 # 廣告數
numbers_of_rewards_1 = [0] * d
numbers_of_rewards_0 = [0] * d
ads_selected = [] # 選擇的廣告
total_reward = 0 # 總獎勵
# 第二步
for n in range(0, N):
ad = 0 # 最大 UCB 的廣告
max_random = 0 # 最大 UCB
for i in range(0, d):
random_beta = random.betavariate(numbers_of_rewards_1[i] + 1, numbers_of_rewards_0[i] + 1)
if random_beta > max_random:
max_random = random_beta
ad = i
ads_selected.append(ad)
reward = dataset.values[n, ad] # 獎勵
if reward == 1:
numbers_of_rewards_1[ad] += 1
else:
numbers_of_rewards_0[ad] += 1
total_reward = total_reward + reward
print(total_reward)
plt.hist(ads_selected)
plt.title('Histogram of ads selections')
plt.xlabel('Ads')
plt.ylabel('Number of times each ad was selected')
plt.show()

1001
section_8_natural_language_processing/Restaurant_Reviews.tsv Normal file
View File

File diff suppressed because it is too large Load Diff

52
section_8_natural_language_processing/main.py Normal file
View File

@ -0,0 +1,52 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
dataset = pd.read_csv("Restaurant_Reviews.tsv", delimiter="\t", quoting=3)
import re
# import nltk
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
# nltk.download('stopwords')
ps = PorterStemmer()
corpus = []
for i in range(0, 1000):
review = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])
review = review.lower()
review = review.split()
review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]
review = ' '.join(review)
corpus.append(review)
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features=1500)
X = cv.fit_transform(corpus).toarray()
Y = dataset.iloc[:, 1].values
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.20, random_state = 0)
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
print(Y_pred)
print(Y_test)
count = 0
for i in range(0,len(Y_pred)):
if Y_pred[i] == Y_test[i]:
count += 1
print(count / len(Y_pred))

179
section_9_pca/Wine.csv Normal file
View File

@ -0,0 +1,179 @@
Alcohol,Malic_Acid,Ash,Ash_Alcanity,Magnesium,Total_Phenols,Flavanoids,Nonflavanoid_Phenols,Proanthocyanins,Color_Intensity,Hue,OD280,Proline,Customer_Segment
14.23,1.71,2.43,15.6,127,2.8,3.06,0.28,2.29,5.64,1.04,3.92,1065,1
13.2,1.78,2.14,11.2,100,2.65,2.76,0.26,1.28,4.38,1.05,3.4,1050,1
13.16,2.36,2.67,18.6,101,2.8,3.24,0.3,2.81,5.68,1.03,3.17,1185,1
14.37,1.95,2.5,16.8,113,3.85,3.49,0.24,2.18,7.8,0.86,3.45,1480,1
13.24,2.59,2.87,21,118,2.8,2.69,0.39,1.82,4.32,1.04,2.93,735,1
14.2,1.76,2.45,15.2,112,3.27,3.39,0.34,1.97,6.75,1.05,2.85,1450,1
14.39,1.87,2.45,14.6,96,2.5,2.52,0.3,1.98,5.25,1.02,3.58,1290,1
14.06,2.15,2.61,17.6,121,2.6,2.51,0.31,1.25,5.05,1.06,3.58,1295,1
14.83,1.64,2.17,14,97,2.8,2.98,0.29,1.98,5.2,1.08,2.85,1045,1
13.86,1.35,2.27,16,98,2.98,3.15,0.22,1.85,7.22,1.01,3.55,1045,1
14.1,2.16,2.3,18,105,2.95,3.32,0.22,2.38,5.75,1.25,3.17,1510,1
14.12,1.48,2.32,16.8,95,2.2,2.43,0.26,1.57,5,1.17,2.82,1280,1
13.75,1.73,2.41,16,89,2.6,2.76,0.29,1.81,5.6,1.15,2.9,1320,1
14.75,1.73,2.39,11.4,91,3.1,3.69,0.43,2.81,5.4,1.25,2.73,1150,1
14.38,1.87,2.38,12,102,3.3,3.64,0.29,2.96,7.5,1.2,3,1547,1
13.63,1.81,2.7,17.2,112,2.85,2.91,0.3,1.46,7.3,1.28,2.88,1310,1
14.3,1.92,2.72,20,120,2.8,3.14,0.33,1.97,6.2,1.07,2.65,1280,1
13.83,1.57,2.62,20,115,2.95,3.4,0.4,1.72,6.6,1.13,2.57,1130,1
14.19,1.59,2.48,16.5,108,3.3,3.93,0.32,1.86,8.7,1.23,2.82,1680,1
