簡單機器學習——最簡單分類算法（LogisticRegression二分類線性模型、LinearSVC一對其余分類器）

代碼：

# -- coding: gbk --
from sklearn.datasets import load_breast_cancer
from pylab import *
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.svm import LinearSVC
from sklearn.datasets import make_blobs
import mglearn
def LogisticRegression二分類線性模型():
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(
        cancer.data, cancer.target, stratify=cancer.target, random_state=42)

    '''構建模型'''
    logreg = LogisticRegression().fit(X_train, y_train)
    #print(logreg.predict())

    '''評測'''
    print("Training set score: {:.3f}".format(logreg.score(X_train, y_train)))
    print("Test set score: {:.3f}".format(logreg.score(X_test, y_test)))

    '''增加C擬合靈活度——————更高訓練集精度'''
    logreg100 = LogisticRegression(C=100).fit(X_train, y_train)
    print("Training set score: {:.3f}".format(logreg100.score(X_train, y_train)))
    print("Test set score: {:.3f}".format(logreg100.score(X_test, y_test)))

def LinearSVC一對其余分類器():
    X, y = make_blobs(random_state=42)
    linear_svm = LinearSVC().fit(X, y)
    '''
    coef_的形狀是(3, 2)，說明coef_每行包含三個類別之一的系數向量，
    每列包含某個特征（這個數據集有2個特征）對應的系數值。
    現在intercept_是一維數組，保存每個類別的截距。 
    '''
    print(linear_svm.coef_)  # 特征
    print(linear_svm.intercept_)  # 截距

    mglearn.discrete_scatter(X[:, 0], X[:, 1], y)
    line = np.linspace(-15, 15)
    print(line)
    for coef, intercept, color in zip(linear_svm.coef_, linear_svm.intercept_, ['b', 'r', 'g']):
        plt.plot(line, -(line * coef[0] + intercept) / coef[1], c=color)
    plt.ylim(-10, 15)
    plt.xlim(-10, 8)
    plt.xlabel("Feature 0")
    plt.ylabel("Feature 1")
    plt.legend(['Class 0', 'Class 1', 'Class 2', 'Line class 0', 'Line class 1', 'Line class 2'], loc=(1.01, 0.3))
    plt.show()
if __name__ =='__main__':
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(
        cancer.data, cancer.target, stratify=cancer.target, random_state=42)
    logreg = LogisticRegression().fit(X_train, y_train)
    y_pred=logreg.predict(X_test)
    print(np.mean(y_pred==y_test))