sklearn实现聚类

 

import numpy as np
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import  KNeighborsClassifier

iris = datasets.load_iris()
iris_X = iris.data
iris_Y = iris.target
# print(iris_X[:2,:])
# print(iris_Y)
##将上面的数据集分成测试集和训练集，其中测试集占30%
X_train,X_test,Y_train,Y_test = train_test_split(iris_X,iris_Y,test_size=0.3)
##此时数据打乱了
#print(Y_train)
knn = KNeighborsClassifier()
##训练
knn.fit(X_train,Y_train)
##预测是哪种花
print(knn.predict(X_test))
##打印真实值
print(Y_test)