13.64,3.1,2.56,15.2,116,2.7,3.03,0.17,1.66,5.1,0.96,3.36,845,1
14.06,1.63,2.28,16,126,3,3.17,0.24,2.1,5.65,1.09,3.71,780,1
12.93,3.8,2.65,18.6,102,2.41,2.41,0.25,1.98,4.5,1.03,3.52,770,1
13.71,1.86,2.36,16.6,101,2.61,2.88,0.27,1.69,3.8,1.11,4,1035,1
12.85,1.6,2.52,17.8,95,2.48,2.37,0.26,1.46,3.93,1.09,3.63,1015,1
13.5,1.81,2.61,20,96,2.53,2.61,0.28,1.66,3.52,1.12,3.82,845,1
13.05,2.05,3.22,25,124,2.63,2.68,0.47,1.92,3.58,1.13,3.2,830,1
13.39,1.77,2.62,16.1,93,2.85,2.94,0.34,1.45,4.8,0.92,3.22,1195,1
13.3,1.72,2.14,17,94,2.4,2.19,0.27,1.35,3.95,1.02,2.77,1285,1
13.87,1.9,2.8,19.4,107,2.95,2.97,0.37,1.76,4.5,1.25,3.4,915,1
14.02,1.68,2.21,16,96,2.65,2.33,0.26,1.98,4.7,1.04,3.59,1035,1
13.73,1.5,2.7,22.5,101,3,3.25,0.29,2.38,5.7,1.19,2.71,1285,1
13.58,1.66,2.36,19.1,106,2.86,3.19,0.22,1.95,6.9,1.09,2.88,1515,1
13.68,1.83,2.36,17.2,104,2.42,2.69,0.42,1.97,3.84,1.23,2.87,990,1
13.76,1.53,2.7,19.5,132,2.95,2.74,0.5,1.35,5.4,1.25,3,1235,1
13.51,1.8,2.65,19,110,2.35,2.53,0.29,1.54,4.2,1.1,2.87,1095,1
13.48,1.81,2.41,20.5,100,2.7,2.98,0.26,1.86,5.1,1.04,3.47,920,1
13.28,1.64,2.84,15.5,110,2.6,2.68,0.34,1.36,4.6,1.09,2.78,880,1
13.05,1.65,2.55,18,98,2.45,2.43,0.29,1.44,4.25,1.12,2.51,1105,1
13.07,1.5,2.1,15.5,98,2.4,2.64,0.28,1.37,3.7,1.18,2.69,1020,1
14.22,3.99,2.51,13.2,128,3,3.04,0.2,2.08,5.1,0.89,3.53,760,1
13.56,1.71,2.31,16.2,117,3.15,3.29,0.34,2.34,6.13,0.95,3.38,795,1
13.41,3.84,2.12,18.8,90,2.45,2.68,0.27,1.48,4.28,0.91,3,1035,1
13.88,1.89,2.59,15,101,3.25,3.56,0.17,1.7,5.43,0.88,3.56,1095,1
13.24,3.98,2.29,17.5,103,2.64,2.63,0.32,1.66,4.36,0.82,3,680,1
13.05,1.77,2.1,17,107,3,3,0.28,2.03,5.04,0.88,3.35,885,1
14.21,4.04,2.44,18.9,111,2.85,2.65,0.3,1.25,5.24,0.87,3.33,1080,1
14.38,3.59,2.28,16,102,3.25,3.17,0.27,2.19,4.9,1.04,3.44,1065,1
13.9,1.68,2.12,16,101,3.1,3.39,0.21,2.14,6.1,0.91,3.33,985,1
14.1,2.02,2.4,18.8,103,2.75,2.92,0.32,2.38,6.2,1.07,2.75,1060,1
13.94,1.73,2.27,17.4,108,2.88,3.54,0.32,2.08,8.9,1.12,3.1,1260,1
13.05,1.73,2.04,12.4,92,2.72,3.27,0.17,2.91,7.2,1.12,2.91,1150,1
13.83,1.65,2.6,17.2,94,2.45,2.99,0.22,2.29,5.6,1.24,3.37,1265,1
13.82,1.75,2.42,14,111,3.88,3.74,0.32,1.87,7.05,1.01,3.26,1190,1
13.77,1.9,2.68,17.1,115,3,2.79,0.39,1.68,6.3,1.13,2.93,1375,1
13.74,1.67,2.25,16.4,118,2.6,2.9,0.21,1.62,5.85,0.92,3.2,1060,1
13.56,1.73,2.46,20.5,116,2.96,2.78,0.2,2.45,6.25,0.98,3.03,1120,1
14.22,1.7,2.3,16.3,118,3.2,3,0.26,2.03,6.38,0.94,3.31,970,1
13.29,1.97,2.68,16.8,102,3,3.23,0.31,1.66,6,1.07,2.84,1270,1
13.72,1.43,2.5,16.7,108,3.4,3.67,0.19,2.04,6.8,0.89,2.87,1285,1
12.37,0.94,1.36,10.6,88,1.98,0.57,0.28,0.42,1.95,1.05,1.82,520,2
12.33,1.1,2.28,16,101,2.05,1.09,0.63,0.41,3.27,1.25,1.67,680,2
12.64,1.36,2.02,16.8,100,2.02,1.41,0.53,0.62,5.75,0.98,1.59,450,2
13.67,1.25,1.92,18,94,2.1,1.79,0.32,0.73,3.8,1.23,2.46,630,2
12.37,1.13,2.16,19,87,3.5,3.1,0.19,1.87,4.45,1.22,2.87,420,2
12.17,1.45,2.53,19,104,1.89,1.75,0.45,1.03,2.95,1.45,2.23,355,2
12.37,1.21,2.56,18.1,98,2.42,2.65,0.37,2.08,4.6,1.19,2.3,678,2
13.11,1.01,1.7,15,78,2.98,3.18,0.26,2.28,5.3,1.12,3.18,502,2
12.37,1.17,1.92,19.6,78,2.11,2,0.27,1.04,4.68,1.12,3.48,510,2
13.34,0.94,2.36,17,110,2.53,1.3,0.55,0.42,3.17,1.02,1.93,750,2
12.21,1.19,1.75,16.8,151,1.85,1.28,0.14,2.5,2.85,1.28,3.07,718,2
