python:sklearn学习笔记

from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier
iris = datasets.load_iris()

# 属性
iris_X = iris.data
# 类别
iris_y = iris.target

# 数据集分为训练集和测试集 测试集占总数据的 30%
X_train,X_test,y_train,y_test = train_test_split(iris_X,iris_y,test_size=0.5)

# 定义模型
knn = KNeighborsClassifier()

# 训练模型
knn.fit(X_train,y_train)

# 预测
test = knn.predict(X_test)
res = y_test
print(test)
print(res)

# 预测结果:

[2 0 0 1 1 1 1 0 2 0 1 2 2 2 2 1 1 2 2 0 1 1 1 1 0 1 2 2 0 1 1 2 2 0 1 0 2
 0 0 2 1 2 0 2 1 2 2 1 0 0 0 2 1 0 1 1 0 2 1 2 0 2 2 0 0 1 1 0 1 1 1 2 2 0
 0]
[2 0 0 1 1 1 1 0 2 0 1 2 2 2 2 1 1 2 2 0 1 1 1 1 0 1 2 2 0 1 1 2 1 0 1 0 2
 0 0 2 1 2 0 2 1 2 2 1 0 0 0 2 1 0 1 1 0 2 1 2 0 2 2 0 0 1 1 0 1 1 1 2 2 0
 0]