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()