12.29,1.61,2.21,20.4,103,1.1,1.02,0.37,1.46,3.05,0.906,1.82,870,2
13.86,1.51,2.67,25,86,2.95,2.86,0.21,1.87,3.38,1.36,3.16,410,2
13.49,1.66,2.24,24,87,1.88,1.84,0.27,1.03,3.74,0.98,2.78,472,2
12.99,1.67,2.6,30,139,3.3,2.89,0.21,1.96,3.35,1.31,3.5,985,2
11.96,1.09,2.3,21,101,3.38,2.14,0.13,1.65,3.21,0.99,3.13,886,2
11.66,1.88,1.92,16,97,1.61,1.57,0.34,1.15,3.8,1.23,2.14,428,2
13.03,0.9,1.71,16,86,1.95,2.03,0.24,1.46,4.6,1.19,2.48,392,2
11.84,2.89,2.23,18,112,1.72,1.32,0.43,0.95,2.65,0.96,2.52,500,2
12.33,0.99,1.95,14.8,136,1.9,1.85,0.35,2.76,3.4,1.06,2.31,750,2
12.7,3.87,2.4,23,101,2.83,2.55,0.43,1.95,2.57,1.19,3.13,463,2
12,0.92,2,19,86,2.42,2.26,0.3,1.43,2.5,1.38,3.12,278,2
12.72,1.81,2.2,18.8,86,2.2,2.53,0.26,1.77,3.9,1.16,3.14,714,2
12.08,1.13,2.51,24,78,2,1.58,0.4,1.4,2.2,1.31,2.72,630,2
13.05,3.86,2.32,22.5,85,1.65,1.59,0.61,1.62,4.8,0.84,2.01,515,2
11.84,0.89,2.58,18,94,2.2,2.21,0.22,2.35,3.05,0.79,3.08,520,2
12.67,0.98,2.24,18,99,2.2,1.94,0.3,1.46,2.62,1.23,3.16,450,2
12.16,1.61,2.31,22.8,90,1.78,1.69,0.43,1.56,2.45,1.33,2.26,495,2
11.65,1.67,2.62,26,88,1.92,1.61,0.4,1.34,2.6,1.36,3.21,562,2
11.64,2.06,2.46,21.6,84,1.95,1.69,0.48,1.35,2.8,1,2.75,680,2
12.08,1.33,2.3,23.6,70,2.2,1.59,0.42,1.38,1.74,1.07,3.21,625,2
12.08,1.83,2.32,18.5,81,1.6,1.5,0.52,1.64,2.4,1.08,2.27,480,2
12,1.51,2.42,22,86,1.45,1.25,0.5,1.63,3.6,1.05,2.65,450,2
12.69,1.53,2.26,20.7,80,1.38,1.46,0.58,1.62,3.05,0.96,2.06,495,2
12.29,2.83,2.22,18,88,2.45,2.25,0.25,1.99,2.15,1.15,3.3,290,2
11.62,1.99,2.28,18,98,3.02,2.26,0.17,1.35,3.25,1.16,2.96,345,2
12.47,1.52,2.2,19,162,2.5,2.27,0.32,3.28,2.6,1.16,2.63,937,2
11.81,2.12,2.74,21.5,134,1.6,0.99,0.14,1.56,2.5,0.95,2.26,625,2
12.29,1.41,1.98,16,85,2.55,2.5,0.29,1.77,2.9,1.23,2.74,428,2
12.37,1.07,2.1,18.5,88,3.52,3.75,0.24,1.95,4.5,1.04,2.77,660,2
12.29,3.17,2.21,18,88,2.85,2.99,0.45,2.81,2.3,1.42,2.83,406,2
12.08,2.08,1.7,17.5,97,2.23,2.17,0.26,1.4,3.3,1.27,2.96,710,2
12.6,1.34,1.9,18.5,88,1.45,1.36,0.29,1.35,2.45,1.04,2.77,562,2
12.34,2.45,2.46,21,98,2.56,2.11,0.34,1.31,2.8,0.8,3.38,438,2
11.82,1.72,1.88,19.5,86,2.5,1.64,0.37,1.42,2.06,0.94,2.44,415,2
12.51,1.73,1.98,20.5,85,2.2,1.92,0.32,1.48,2.94,1.04,3.57,672,2
12.42,2.55,2.27,22,90,1.68,1.84,0.66,1.42,2.7,0.86,3.3,315,2
12.25,1.73,2.12,19,80,1.65,2.03,0.37,1.63,3.4,1,3.17,510,2
12.72,1.75,2.28,22.5,84,1.38,1.76,0.48,1.63,3.3,0.88,2.42,488,2
12.22,1.29,1.94,19,92,2.36,2.04,0.39,2.08,2.7,0.86,3.02,312,2
11.61,1.35,2.7,20,94,2.74,2.92,0.29,2.49,2.65,0.96,3.26,680,2
11.46,3.74,1.82,19.5,107,3.18,2.58,0.24,3.58,2.9,0.75,2.81,562,2
12.52,2.43,2.17,21,88,2.55,2.27,0.26,1.22,2,0.9,2.78,325,2
11.76,2.68,2.92,20,103,1.75,2.03,0.6,1.05,3.8,1.23,2.5,607,2
11.41,0.74,2.5,21,88,2.48,2.01,0.42,1.44,3.08,1.1,2.31,434,2
12.08,1.39,2.5,22.5,84,2.56,2.29,0.43,1.04,2.9,0.93,3.19,385,2
11.03,1.51,2.2,21.5,85,2.46,2.17,0.52,2.01,1.9,1.71,2.87,407,2
11.82,1.47,1.99,20.8,86,1.98,1.6,0.3,1.53,1.95,0.95,3.33,495,2
12.42,1.61,2.19,22.5,108,2,2.09,0.34,1.61,2.06,1.06,2.96,345,2
12.77,3.43,1.98,16,80,1.63,1.25,0.43,0.83,3.4,0.7,2.12,372,2
12,3.43,2,19,87,2,1.64,0.37,1.87,1.28,0.93,3.05,564,2
11.45,2.4,2.42,20,96,2.9,2.79,0.32,1.83,3.25,0.8,3.39,625,2
11.56,2.05,3.23,28.5,119,3.18,5.08,0.47,1.87,6,0.93,3.69,465,2
12.42,4.43,2.73,26.5,102,2.2,2.13,0.43,1.71,2.08,0.92,3.12,365,2
