python 集成学习 RandomForestClassifier，RandomForestRegressor 模型

运行环境：win10 64位 py 3.6 pycharm 2018.1.1

import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,cross_validation,ensemble,naive_bayes

#加载分类数据集
def load_data_classification():
    digits = datasets.load_digits()
    return cross_validation.train_test_split(digits.data,digits.target,test_size=0.25,random_state=0)

def test_RandomForestClassifier(*data):
    X_train,X_test,y_train,y_test=data
    clf = ensemble.RandomForestClassifier()
    clf.fit(X_train,y_train)
    ##绘图
    print("Traing Score:%f"%clf.score(X_train,y_train))
    print("Tesing Score:%f"%clf.score(X_test,y_test))
X_train,X_test,y_train,y_test=load_data_classification()
test_RandomForestClassifier(X_train,X_test,y_train,y_test)

# 个休决策树的数量对预测性能的影响
def test_RandomForestClassifier_num(*data):
    X_train, X_test, y_train, y_test = data
    nums = np.arange(1,100,step=2)
    ##绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    testing_scores=[]
    training_scores=[]
    ###默认的分类器
    for num in nums:
        clf = ensemble.RandomForestClassifier(n_estimators=num)
        clf.fit(X_train,y_train)
        training_scores.append(clf.score(X_train,y_train))
        testing_scores.append(clf.score(X_test,y_test))
    ax.plot(nums, training_scores, label='Traing score')
    ax.plot(nums, testing_scores, label='Testing score')
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc='lower right')
    ax.set_ylim(0, 1.05)
    plt.suptitle("RandomForestClassifier")
    plt.show()
X_train,X_test,y_train,y_test=load_data_classification()
test_RandomForestClassifier_num(X_train,X_test,y_train,y_test)

#考察个体决策树的最大深度的预测性能的影响
def test_RandomForestClassifier_max_depth(*data):
    X_train, X_test, y_train, y_test = data
    maxdepths = np.arange(1,20)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    traing_scores = []
    testing_scores = []
    for maxdepth in maxdepths:
        clf = ensemble.RandomForestClassifier(max_depth=maxdepth)
        clf.fit(X_train,y_train)
        traing_scores.append(clf.score(X_train,y_train))
        testing_scores.append(clf.score(X_test,y_test))
    ax.plot(maxdepths,traing_scores,label='Traning Score')
    ax.plot(maxdepths,testing_scores,label='Testing Score')
    ax.set_xlabel("max_depth")
    ax.set_ylabel("score")
    ax.legend(loc='best')
    ax.set_ylim(0,1.05)
    plt.suptitle('RandomForestClassifier')
    plt.show()
X_train,X_test,y_train,y_test = load_data_classification()
test_RandomForestClassifier_max_depth(X_train,X_test,y_train,y_test)

#考察个体决策树的参数预测性能的影响
def test_RandomForestClassifier_max_features(*data):
    X_train, X_test, y_train, y_test = data
    max_features = np.linspace(0.01,1.0)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    traing_scores = []
    testing_scores = []
    for max_feature in max_features:
        clf = ensemble.RandomForestClassifier(max_features=max_feature)
        clf.fit(X_train,y_train)
        traing_scores.append(clf.score(X_train,y_train))
        testing_scores.append(clf.score(X_test,y_test))
    ax.plot(max_features,traing_scores,label='Traning Score')
    ax.plot(max_features,testing_scores,label='Testing Score')
    ax.set_xlabel("max_features")
    ax.set_ylabel("score")
    ax.legend(loc='best')
    ax.set_ylim(0,1.05)
    plt.suptitle('RandomForestClassifier')
    plt.show()
X_train,X_test,y_train,y_test = load_data_classification()
test_RandomForestClassifier_max_features(X_train,X_test,y_train,y_test)

import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,cross_validation,ensemble,naive_bayes

#加载回归数据
def load_data_regression():
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)

def test_RandomForestRegressor(*data):
    X_train,X_test,y_train,y_test=data
    regr = ensemble.RandomForestRegressor()
    regr.fit(X_train,y_train)
    ##绘图
    print("Traing Score:%f"%regr.score(X_train,y_train))
    print("Tesing Score:%f"%regr.score(X_test,y_test))
X_train,X_test,y_train,y_test=load_data_regression()
test_RandomForestRegressor(X_train,X_test,y_train,y_test)

# 个休决策树的数量对预测性能的影响
def test_RandomForestRegressor_num(*data):
    X_train, X_test, y_train, y_test = data
    nums = np.arange(1,100,step=2)
    ##绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    testing_scores=[]
    training_scores=[]
    ###默认的分类器
    for num in nums:
        regr = ensemble.RandomForestRegressor(n_estimators=num)
        regr.fit(X_train,y_train)
        training_scores.append(regr.score(X_train,y_train))
        testing_scores.append(regr.score(X_test,y_test))
    ax.plot(nums, training_scores, label='Traing score')
    ax.plot(nums, testing_scores, label='Testing score')
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc='lower right')
    ax.set_ylim(-1, 1.05)
    plt.suptitle("RandomForestRegressor")
    plt.show()
X_train,X_test,y_train,y_test=load_data_regression()
test_RandomForestRegressor_num(X_train,X_test,y_train,y_test)

#考察个体决策树的最大深度的预测性能的影响
def test_RandomForestRegressor_max_depth(*data):
    X_train, X_test, y_train, y_test = data
    maxdepths = np.arange(1,20)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    traing_scores = []
    testing_scores = []
    for maxdepth in maxdepths:
        regr = ensemble.RandomForestRegressor(max_depth=maxdepth)
        regr.fit(X_train,y_train)
        traing_scores.append(regr.score(X_train,y_train))
        testing_scores.append(regr.score(X_test,y_test))
    ax.plot(maxdepths,traing_scores,label='Traning Score')
    ax.plot(maxdepths,testing_scores,label='Testing Score')
    ax.set_xlabel("max_depth")
    ax.set_ylabel("score")
    ax.legend(loc='best')
    ax.set_ylim(0,1.05)
    plt.suptitle('RandomForestRegressor')
    plt.show()
X_train,X_test,y_train,y_test = load_data_regression()
test_RandomForestRegressor_max_depth(X_train,X_test,y_train,y_test)

#考察个体决策树的参数预测性能的影响
def test_RandomForestRegressor_max_features(*data):
    X_train, X_test, y_train, y_test = data
    max_features = np.linspace(0.01,1.0)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    traing_scores = []
    testing_scores = []
    for max_feature in max_features:
        regr = ensemble.RandomForestRegressor(max_features=max_feature)
        regr.fit(X_train,y_train)
        traing_scores.append(regr.score(X_train,y_train))
        testing_scores.append(regr.score(X_test,y_test))
    ax.plot(max_features,traing_scores,label='Traning Score')
    ax.plot(max_features,testing_scores,label='Testing Score')
    ax.set_xlabel("max_features")
    ax.set_ylabel("score")
    ax.legend(loc='best')
    ax.set_ylim(0,1.05)
    plt.suptitle('RandomForestRegressor')
    plt.show()
X_train,X_test,y_train,y_test = load_data_regression()
test_RandomForestRegressor_max_features(X_train,X_test,y_train,y_test)