关于:cross_validation.scores

# -*- coding: utf-8 -*-

"""

Created on Wed Aug 10 08:10:35 2016

@author: Administrator

"""

'''

关于:cross_validation.scores

此处cross_validation.scores并不是cross_validation的scores，

而是分类函数（本文是clf,svm）的scores
分成K部分
K-1是训练
1次是测试
共K个scores

'''

import time

import numpy as np

from sklearn import cross_validation

from sklearn import datasets

from sklearn import svm

start = time.time()

iris = datasets.load_iris()

print iris.data.shape, iris.target.shape

#(150L, 4L) (150L,)

X_train, X_test, y_train, y_test = cross_validation.train_test_split(iris.data, iris.target, test_size=0.4, random_state=0)

print X_train.shape, y_train.shape

print X_test.shape, y_test.shape

#(90L, 4L) (90L,)

#(60L, 4L) (60L,)

clf = svm.SVC(kernel='linear', C=1).fit(X_train, y_train)

print clf.score(X_test, y_test)

#0.966666666667

#模块2

clf = svm.SVC(kernel='linear', C=1)

scores = cross_validation.cross_val_score(clf, iris.data, iris.target, cv=5)

print scores

#[ 0.96666667  1.          0.96666667  0.96666667  1.        ]

print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

#Accuracy: 0.98 (+/- 0.03)

#模块3

from sklearn import metrics

scores = cross_validation.cross_val_score(clf, iris.data, iris.target,cv=5, scoring='f1_weighted')

print scores

#[ 0.96658312  1.          0.96658312  0.96658312  1.        ]

print("Took %.2f seconds for" % ((time.time() - start)))