13.05,5.8,2.13,21.5,86,2.62,2.65,0.3,2.01,2.6,0.73,3.1,380,2
11.87,4.31,2.39,21,82,2.86,3.03,0.21,2.91,2.8,0.75,3.64,380,2
12.07,2.16,2.17,21,85,2.6,2.65,0.37,1.35,2.76,0.86,3.28,378,2
12.43,1.53,2.29,21.5,86,2.74,3.15,0.39,1.77,3.94,0.69,2.84,352,2
11.79,2.13,2.78,28.5,92,2.13,2.24,0.58,1.76,3,0.97,2.44,466,2
12.37,1.63,2.3,24.5,88,2.22,2.45,0.4,1.9,2.12,0.89,2.78,342,2
12.04,4.3,2.38,22,80,2.1,1.75,0.42,1.35,2.6,0.79,2.57,580,2
12.86,1.35,2.32,18,122,1.51,1.25,0.21,0.94,4.1,0.76,1.29,630,3
12.88,2.99,2.4,20,104,1.3,1.22,0.24,0.83,5.4,0.74,1.42,530,3
12.81,2.31,2.4,24,98,1.15,1.09,0.27,0.83,5.7,0.66,1.36,560,3
12.7,3.55,2.36,21.5,106,1.7,1.2,0.17,0.84,5,0.78,1.29,600,3
12.51,1.24,2.25,17.5,85,2,0.58,0.6,1.25,5.45,0.75,1.51,650,3
12.6,2.46,2.2,18.5,94,1.62,0.66,0.63,0.94,7.1,0.73,1.58,695,3
12.25,4.72,2.54,21,89,1.38,0.47,0.53,0.8,3.85,0.75,1.27,720,3
12.53,5.51,2.64,25,96,1.79,0.6,0.63,1.1,5,0.82,1.69,515,3
13.49,3.59,2.19,19.5,88,1.62,0.48,0.58,0.88,5.7,0.81,1.82,580,3
12.84,2.96,2.61,24,101,2.32,0.6,0.53,0.81,4.92,0.89,2.15,590,3
12.93,2.81,2.7,21,96,1.54,0.5,0.53,0.75,4.6,0.77,2.31,600,3
13.36,2.56,2.35,20,89,1.4,0.5,0.37,0.64,5.6,0.7,2.47,780,3
13.52,3.17,2.72,23.5,97,1.55,0.52,0.5,0.55,4.35,0.89,2.06,520,3
13.62,4.95,2.35,20,92,2,0.8,0.47,1.02,4.4,0.91,2.05,550,3
12.25,3.88,2.2,18.5,112,1.38,0.78,0.29,1.14,8.21,0.65,2,855,3
13.16,3.57,2.15,21,102,1.5,0.55,0.43,1.3,4,0.6,1.68,830,3
13.88,5.04,2.23,20,80,0.98,0.34,0.4,0.68,4.9,0.58,1.33,415,3
12.87,4.61,2.48,21.5,86,1.7,0.65,0.47,0.86,7.65,0.54,1.86,625,3
13.32,3.24,2.38,21.5,92,1.93,0.76,0.45,1.25,8.42,0.55,1.62,650,3
13.08,3.9,2.36,21.5,113,1.41,1.39,0.34,1.14,9.4,0.57,1.33,550,3
13.5,3.12,2.62,24,123,1.4,1.57,0.22,1.25,8.6,0.59,1.3,500,3
12.79,2.67,2.48,22,112,1.48,1.36,0.24,1.26,10.8,0.48,1.47,480,3
13.11,1.9,2.75,25.5,116,2.2,1.28,0.26,1.56,7.1,0.61,1.33,425,3
13.23,3.3,2.28,18.5,98,1.8,0.83,0.61,1.87,10.52,0.56,1.51,675,3
12.58,1.29,2.1,20,103,1.48,0.58,0.53,1.4,7.6,0.58,1.55,640,3
13.17,5.19,2.32,22,93,1.74,0.63,0.61,1.55,7.9,0.6,1.48,725,3
13.84,4.12,2.38,19.5,89,1.8,0.83,0.48,1.56,9.01,0.57,1.64,480,3
12.45,3.03,2.64,27,97,1.9,0.58,0.63,1.14,7.5,0.67,1.73,880,3
14.34,1.68,2.7,25,98,2.8,1.31,0.53,2.7,13,0.57,1.96,660,3
13.48,1.67,2.64,22.5,89,2.6,1.1,0.52,2.29,11.75,0.57,1.78,620,3
12.36,3.83,2.38,21,88,2.3,0.92,0.5,1.04,7.65,0.56,1.58,520,3
13.69,3.26,2.54,20,107,1.83,0.56,0.5,0.8,5.88,0.96,1.82,680,3
12.85,3.27,2.58,22,106,1.65,0.6,0.6,0.96,5.58,0.87,2.11,570,3
12.96,3.45,2.35,18.5,106,1.39,0.7,0.4,0.94,5.28,0.68,1.75,675,3
13.78,2.76,2.3,22,90,1.35,0.68,0.41,1.03,9.58,0.7,1.68,615,3
13.73,4.36,2.26,22.5,88,1.28,0.47,0.52,1.15,6.62,0.78,1.75,520,3
13.45,3.7,2.6,23,111,1.7,0.92,0.43,1.46,10.68,0.85,1.56,695,3
12.82,3.37,2.3,19.5,88,1.48,0.66,0.4,0.97,10.26,0.72,1.75,685,3
13.58,2.58,2.69,24.5,105,1.55,0.84,0.39,1.54,8.66,0.74,1.8,750,3
13.4,4.6,2.86,25,112,1.98,0.96,0.27,1.11,8.5,0.67,1.92,630,3
12.2,3.03,2.32,19,96,1.25,0.49,0.4,0.73,5.5,0.66,1.83,510,3
12.77,2.39,2.28,19.5,86,1.39,0.51,0.48,0.64,9.899999,0.57,1.63,470,3
14.16,2.51,2.48,20,91,1.68,0.7,0.44,1.24,9.7,0.62,1.71,660,3
13.71,5.65,2.45,20.5,95,1.68,0.61,0.52,1.06,7.7,0.64,1.74,740,3
13.4,3.91,2.48,23,102,1.8,0.75,0.43,1.41,7.3,0.7,1.56,750,3
