第5步：应用PCA功能

将PCA功能应用于训练和测试集进行分析。

# Applying PCA function on training

# and testing set of X component

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_

步骤6：使Logistic回归拟合到训练集

# Fitting Logistic Regression To the training set

from sklearn.linear_model import LogisticRegression

classifier = LogisticRegression(random_state = 0)

classifier.fit(X_train, y_train)

第7步：预测测试集结果

# Predicting the test set result using

# predict function under LogisticRegression

y_pred = classifier.predict(X_test)

第8步：制作混淆矩阵

# making confusion matrix between

# test set of Y and predicted value.

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_test, y_pred)

步骤9：预测训练集结果

# Predicting the training set

# result through scatter plot

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(('yellow', 'white', 'aquamarine')))

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(('red', 'green', 'blue'))(i), label = j)

plt.title('Logistic Regression (Training set)')

plt.xlabel('PC1') # for Xlabel

plt.ylabel('PC2') # for Ylabel

plt.legend() # to show legend

# show scatter plot

plt.show()

步骤10：可视化测试集结果

# Visualising the Test set results through scatter plot

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(('yellow', 'white', 'aquamarine')))

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(('red', 'green', 'blue'))(i), label = j)

# title for scatter plot

plt.title('Logistic Regression (Test set)')

plt.xlabel('PC1') # for Xlabel

plt.ylabel('PC2') # for Ylabel

plt.legend()

# show scatter plot

plt.show()