python sklearn 案例

##############分词、自定义词表、停用词################
#导入模块
from sklearn import datasets
from sklearn.cross_validation import train_test_split,cross_val_score
from sklearn.neighbors import KNeighborsClassifier

#创建数据
iris = datasets.load_iris()
iris_X = iris.data
iris_Y = iris.target

#查看数据
print(iris_X[:2, :])
print(iris_Y)

#数据集分为训练集测试集，其中训练集占30%
X_train, X_test, Y_train, Y_test = train_test_split(iris_X, iris_Y, test_size=0.3)
print(Y_train)

#定义分类模块
knn = KNeighborsClassifier()

#用fit训练数据集
knn.fit(X_train, Y_train)

#用训练好的模型knn来预测数据
print(knn.predict(X_test))
print(Y_test)