机器学习python实现

参考

python大战机器学习

01.线性模型

import matplotlib.pyplot as plt

import numpy as np

from sklearn import datasets,linear_model,discriminant_analysis,model_selection




#加载数据集，返回元组（训练集，测试集，及其标签值）

def load_data():

    diabetes = datasets.load_diabetes()

    return model_selection.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)



#线性回归模型

def test_LinearRegression(*data):

    X_train,X_test,y_train,y_test=data

    #加载模型
    regr=linear_model.LinearRegression()

    #用模型训练数据
    regr.fit(X_train,y_train)

    #输出权重和截距
    print('权重: %s ,截距: %.2f '%(regr.coef_,regr.intercept_))

    #残差平方和
    print("残差平方和: %.2f "%np.mean((regr.predict(X_test) - y_test)**2))

    #性能
    print('score: %.2f'%regr.score(X_test,y_test))


#调用函数
X_train,X_test,y_train,y_test=load_data()
test_LinearRegression(X_train,X_test,y_train,y_test)

02.岭回归

import matplotlib.pyplot as plt

import numpy as np

from sklearn import datasets,linear_model,discriminant_analysis,model_selection




#加载数据集，返回元组（训练集，测试集，及其标签值）

def load_data():

    diabetes = datasets.load_diabetes()

    return model_selection.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)


#岭回归

def test_Ridge(*data):

    X_train,X_test,y_train,y_test=data

    #加载 岭回归
    regr=linear_model.Ridge()

    regr.fit(X_train,y_train)

    # 输出权重和截距
    print('权重: %s ,截距: %.2f ' % (regr.coef_, regr.intercept_))

    # 残差平方和
    print("残差平方和: %.2f " % np.mean((regr.predict(X_test) - y_test) ** 2))

    # 性能
    print('score: %.2f' % regr.score(X_test, y_test))


def test_Ridge_alpha(*data):

    X_train,X_test,y_train,y_test=data

    alphas=[0.01,0.02,0.05,0.1,0.2,0.5,1,2,5,10,20,50,100,200,500,1000]

    scores=[]

    for i,alpha in enumerate(alphas):

        regr=linear_model.Ridge(alpha=alpha)

        regr.fit(X_train,y_train)

        scores.append(regr.score(X_test,y_test))


    ##绘图

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    ax.plot(alphas,scores)

    ax.set_xlabel(r"$\alpha&")

    ax.set_ylabel(r"score")

    ax.set_xscale('log')

    ax.set_title("Ridge")

    plt.show()



X_train,X_test,y_train,y_test=load_data()
test_Ridge(X_train,X_test,y_train,y_test)


X_train,X_test,y_train,y_test=load_data()
test_Ridge_alpha(X_train,X_test,y_train,y_test)

03.Lasso回归

import matplotlib.pyplot as plt

import numpy as np

from sklearn import datasets,linear_model,discriminant_analysis,model_selection




########加载数据集，返回元组（训练集，测试集，及其标签值）

def load_data():

    diabetes = datasets.load_diabetes()

    return model_selection.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)


######## Lasso

def test_Lasso(*data):

    X_train,X_test,y_train,y_test=data

    regr=linear_model.Lasso()

    regr.fit(X_train,y_train)

    # 输出权重和截距
    print('权重: %s ,截距: %.2f ' % (regr.coef_, regr.intercept_))

    # 残差平方和
    print("残差平方和: %.2f " % np.mean((regr.predict(X_test) - y_test) ** 2))

    # 性能
    print('score: %.2f' % regr.score(X_test, y_test))


def test_Lasso_alpha(*data):

    X_train,X_test,y_train,y_test=data

    alphas=[0.01,0.02,0.05,0.1,0.2,0.5,1,2,5,10,20,50,100,200,500,1000]

    scores=[]

    for i,alpha in enumerate(alphas):

        regr=linear_model.Lasso(alpha=alpha)

        regr.fit(X_train,y_train)

        scores.append(regr.score(X_test,y_test))

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    ax.plot(alphas,scores)

    ax.set_xlabel(r'&\alpha$')

    ax.set_ylabel(r"score")

    #把x轴设置为对数坐标
    ax.set_xscale('log')

    ax.set_title("Lasso")

    plt.show()


X_train,X_test,y_train,y_test=load_data()
test_Lasso(X_train,X_test,y_train,y_test)


X_train,X_test,y_train,y_test=load_data()
test_Lasso_alpha(X_train,X_test,y_train,y_test)

