import numpy as np
import matplotlib.pyplot as plt

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

def load_classification_data():
    # 使用 scikit-learn 自带的手写识别数据集 Digit Dataset
    digits=datasets.load_digits() 
    X_train=digits.data
    y_train=digits.target
    # 进行分层采样拆分,测试集大小占 1/4
    return train_test_split(X_train, y_train,test_size=0.25,random_state=0,stratify=y_train) 

#KNN分类KNeighborsClassifier模型
def test_KNeighborsClassifier(*data):
    X_train,X_test,y_train,y_test=data
    clf=neighbors.KNeighborsClassifier()
    clf.fit(X_train,y_train)
    print("Training Score:%f"%clf.score(X_train,y_train))
    print("Testing Score:%f"%clf.score(X_test,y_test))
    
# 获取分类模型的数据集
X_train,X_test,y_train,y_test=load_classification_data()
# 调用 test_KNeighborsClassifier
test_KNeighborsClassifier(X_train,X_test,y_train,y_test) 

def test_KNeighborsClassifier_k_w(*data):
    '''
    测试 KNeighborsClassifier 中 n_neighbors 和 weights 参数的影响
    '''
    X_train,X_test,y_train,y_test=data
    Ks=np.linspace(1,y_train.size,num=100,endpoint=False,dtype='int')
    weights=['uniform','distance']

    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    ### 绘制不同 weights 下, 预测得分随 n_neighbors 的曲线
    for weight in weights:
        training_scores=[]
        testing_scores=[]
        for K in Ks:
            clf=neighbors.KNeighborsClassifier(weights=weight,n_neighbors=K)
            clf.fit(X_train,y_train)
            testing_scores.append(clf.score(X_test,y_test))
            training_scores.append(clf.score(X_train,y_train))
        ax.plot(Ks,testing_scores,label="testing score:weight=%s"%weight)
        ax.plot(Ks,training_scores,label="training score:weight=%s"%weight)
    ax.legend(loc='best')
    ax.set_xlabel("K")
    ax.set_ylabel("score")
    ax.set_ylim(0,1.05)
    ax.set_title("KNeighborsClassifier")
    plt.show()
    
# 获取分类模型的数据集
X_train,X_test,y_train,y_test=load_classification_data()
# 调用 test_KNeighborsClassifier_k_w
test_KNeighborsClassifier_k_w(X_train,X_test,y_train,y_test) 

def test_KNeighborsClassifier_k_p(*data):
    '''
    测试 KNeighborsClassifier 中 n_neighbors 和 p 参数的影响
    '''
    X_train,X_test,y_train,y_test=data
    Ks=np.linspace(1,y_train.size,endpoint=False,dtype='int')
    Ps=[1,2,10]

    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    ### 绘制不同 p 下, 预测得分随 n_neighbors 的曲线
    for P in Ps:
        training_scores=[]
        testing_scores=[]
        for K in Ks:
            clf=neighbors.KNeighborsClassifier(p=P,n_neighbors=K)
            clf.fit(X_train,y_train)
            testing_scores.append(clf.score(X_test,y_test))
            training_scores.append(clf.score(X_train,y_train))
        ax.plot(Ks,testing_scores,label="testing score:p=%d"%P)
        ax.plot(Ks,training_scores,label="training score:p=%d"%P)
    ax.legend(loc='best')
    ax.set_xlabel("K")
    ax.set_ylabel("score")
    ax.set_ylim(0,1.05)
    ax.set_title("KNeighborsClassifier")
    plt.show()
    
# 获取分类模型的数据集
X_train,X_test,y_train,y_test=load_classification_data()
# 调用 test_KNeighborsClassifier_k_p
test_KNeighborsClassifier_k_p(X_train,X_test,y_train,y_test)