13.27,4.28,2.26,20,120,1.59,0.69,0.43,1.35,10.2,0.59,1.56,835,3
13.17,2.59,2.37,20,120,1.65,0.68,0.53,1.46,9.3,0.6,1.62,840,3
14.13,4.1,2.74,24.5,96,2.05,0.76,0.56,1.35,9.2,0.61,1.6,560,3
1 Alcohol Malic_Acid Ash Ash_Alcanity Magnesium Total_Phenols Flavanoids Nonflavanoid_Phenols Proanthocyanins Color_Intensity Hue OD280 Proline Customer_Segment
2 14.23 1.71 2.43 15.6 127 2.8 3.06 0.28 2.29 5.64 1.04 3.92 1065 1
3 13.2 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.4 1050 1
4 13.16 2.36 2.67 18.6 101 2.8 3.24 0.3 2.81 5.68 1.03 3.17 1185 1
5 14.37 1.95 2.5 16.8 113 3.85 3.49 0.24 2.18 7.8 0.86 3.45 1480 1
6 13.24 2.59 2.87 21 118 2.8 2.69 0.39 1.82 4.32 1.04 2.93 735 1
7 14.2 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 1450 1
8 14.39 1.87 2.45 14.6 96 2.5 2.52 0.3 1.98 5.25 1.02 3.58 1290 1
9 14.06 2.15 2.61 17.6 121 2.6 2.51 0.31 1.25 5.05 1.06 3.58 1295 1
10 14.83 1.64 2.17 14 97 2.8 2.98 0.29 1.98 5.2 1.08 2.85 1045 1
11 13.86 1.35 2.27 16 98 2.98 3.15 0.22 1.85 7.22 1.01 3.55 1045 1
12 14.1 2.16 2.3 18 105 2.95 3.32 0.22 2.38 5.75 1.25 3.17 1510 1
13 14.12 1.48 2.32 16.8 95 2.2 2.43 0.26 1.57 5 1.17 2.82 1280 1
14 13.75 1.73 2.41 16 89 2.6 2.76 0.29 1.81 5.6 1.15 2.9 1320 1
15 14.75 1.73 2.39 11.4 91 3.1 3.69 0.43 2.81 5.4 1.25 2.73 1150 1
16 14.38 1.87 2.38 12 102 3.3 3.64 0.29 2.96 7.5 1.2 3 1547 1
17 13.63 1.81 2.7 17.2 112 2.85 2.91 0.3 1.46 7.3 1.28 2.88 1310 1
18 14.3 1.92 2.72 20 120 2.8 3.14 0.33 1.97 6.2 1.07 2.65 1280 1
19 13.83 1.57 2.62 20 115 2.95 3.4 0.4 1.72 6.6 1.13 2.57 1130 1
20 14.19 1.59 2.48 16.5 108 3.3 3.93 0.32 1.86 8.7 1.23 2.82 1680 1
21 13.64 3.1 2.56 15.2 116 2.7 3.03 0.17 1.66 5.1 0.96 3.36 845 1
22 14.06 1.63 2.28 16 126 3 3.17 0.24 2.1 5.65 1.09 3.71 780 1
23 12.93 3.8 2.65 18.6 102 2.41 2.41 0.25 1.98 4.5 1.03 3.52 770 1
24 13.71 1.86 2.36 16.6 101 2.61 2.88 0.27 1.69 3.8 1.11 4 1035 1
25 12.85 1.6 2.52 17.8 95 2.48 2.37 0.26 1.46 3.93 1.09 3.63 1015 1
26 13.5 1.81 2.61 20 96 2.53 2.61 0.28 1.66 3.52 1.12 3.82 845 1
27 13.05 2.05 3.22 25 124 2.63 2.68 0.47 1.92 3.58 1.13 3.2 830 1
28 13.39 1.77 2.62 16.1 93 2.85 2.94 0.34 1.45 4.8 0.92 3.22 1195 1
29 13.3 1.72 2.14 17 94 2.4 2.19 0.27 1.35 3.95 1.02 2.77 1285 1
30 13.87 1.9 2.8 19.4 107 2.95 2.97 0.37 1.76 4.5 1.25 3.4 915 1
31 14.02 1.68 2.21 16 96 2.65 2.33 0.26 1.98 4.7 1.04 3.59 1035 1
32 13.73 1.5 2.7 22.5 101 3 3.25 0.29 2.38 5.7 1.19 2.71 1285 1
33 13.58 1.66 2.36 19.1 106 2.86 3.19 0.22 1.95 6.9 1.09 2.88 1515 1
34 13.68 1.83 2.36 17.2 104 2.42 2.69 0.42 1.97 3.84 1.23 2.87 990 1
35 13.76 1.53 2.7 19.5 132 2.95 2.74 0.5 1.35 5.4 1.25 3 1235 1
36 13.51 1.8 2.65 19 110 2.35 2.53 0.29 1.54 4.2 1.1 2.87 1095 1
37 13.48 1.81 2.41 20.5 100 2.7 2.98 0.26 1.86 5.1 1.04 3.47 920 1
38 13.28 1.64 2.84 15.5 110 2.6 2.68 0.34 1.36 4.6 1.09 2.78 880 1
39 13.05 1.65 2.55 18 98 2.45 2.43 0.29 1.44 4.25 1.12 2.51 1105 1
40 13.07 1.5 2.1 15.5 98 2.4 2.64 0.28 1.37 3.7 1.18 2.69 1020 1
41 14.22 3.99 2.51 13.2 128 3 3.04 0.2 2.08 5.1 0.89 3.53 760 1
42 13.56 1.71 2.31 16.2 117 3.15 3.29 0.34 2.34 6.13 0.95 3.38 795 1
43 13.41 3.84 2.12 18.8 90 2.45 2.68 0.27 1.48 4.28 0.91 3 1035 1
44 13.88 1.89 2.59 15 101 3.25 3.56 0.17 1.7 5.43 0.88 3.56 1095 1
45 13.24 3.98 2.29 17.5 103 2.64 2.63 0.32 1.66 4.36 0.82 3 680 1
