简单机器学习算法——线性回归 包含（最小二乘法、岭回归、lasso 、ElasticNet算法）另有多个数据集（forge、wave、肿瘤、波士顿）

因为注释已经很详细了，所以直接上代码:

# -- coding: gbk --
import mglearn
from pylab import *
from sklearn.model_selection import train_test_split
mpl.rcParams['font.sans-serif'] = ['SimHei']
from sklearn.datasets import load_breast_cancer
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression
import sklearn
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet
def forge数据集():
    print("A")
    X,y=mglearn.datasets.make_forge()
    print(X.shape)
    print(y.shape)
    mglearn.discrete_scatter(X[:, 0], X[:, 1], y)
    plt.legend(["Class 0", "Class 1"], loc=4)
    plt.xlabel("第一特征")
    plt.ylabel("第二特征")
    #plt.show()

def wave数据集():
    X,y=mglearn.datasets.make_wave(n_samples=40)
    plt.plot(X, y, 'o')
    plt.ylim(-3, 3)
    plt.xlabel("Feature")
    plt.ylabel("Target")
    plt.show()

def 肿瘤数据集():
    cancer=load_breast_cancer()
    print(cancer.keys())
    print("AAAA")
    print(np.bincount(cancer.target))
    print("Sample counts per class:\n{}".format(
        {n: v for n, v in zip(cancer.target_names, np.bincount(cancer.target))}))

def 波士顿():
    boston = load_boston()
    print("Data shape: {}".format(boston.data.shape))

def 线性回归_最小二乘法():
    X, y = mglearn.datasets.load_extended_boston()
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

    '''最小二乘法'''
    lr = LinearRegression().fit(X_train, y_train)
    print("斜率", lr.coef_)
    print("截距", lr.intercept_)

    '''评测数据'''
    print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
    print("Test set score: {:.2f}".format(lr.score(X_test, y_test)))

def 岭回归Ridge():
    X, y = mglearn.datasets.load_extended_boston()
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
    ridge = Ridge(alpha=10).fit(X_train, y_train)
    '''岭回归'''
    print("斜率", ridge.coef_)
    print("截距", ridge.intercept_)

    '''评测'''
    print("Training set score: {:.2f}".format(ridge.score(X_train, y_train)))
    print("Test set score: {:.2f}".format(ridge.score(X_test, y_test)))

def lasso():
    X, y = mglearn.datasets.load_extended_boston()
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
    lasso = Lasso().fit(X_train, y_train)
    '''lasso'''
    print("斜率", lasso.coef_)
    print("截距", lasso.intercept_)

    '''评测'''
    print("Training set score: {:.2f}".format(lasso.score(X_train, y_train)))
    print("Test set score: {:.2f}".format(lasso.score(X_test, y_test)))
    print("Number of features used: {}".format(np.sum(lasso.coef_ != 0)))

    lasso001 = Lasso(alpha=0.01, max_iter=100000).fit(X_train, y_train)
    print("Training set score: {:.2f}".format(lasso001.score(X_train, y_train)))
    print("Test set score: {:.2f}".format(lasso001.score(X_test, y_test)))
    print("Number of features used: {}".format(np.sum(lasso001.coef_ != 0)))

def ElasticNet_L1正则化_L2正则化():
    X, y = mglearn.datasets.load_extended_boston()
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
    lasso = ElasticNet().fit(X_train, y_train)
    '''lasso'''
    print("斜率", lasso.coef_)
    print("截距", lasso.intercept_)
if __name__ =='__main__':
    lasso()