sklearn学习——SVM例程总结(PCA+Pipline+cv+GridSearch)
Introduction
其实对于SVM调节超参数不需要这么复杂，因为gamma可能更重要一点，固定C=1，手动调节gamma即可。此外，sklearn的网格搜索极其的慢，下面的代码出来结果至少要半个多小时，如果有经验根本不需要。对于有经验的人来说或许看学习曲线就能知道调什么参数。但是为什么还要这么做呢？可能是为了装吧，或许更直观一点，不需要老中医式的随便开点良药，看看效果再换药了！
PCA：主成分分析
Pipline: 管道机制、官网
GridSearch：官网
Method
下面给出修改后的代码，里面都有注释，直接拿回去慢慢调：
数据是sklearn自带的，数据量不大，如果是比赛数据，根本没法跑，太慢了！！！
官网例程：比较三种降维方法：PCA+NMF(非负矩阵分解)+KBest
#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
=================================================================
Selecting dimensionality reduction with Pipeline and GridSearchCV
=================================================================
This example constructs a pipeline that does dimensionality
reduction followed by prediction with a support vector
classifier. It demonstrates the use of GridSearchCV and
Pipeline to optimize over different classes of estimators in a
single CV run -- unsupervised PCA and NMF dimensionality
reductions are compared to univariate feature selection during
the grid search.
"""
# Authors: Robert McGibbon, Joel Nothman
from __future__ import print_function, division
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.model_selection import StratifiedShuffleSplit#分层洗牌分割交叉验证
from sklearn.svm import LinearSVC
from sklearn.decomposition import PCA, NMF
from sklearn.feature_selection import SelectKBest, chi2
digits = load_digits()
print(__doc__)
pipe = Pipeline([
('reduce_dim', PCA()),
('classify', LinearSVC())
])
N_FEATURES_OPTIONS = [2, 4, 8]
C_OPTIONS = [1, 10, 100, 1000]
param_grid = [
{
'reduce_dim': [PCA(iterated_power=7), NMF()],
'reduce_dim__n_components': N_FEATURES_OPTIONS,
'classify__C': C_OPTIONS
},
{
'reduce_dim': [SelectKBest(chi2)],
'reduce_dim__k': N_FEATURES_OPTIONS,
'classify__C': C_OPTIONS
},
]
reducer_labels = ['PCA', 'NMF', 'KBest(chi2)']
cv = StratifiedShuffleSplit(n_splits=10, test_size=0.2, random_state=42)
grid = GridSearchCV(pipe, cv=3, n_jobs=2, param_grid=param_grid)
grid.fit(digits.data, digits.target)
mean_scores = np.array(grid.cv_results_['mean_test_score'])
# scores are in the order of param_grid iteration, which is alphabetical
mean_scores = mean_scores.reshape(len(C_OPTIONS), -1, len(N_FEATURES_OPTIONS))
# select score for best C
mean_scores = mean_scores.max(axis=0)
bar_offsets = (np.arange(len(N_FEATURES_OPTIONS)) *
(len(reducer_labels) + 1) + .5)
plt.figure()
COLORS = 'bgrcmyk'
for i, (label, reducer_scores) in enumerate(zip(reducer_labels, mean_scores)):
plt.bar(bar_offsets + i, reducer_scores, label=label, color=COLORS[i])
plt.title("Comparing feature reduction techniques")
plt.xlabel('Reduced number of features')
plt.xticks(bar_offsets + len(reducer_labels) / 2, N_FEATURES_OPTIONS)
plt.ylabel('Digit classification accuracy')
plt.ylim((0, 1))
plt.legend(loc='upper left')
plt.show()
寻找最优超参数：
# -*- coding: utf-8 -*-
"""
Created on Wed Jul 26 22:06:34 2017
@author: qiu
"""
from __future__ import print_function, division
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.model_selection import StratifiedShuffleSplit#分层洗牌分割交叉验证
from sklearn.svm import SVC
from sklearn.decomposition import PCA, NMF
from sklearn.feature_selection import SelectKBest, chi2
digits = load_digits()
#网格搜索可视化——热力图
pipe = Pipeline(steps=[
('classify', SVC())
])
C_range = np.logspace(-2, 1, 4)# logspace(a,b,N)把10的a次方到10的b次方区间分成N份
gamma_range = np.logspace(-9, -6, 4)
param_grid = [
{
'classify__C': C_range,
'classify__gamma': gamma_range
},
]
cv = StratifiedShuffleSplit(n_splits=10, test_size=0.2, random_state=42)
grid = GridSearchCV(pipe, param_grid=param_grid, cv=cv)#基于交叉验证的网格搜索。
grid.fit(digits.data, digits.target)
print("The best parameters are %s with a score of %0.2f"
% (grid.best_params_, grid.best_score_))#找到最佳超参数未完待续。。。
网格搜索可视化——热力图，参考sklearn学习-SVM例程总结3(网格搜索+交叉验证——寻找最优超参数)
在获取最佳参数后画学习曲线，参考