46 13.05 1.77 2.1 17 107 3 3 0.28 2.03 5.04 0.88 3.35 885 1
47 14.21 4.04 2.44 18.9 111 2.85 2.65 0.3 1.25 5.24 0.87 3.33 1080 1
48 14.38 3.59 2.28 16 102 3.25 3.17 0.27 2.19 4.9 1.04 3.44 1065 1
49 13.9 1.68 2.12 16 101 3.1 3.39 0.21 2.14 6.1 0.91 3.33 985 1
50 14.1 2.02 2.4 18.8 103 2.75 2.92 0.32 2.38 6.2 1.07 2.75 1060 1
51 13.94 1.73 2.27 17.4 108 2.88 3.54 0.32 2.08 8.9 1.12 3.1 1260 1
52 13.05 1.73 2.04 12.4 92 2.72 3.27 0.17 2.91 7.2 1.12 2.91 1150 1
53 13.83 1.65 2.6 17.2 94 2.45 2.99 0.22 2.29 5.6 1.24 3.37 1265 1
54 13.82 1.75 2.42 14 111 3.88 3.74 0.32 1.87 7.05 1.01 3.26 1190 1
55 13.77 1.9 2.68 17.1 115 3 2.79 0.39 1.68 6.3 1.13 2.93 1375 1
56 13.74 1.67 2.25 16.4 118 2.6 2.9 0.21 1.62 5.85 0.92 3.2 1060 1
57 13.56 1.73 2.46 20.5 116 2.96 2.78 0.2 2.45 6.25 0.98 3.03 1120 1
58 14.22 1.7 2.3 16.3 118 3.2 3 0.26 2.03 6.38 0.94 3.31 970 1
59 13.29 1.97 2.68 16.8 102 3 3.23 0.31 1.66 6 1.07 2.84 1270 1
60 13.72 1.43 2.5 16.7 108 3.4 3.67 0.19 2.04 6.8 0.89 2.87 1285 1
61 12.37 0.94 1.36 10.6 88 1.98 0.57 0.28 0.42 1.95 1.05 1.82 520 2
62 12.33 1.1 2.28 16 101 2.05 1.09 0.63 0.41 3.27 1.25 1.67 680 2
63 12.64 1.36 2.02 16.8 100 2.02 1.41 0.53 0.62 5.75 0.98 1.59 450 2
64 13.67 1.25 1.92 18 94 2.1 1.79 0.32 0.73 3.8 1.23 2.46 630 2
65 12.37 1.13 2.16 19 87 3.5 3.1 0.19 1.87 4.45 1.22 2.87 420 2
66 12.17 1.45 2.53 19 104 1.89 1.75 0.45 1.03 2.95 1.45 2.23 355 2
67 12.37 1.21 2.56 18.1 98 2.42 2.65 0.37 2.08 4.6 1.19 2.3 678 2
68 13.11 1.01 1.7 15 78 2.98 3.18 0.26 2.28 5.3 1.12 3.18 502 2
69 12.37 1.17 1.92 19.6 78 2.11 2 0.27 1.04 4.68 1.12 3.48 510 2
70 13.34 0.94 2.36 17 110 2.53 1.3 0.55 0.42 3.17 1.02 1.93 750 2
71 12.21 1.19 1.75 16.8 151 1.85 1.28 0.14 2.5 2.85 1.28 3.07 718 2
72 12.29 1.61 2.21 20.4 103 1.1 1.02 0.37 1.46 3.05 0.906 1.82 870 2
73 13.86 1.51 2.67 25 86 2.95 2.86 0.21 1.87 3.38 1.36 3.16 410 2
74 13.49 1.66 2.24 24 87 1.88 1.84 0.27 1.03 3.74 0.98 2.78 472 2
75 12.99 1.67 2.6 30 139 3.3 2.89 0.21 1.96 3.35 1.31 3.5 985 2
76 11.96 1.09 2.3 21 101 3.38 2.14 0.13 1.65 3.21 0.99 3.13 886 2
77 11.66 1.88 1.92 16 97 1.61 1.57 0.34 1.15 3.8 1.23 2.14 428 2
78 13.03 0.9 1.71 16 86 1.95 2.03 0.24 1.46 4.6 1.19 2.48 392 2
79 11.84 2.89 2.23 18 112 1.72 1.32 0.43 0.95 2.65 0.96 2.52 500 2
80 12.33 0.99 1.95 14.8 136 1.9 1.85 0.35 2.76 3.4 1.06 2.31 750 2
81 12.7 3.87 2.4 23 101 2.83 2.55 0.43 1.95 2.57 1.19 3.13 463 2
82 12 0.92 2 19 86 2.42 2.26 0.3 1.43 2.5 1.38 3.12 278 2
83 12.72 1.81 2.2 18.8 86 2.2 2.53 0.26 1.77 3.9 1.16 3.14 714 2
84 12.08 1.13 2.51 24 78 2 1.58 0.4 1.4 2.2 1.31 2.72 630 2
85 13.05 3.86 2.32 22.5 85 1.65 1.59 0.61 1.62 4.8 0.84 2.01 515 2
86 11.84 0.89 2.58 18 94 2.2 2.21 0.22 2.35 3.05 0.79 3.08 520 2
87 12.67 0.98 2.24 18 99 2.2 1.94 0.3 1.46 2.62 1.23 3.16 450 2
88 12.16 1.61 2.31 22.8 90 1.78 1.69 0.43 1.56 2.45 1.33 2.26 495 2
89 11.65 1.67 2.62 26 88 1.92 1.61 0.4 1.34 2.6 1.36 3.21 562 2
90 11.64 2.06 2.46 21.6 84 1.95 1.69 0.48 1.35 2.8 1 2.75 680 2
91 12.08 1.33 2.3 23.6 70 2.2 1.59 0.42 1.38 1.74 1.07 3.21 625 2
92 12.08 1.83 2.32 18.5 81 1.6 1.5 0.52 1.64 2.4 1.08 2.27 480 2
93 12 1.51 2.42 22 86 1.45 1.25 0.5 1.63 3.6 1.05 2.65 450 2
94 12.69 1.53 2.26 20.7 80 1.38 1.46 0.58 1.62 3.05 0.96 2.06 495 2
95 12.29 2.83 2.22 18 88 2.45 2.25 0.25 1.99 2.15 1.15 3.3 290 2
