# -*- coding: utf-8 -*-
"""
Created on Sun Sep 17 21:27:03 2017
@author: aa
"""
from sklearn.datasets import load_iris
iris=load_iris()
print(iris.data.shape)  
#(150L, 4L)
#print iris.DESCR
from sklearn.cross_validation import train_test_split
# train_test_split 用于数据分割
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,test_size=0.25,random_state=33)
# 采样25%作为测试集
from sklearn.preprocessing import StandardScaler 
# 导入数据标准化模块
from sklearn.neighbors import KNeighborsClassifier
ss=StandardScaler()
X_train=ss.fit_transform(X_train)
X_test=ss.fit_transform(X_test)
# 标准化 训练和测试数据
knc=KNeighborsClassifier()
knc.fit(X_train,y_train)
y_predict=knc.predict(X_test)
print 'The accuracy of K-Nearest Neighor Classifier is',knc.score(X_test,y_test)
# 模型自带的评估函数进行准确率测评
# 0.710526315789
from sklearn.metrics import classification_report
print classification_report(y_test,y_predict,target_names=iris.target_names)
# classification_report对预测结果进行更详细的分析
#             precision    recall  f1-score   support
#
#     setosa       1.00      1.00      1.00         8
# versicolor       0.50      1.00      0.67        11
#  virginica       1.00      0.42      0.59        19
#avg / total       0.86      0.71      0.70        38