04.ElasitcNet回归

import matplotlib.pyplot as plt

import numpy as np

from sklearn import datasets,linear_model,discriminant_analysis,model_selection




#加载数据集，返回元组（训练集，测试集，及其标签值）

def load_data():

    diabetes = datasets.load_diabetes()

    return model_selection.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)


#ElasticNet回归

def test_ElasticNet(*data):

    X_train,X_test,y_train,y_test=data

    regr=linear_model.ElasticNet()

    regr.fit(X_train,y_train)

    # 输出权重和截距
    print('权重: %s ,截距: %.2f ' % (regr.coef_, regr.intercept_))

    # 残差平方和
    print("残差平方和: %.2f " % np.mean((regr.predict(X_test) - y_test) ** 2))

    # 性能
    print('score: %.2f' % regr.score(X_test, y_test))



def test_ElasticNet_alpha_rho(*data):

    X_train,X_test,y_train,y_test=data

    alphas=np.logspace(-2,2)

    rhos=np.linspace(0.01,1)

    scores=[]

    for alpha in alphas:

        for rho in rhos:

            regr=linear_model.ElasticNet(alpha=alpha,l1_ratio=rho)

            regr.fit(X_train,y_train)

            scores.append(regr.score(X_test,y_test))


    alphas,rhos=np.meshgrid(alphas,rhos)

    scores=np.array(scores).reshape(alphas.shape)

    from mpl_toolkits.mplot3d import Axes3D

    from matplotlib import cm

    fig=plt.figure()

    ax=Axes3D(fig)

    surf=ax.plot_surface(alphas,rhos,scores,rstride=1,cstride=1,cmap=cm.jet,linewidth=0,antialiased=False)

    fig.colorbar(surf,shrink=0.5,aspect=5)

    ax.set_xlabel(r"$\alpha$")

    ax.set_ylabel(r"$\rho$")

    ax.set_zlabel("score")

    ax.set_title("ElasticNet")

    plt.show()



X_train,X_test,y_train,y_test=load_data()
test_ElasticNet(X_train,X_test,y_train,y_test)


X_train,X_test,y_train,y_test=load_data()
test_ElasticNet_alpha_rho(X_train,X_test,y_train,y_test)

05.逻辑回归

import matplotlib.pyplot as plt

import numpy as np

from sklearn import datasets,linear_model,discriminant_analysis,model_selection




def load_data():

    iris=datasets.load_iris()

    X_train=iris.data

    y_train=iris.target

    return model_selection.train_test_split(X_train,y_train,test_size=0.25,random_state=0,stratify=y_train)




def test_LogisticRegression(*data):

    X_train,X_test,y_train,y_test=data

    regr=linear_model.LogisticRegression()

    regr.fit(X_train,y_train)

    # 输出权重和截距
    print('权重: %s ,截距: %s ' % (regr.coef_, regr.intercept_))

    # 性能
    print('score: %.2f' % regr.score(X_test, y_test))




def test_LogisticRegression_multinomial(*data):

    X_train, X_test, y_train, y_test = data

    regr = linear_model.LogisticRegression(multi_class='multinomial',solver='lbfgs')

    regr.fit(X_train,y_train)

    # 输出权重和截距
    print('权重: %s ,截距: %s ' % (regr.coef_, regr.intercept_))

    # 性能
    print('score: %.2f' % regr.score(X_test, y_test))




def test_LogisticRegression_C(*data):

    X_train, X_test, y_train, y_test = data

    Cs=np.logspace(-2,4,num=100)

    scores=[]

    for C in Cs:

        regr=linear_model.LogisticRegression(C=C)

        regr.fit(X_train,y_train)

        scores.append(regr.score(X_test,y_test))


    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    ax.plot(Cs,scores)

    ax.set_xlabel(r"C")

    ax.set_ylabel(r"score")

    ax.set_xscale('log')

    ax.set_title("LogisticRegression")

    plt.show()




X_train,X_test,y_train,y_test=load_data()
test_LogisticRegression(X_train,X_test,y_train,y_test)


X_train,X_test,y_train,y_test=load_data()
test_LogisticRegression_multinomial(X_train,X_test,y_train,y_test)


X_train,X_test,y_train,y_test=load_data()
test_LogisticRegression_C(X_train,X_test,y_train,y_test)

06.决策树回归

import numpy as np

from sklearn.tree import DecisionTreeRegressor

from sklearn import model_selection

import matplotlib.pyplot as plt



#随机产生的数据集

def creat_data(n):

    np.random.seed(0)

    X=5*np.random.rand(n,1)

    y=np.sin