96 11.62 1.99 2.28 18 98 3.02 2.26 0.17 1.35 3.25 1.16 2.96 345 2
97 12.47 1.52 2.2 19 162 2.5 2.27 0.32 3.28 2.6 1.16 2.63 937 2
98 11.81 2.12 2.74 21.5 134 1.6 0.99 0.14 1.56 2.5 0.95 2.26 625 2
99 12.29 1.41 1.98 16 85 2.55 2.5 0.29 1.77 2.9 1.23 2.74 428 2
100 12.37 1.07 2.1 18.5 88 3.52 3.75 0.24 1.95 4.5 1.04 2.77 660 2
101 12.29 3.17 2.21 18 88 2.85 2.99 0.45 2.81 2.3 1.42 2.83 406 2
102 12.08 2.08 1.7 17.5 97 2.23 2.17 0.26 1.4 3.3 1.27 2.96 710 2
103 12.6 1.34 1.9 18.5 88 1.45 1.36 0.29 1.35 2.45 1.04 2.77 562 2
104 12.34 2.45 2.46 21 98 2.56 2.11 0.34 1.31 2.8 0.8 3.38 438 2
105 11.82 1.72 1.88 19.5 86 2.5 1.64 0.37 1.42 2.06 0.94 2.44 415 2
106 12.51 1.73 1.98 20.5 85 2.2 1.92 0.32 1.48 2.94 1.04 3.57 672 2
107 12.42 2.55 2.27 22 90 1.68 1.84 0.66 1.42 2.7 0.86 3.3 315 2
108 12.25 1.73 2.12 19 80 1.65 2.03 0.37 1.63 3.4 1 3.17 510 2
109 12.72 1.75 2.28 22.5 84 1.38 1.76 0.48 1.63 3.3 0.88 2.42 488 2
110 12.22 1.29 1.94 19 92 2.36 2.04 0.39 2.08 2.7 0.86 3.02 312 2
111 11.61 1.35 2.7 20 94 2.74 2.92 0.29 2.49 2.65 0.96 3.26 680 2
112 11.46 3.74 1.82 19.5 107 3.18 2.58 0.24 3.58 2.9 0.75 2.81 562 2
113 12.52 2.43 2.17 21 88 2.55 2.27 0.26 1.22 2 0.9 2.78 325 2
114 11.76 2.68 2.92 20 103 1.75 2.03 0.6 1.05 3.8 1.23 2.5 607 2
115 11.41 0.74 2.5 21 88 2.48 2.01 0.42 1.44 3.08 1.1 2.31 434 2
116 12.08 1.39 2.5 22.5 84 2.56 2.29 0.43 1.04 2.9 0.93 3.19 385 2
117 11.03 1.51 2.2 21.5 85 2.46 2.17 0.52 2.01 1.9 1.71 2.87 407 2
118 11.82 1.47 1.99 20.8 86 1.98 1.6 0.3 1.53 1.95 0.95 3.33 495 2
119 12.42 1.61 2.19 22.5 108 2 2.09 0.34 1.61 2.06 1.06 2.96 345 2
120 12.77 3.43 1.98 16 80 1.63 1.25 0.43 0.83 3.4 0.7 2.12 372 2
121 12 3.43 2 19 87 2 1.64 0.37 1.87 1.28 0.93 3.05 564 2
122 11.45 2.4 2.42 20 96 2.9 2.79 0.32 1.83 3.25 0.8 3.39 625 2
123 11.56 2.05 3.23 28.5 119 3.18 5.08 0.47 1.87 6 0.93 3.69 465 2
124 12.42 4.43 2.73 26.5 102 2.2 2.13 0.43 1.71 2.08 0.92 3.12 365 2
125 13.05 5.8 2.13 21.5 86 2.62 2.65 0.3 2.01 2.6 0.73 3.1 380 2
126 11.87 4.31 2.39 21 82 2.86 3.03 0.21 2.91 2.8 0.75 3.64 380 2
127 12.07 2.16 2.17 21 85 2.6 2.65 0.37 1.35 2.76 0.86 3.28 378 2
128 12.43 1.53 2.29 21.5 86 2.74 3.15 0.39 1.77 3.94 0.69 2.84 352 2
129 11.79 2.13 2.78 28.5 92 2.13 2.24 0.58 1.76 3 0.97 2.44 466 2
130 12.37 1.63 2.3 24.5 88 2.22 2.45 0.4 1.9 2.12 0.89 2.78 342 2
131 12.04 4.3 2.38 22 80 2.1 1.75 0.42 1.35 2.6 0.79 2.57 580 2
132 12.86 1.35 2.32 18 122 1.51 1.25 0.21 0.94 4.1 0.76 1.29 630 3
133 12.88 2.99 2.4 20 104 1.3 1.22 0.24 0.83 5.4 0.74 1.42 530 3
134 12.81 2.31 2.4 24 98 1.15 1.09 0.27 0.83 5.7 0.66 1.36 560 3
135 12.7 3.55 2.36 21.5 106 1.7 1.2 0.17 0.84 5 0.78 1.29 600 3
136 12.51 1.24 2.25 17.5 85 2 0.58 0.6 1.25 5.45 0.75 1.51 650 3
137 12.6 2.46 2.2 18.5 94 1.62 0.66 0.63 0.94 7.1 0.73 1.58 695 3
138 12.25 4.72 2.54 21 89 1.38 0.47 0.53 0.8 3.85 0.75 1.27 720 3
139 12.53 5.51 2.64 25 96 1.79 0.6 0.63 1.1 5 0.82 1.69 515 3
140 13.49 3.59 2.19 19.5 88 1.62 0.48 0.58 0.88 5.7 0.81 1.82 580 3
141 12.84 2.96 2.61 24 101 2.32 0.6 0.53 0.81 4.92 0.89 2.15 590 3
142 12.93 2.81 2.7 21 96 1.54 0.5 0.53 0.75 4.6 0.77 2.31 600 3
143 13.36 2.56 2.35 20 89 1.4 0.5 0.37 0.64 5.6 0.7 2.47 780 3
144 13.52 3.17 2.72 23.5 97 1.55 0.52 0.5 0.55 4.35 0.89 2.06 520 3
