import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets,ensemble
from sklearn.model_selection import train_test_split

def load_data_classification():
    '''
    加载用于分类问题的数据集
    '''
    # 使用 scikit-learn 自带的 digits 数据集
    digits=datasets.load_digits() 
    # 分层采样拆分成训练集和测试集，测试集大小为原始数据集大小的 1/4
    return train_test_split(digits.data,digits.target,test_size=0.25,random_state=0,stratify=digits.target) 

#集成学习随机森林RandomForestClassifier分类模型
def test_RandomForestClassifier(*data):
    X_train,X_test,y_train,y_test=data
    clf=ensemble.RandomForestClassifier()
    clf.fit(X_train,y_train)
    print("Traing Score:%f"%clf.score(X_train,y_train))
    print("Testing Score:%f"%clf.score(X_test,y_test))
    
# 获取分类数据
X_train,X_test,y_train,y_test=load_data_classification() 
# 调用 test_RandomForestClassifier
test_RandomForestClassifier(X_train,X_test,y_train,y_test) 

def test_RandomForestClassifier_num(*data):
    '''
    测试 RandomForestClassifier 的预测性能随 n_estimators 参数的影响
    '''
    X_train,X_test,y_train,y_test=data
    nums=np.arange(1,100,step=2)
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    testing_scores=[]
    training_scores=[]
    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="Training 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()
    
# 调用 test_RandomForestClassifier_num
test_RandomForestClassifier_num(X_train,X_test,y_train,y_test) 

def test_RandomForestClassifier_max_depth(*data):
    '''
    测试 RandomForestClassifier 的预测性能随 max_depth 参数的影响
    '''
    X_train,X_test,y_train,y_test=data
    maxdepths=range(1,20)
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    testing_scores=[]
    training_scores=[]
    for max_depth in maxdepths:
        clf=ensemble.RandomForestClassifier(max_depth=max_depth)
        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(maxdepths,training_scores,label="Training Score")
    ax.plot(maxdepths,testing_scores,label="Testing Score")
    ax.set_xlabel("max_depth")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1.05)
    plt.suptitle("RandomForestClassifier")
    plt.show()
    
# 调用 test_RandomForestClassifier_max_depth
test_RandomForestClassifier_max_depth(X_train,X_test,y_train,y_test) 

def test_RandomForestClassifier_max_features(*data):
    '''
    测试 RandomForestClassifier 的预测性能随 max_features 参数的影响
    '''
    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)
    testing_scores=[]
    training_scores=[]
    for max_feature in max_features:
        clf=ensemble.RandomForestClassifier(max_features=max_feature)
        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(max_features,training_scores,label="Training Score")
    ax.plot(max_features,testing_scores,label="Testing Score")
    ax.set_xlabel("max_feature")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1.05)
    plt.suptitle("RandomForestClassifier")
    plt.show()
        
# 调用 test_RandomForestClassifier_max_features
test_RandomForestClassifier_max_features(X_train,X_test,y_train,y_test)