【申精】花花公子成人频道Playboy TV-Spring Break (春假派对系列 全）

panjinhua2

可以的喜欢这类型

bladekiss

喜欢这种群交题材的

a740815223

好多人人啊

GAOg0036

感觉还是不错

小猫不2

看上去不错

rogercheng

尝试下西片吧

gu80542

偶尔换个口味

功夫茶

import numpy as np
' I) q6 g( M7 ^, `import matplotlib.pyplot as plt

% w0 W: J7 H* T: M" Wimport utilities
! a. [) ~7 B) i! q( P
# Load input data
! {+ C5 W* h  N, _3 c: t3 v9 Pinput_file = 'D:\\1.Modeling material\\Py_Study\\2.code_model\\Python-Machine-Learning-Cookbook\\Python-Machine-Learning-Cookbook-master\\Chapter03\\data_multivar.txt'
4 P0 U+ U) J4 i7 [X, y = utilities.load_data(input_file)

( Z" c" ^% F# t* F9 K2 X& g###############################################
/ f' J: [/ ~# C- l/ A( v9 [, T5 r" R# Separate the data into classes based on 'y'
6 x% C+ C& v/ D8 V3 rclass_0 = np.array([X[i] for i in range(len(X)) if y[i]==0])
# J- x8 j& o: y, d' aclass_1 = np.array([X[i] for i in range(len(X)) if y[i]==1])
1 z3 x% D9 E* M2 A9 L5 C  C  Q
/ C' X8 X; E. L* n% H6 \# Plot the input data
# J4 z( o" ?  b! nplt.figure()
' R$ u0 T. \+ u7 Y0 Lplt.scatter(class_0[:,0], class_0[:,1], facecolors='black', edgecolors='black', marker='s')
+ u% S  e. R0 @# ^4 R0 \3 Jplt.scatter(class_1[:,0], class_1[:,1], facecolors='None', edgecolors='black', marker='s')
- R8 k9 ]  p: e3 B' s* xplt.title('Input data')
$ f5 }! J. N% B: p
###############################################
/ B5 _( g8 K8 n# Train test split and SVM training
' n8 x: n+ x7 \9 Mfrom sklearn import cross_validation
from sklearn.svm import SVC

8 i9 i0 B; c. m  CX_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=5)
* U  v! v+ ?' e  l; ]
#params = {'kernel': 'linear'}
#params = {'kernel': 'poly', 'degree': 3}
params = {'kernel': 'rbf'}
) x. f& @  g/ n; |# \- wclassifier = SVC(**params)
$ w2 Q$ f9 p7 `% p& dclassifier.fit(X_train, y_train)
utilities.plot_classifier(classifier, X_train, y_train, 'Training dataset')
5 i6 z% ]) R6 Y# u4 a6 t# y
# w" N( y' B  ^6 {4 k# k. W- \& ^y_test_pred = classifier.predict(X_test)
utilities.plot_classifier(classifier, X_test, y_test, 'Test dataset')

+ K$ v  R+ f% Y. X###############################################
) [! P  \4 b9 o/ x# Evaluate classifier performance

from sklearn.metrics import classification_report

2 X! `$ R) a( E8 a% m/ Ttarget_names = ['Class-' + str(int(i)) for i in set(y)]
0 k( V* M7 B! }: J" ]print "\n" + "#"*30
print "\nClassifier performance on training dataset\n"
0 ~4 B" y* @2 A0 w: m! b0 Sprint classification_report(y_train, classifier.predict(X_train), target_names=target_names)
( W, s+ }( d) C- n0 Z1 F* Fprint "#"*30 + "\n"
0 {" f0 K# |. H( n1 O
! R! {" k# D, u! C+ L6 lprint "#"*30
print "\nClassification report on test dataset\n"
print classification_report(y_test, y_test_pred, target_names=target_names)
print "#"*30 + "\n"

, `4 K3 }& M+ t( [6 n6 [4 l

jteo21

好片强烈支持

wxw0214

你就我们摸我