145 13.62 4.95 2.35 20 92 2 0.8 0.47 1.02 4.4 0.91 2.05 550 3
146 12.25 3.88 2.2 18.5 112 1.38 0.78 0.29 1.14 8.21 0.65 2 855 3
147 13.16 3.57 2.15 21 102 1.5 0.55 0.43 1.3 4 0.6 1.68 830 3
148 13.88 5.04 2.23 20 80 0.98 0.34 0.4 0.68 4.9 0.58 1.33 415 3
149 12.87 4.61 2.48 21.5 86 1.7 0.65 0.47 0.86 7.65 0.54 1.86 625 3
150 13.32 3.24 2.38 21.5 92 1.93 0.76 0.45 1.25 8.42 0.55 1.62 650 3
151 13.08 3.9 2.36 21.5 113 1.41 1.39 0.34 1.14 9.4 0.57 1.33 550 3
152 13.5 3.12 2.62 24 123 1.4 1.57 0.22 1.25 8.6 0.59 1.3 500 3
153 12.79 2.67 2.48 22 112 1.48 1.36 0.24 1.26 10.8 0.48 1.47 480 3
154 13.11 1.9 2.75 25.5 116 2.2 1.28 0.26 1.56 7.1 0.61 1.33 425 3
155 13.23 3.3 2.28 18.5 98 1.8 0.83 0.61 1.87 10.52 0.56 1.51 675 3
156 12.58 1.29 2.1 20 103 1.48 0.58 0.53 1.4 7.6 0.58 1.55 640 3
157 13.17 5.19 2.32 22 93 1.74 0.63 0.61 1.55 7.9 0.6 1.48 725 3
158 13.84 4.12 2.38 19.5 89 1.8 0.83 0.48 1.56 9.01 0.57 1.64 480 3
159 12.45 3.03 2.64 27 97 1.9 0.58 0.63 1.14 7.5 0.67 1.73 880 3
160 14.34 1.68 2.7 25 98 2.8 1.31 0.53 2.7 13 0.57 1.96 660 3
161 13.48 1.67 2.64 22.5 89 2.6 1.1 0.52 2.29 11.75 0.57 1.78 620 3
162 12.36 3.83 2.38 21 88 2.3 0.92 0.5 1.04 7.65 0.56 1.58 520 3
163 13.69 3.26 2.54 20 107 1.83 0.56 0.5 0.8 5.88 0.96 1.82 680 3
164 12.85 3.27 2.58 22 106 1.65 0.6 0.6 0.96 5.58 0.87 2.11 570 3
165 12.96 3.45 2.35 18.5 106 1.39 0.7 0.4 0.94 5.28 0.68 1.75 675 3
166 13.78 2.76 2.3 22 90 1.35 0.68 0.41 1.03 9.58 0.7 1.68 615 3
167 13.73 4.36 2.26 22.5 88 1.28 0.47 0.52 1.15 6.62 0.78 1.75 520 3
168 13.45 3.7 2.6 23 111 1.7 0.92 0.43 1.46 10.68 0.85 1.56 695 3
169 12.82 3.37 2.3 19.5 88 1.48 0.66 0.4 0.97 10.26 0.72 1.75 685 3
170 13.58 2.58 2.69 24.5 105 1.55 0.84 0.39 1.54 8.66 0.74 1.8 750 3
171 13.4 4.6 2.86 25 112 1.98 0.96 0.27 1.11 8.5 0.67 1.92 630 3
172 12.2 3.03 2.32 19 96 1.25 0.49 0.4 0.73 5.5 0.66 1.83 510 3
173 12.77 2.39 2.28 19.5 86 1.39 0.51 0.48 0.64 9.899999 0.57 1.63 470 3
174 14.16 2.51 2.48 20 91 1.68 0.7 0.44 1.24 9.7 0.62 1.71 660 3
175 13.71 5.65 2.45 20.5 95 1.68 0.61 0.52 1.06 7.7 0.64 1.74 740 3
176 13.4 3.91 2.48 23 102 1.8 0.75 0.43 1.41 7.3 0.7 1.56 750 3
177 13.27 4.28 2.26 20 120 1.59 0.69 0.43 1.35 10.2 0.59 1.56 835 3
178 13.17 2.59 2.37 20 120 1.65 0.68 0.53 1.46 9.3 0.6 1.62 840 3
179 14.13 4.1 2.74 24.5 96 2.05 0.76 0.56 1.35 9.2 0.61 1.6 560 3

69
section_9_pca/main.py Normal file
View File

@ -0,0 +1,69 @@
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# 資料預處理
dataset = pd.read_csv("Wine.csv")
X = dataset.iloc[:, [0,13]].values
Y = dataset.iloc[:, 13].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# PCA
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
X_train = pca.fit_transform(X_train)
X_test = pca.transform(X_test)
explained_variance = pca.explained_variance_ratio_
# 擬合和預測
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state=0)
classifier.fit(X_train, Y_train)
Y_pred = classifier.predict(X_test)
print(Y_test)
print(Y_pred)
# 評估性能
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
# 視覺化
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, Y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green', 'black')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('orange', 'blue', 'grey'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.legend()
plt.show()