# Python机器学习库scikit-learn实践

2017/01/18 10:53

 线性 逻辑回归、朴素贝叶斯、最大熵等 训练和预测的效率比较高，但最终效果对特征的依赖程度较高，需要数据在特征层面上是线性可分的。 非线性 随机森林、决策树、神经网络、核机器等 可以建模复杂的分类面，从而能更好的拟合数据

2.1、Python的准备工作

2）Pip：在pip官网https://pypi.python.org/pypi/pip

3）源码包：如果上述两种方法都没有找到你的库，那你直接把库的源码下载回来，解压，然后在目录中会有个setup.py文件。执行#python setup.py install 即可把这个库安装到python的默认库目录中。

2.2、Scikit-learn的测试

scikit-learn已经包含在Anaconda中。也可以在官方下载源码包进行安装。本文代码里封装了如下机器学习算法，我们修改数据加载函数，即可一键测试：

classifiers = {'NB':naive_bayes_classifier,
'KNN':knn_classifier,
'LR':logistic_regression_classifier,
'RF':random_forest_classifier,
'DT':decision_tree_classifier,
'SVM':svm_classifier,
'SVMCV':svm_cross_validation,
}

train_test.py

#!usr/bin/env python
#-*- coding: utf-8 -*-

import sys
import os
import time
from sklearn import metrics
import numpy as np
import cPickle as pickle

sys.setdefaultencoding('utf8')

# Multinomial Naive Bayes Classifier
def naive_bayes_classifier(train_x, train_y):
from sklearn.naive_bayes import MultinomialNB
model = MultinomialNB(alpha=0.01)
model.fit(train_x, train_y)
return model

# KNN Classifier
def knn_classifier(train_x, train_y):
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier()
model.fit(train_x, train_y)
return model

# Logistic Regression Classifier
def logistic_regression_classifier(train_x, train_y):
from sklearn.linear_model import LogisticRegression
model = LogisticRegression(penalty='l2')
model.fit(train_x, train_y)
return model

# Random Forest Classifier
def random_forest_classifier(train_x, train_y):
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=8)
model.fit(train_x, train_y)
return model

# Decision Tree Classifier
def decision_tree_classifier(train_x, train_y):
from sklearn import tree
model = tree.DecisionTreeClassifier()
model.fit(train_x, train_y)
return model

# GBDT(Gradient Boosting Decision Tree) Classifier
model.fit(train_x, train_y)
return model

# SVM Classifier
def svm_classifier(train_x, train_y):
from sklearn.svm import SVC
model = SVC(kernel='rbf', probability=True)
model.fit(train_x, train_y)
return model

# SVM Classifier using cross validation
def svm_cross_validation(train_x, train_y):
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC
model = SVC(kernel='rbf', probability=True)
param_grid = {'C': [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], 'gamma': [0.001, 0.0001]}
grid_search = GridSearchCV(model, param_grid, n_jobs = 1, verbose=1)
grid_search.fit(train_x, train_y)
best_parameters = grid_search.best_estimator_.get_params()
for para, val in best_parameters.items():
print para, val
model = SVC(kernel='rbf', C=best_parameters['C'], gamma=best_parameters['gamma'], probability=True)
model.fit(train_x, train_y)
return model

import gzip
f = gzip.open(data_file, "rb")
f.close()
train_x = train[0]
train_y = train[1]
test_x = test[0]
test_y = test[1]
return train_x, train_y, test_x, test_y

if __name__ == '__main__':
data_file = "mnist.pkl.gz"
thresh = 0.5
model_save_file = None
model_save = {}

test_classifiers = ['NB', 'KNN', 'LR', 'RF', 'DT', 'SVM', 'GBDT']
classifiers = {'NB':naive_bayes_classifier,
'KNN':knn_classifier,
'LR':logistic_regression_classifier,
'RF':random_forest_classifier,
'DT':decision_tree_classifier,
'SVM':svm_classifier,
'SVMCV':svm_cross_validation,
}

print 'reading training and testing data...'
train_x, train_y, test_x, test_y = read_data(data_file)
num_train, num_feat = train_x.shape
num_test, num_feat = test_x.shape
is_binary_class = (len(np.unique(train_y)) == 2)
print '******************** Data Info *********************'
print '#training data: %d, #testing_data: %d, dimension: %d' % (num_train, num_test, num_feat)

for classifier in test_classifiers:
print '******************* %s ********************' % classifier
start_time = time.time()
model = classifiers[classifier](train_x, train_y)
print 'training took %fs!' % (time.time() - start_time)
predict = model.predict(test_x)
if model_save_file != None:
model_save[classifier] = model
if is_binary_class:
precision = metrics.precision_score(test_y, predict)
recall = metrics.recall_score(test_y, predict)
print 'precision: %.2f%%, recall: %.2f%%' % (100 * precision, 100 * recall)
accuracy = metrics.accuracy_score(test_y, predict)
print 'accuracy: %.2f%%' % (100 * accuracy)

if model_save_file != None:
pickle.dump(model_save, open(model_save_file, 'wb'))

本次使用mnist手写体库进行实验：

http://deeplearning.net/data/mnist/mnist.pkl.gz。共5万训练样本和1万测试样本。

代码运行结果如下：

******************** Data Info *********************
#training data: 50000, #testing_data: 10000, dimension: 784
******************* NB ********************
training took 0.287000s!
accuracy: 83.69%
******************* KNN ********************
training took 31.991000s!
accuracy: 96.64%
******************* LR ********************
training took 101.282000s!
accuracy: 91.99%
******************* RF ********************
training took 5.442000s!
accuracy: 93.78%
******************* DT ********************
training took 28.326000s!
accuracy: 87.23%
******************* SVM ********************
training took 3152.369000s!
accuracy: 94.35%
******************* GBDT ********************
training took 7623.761000s!
accuracy: 96.18%

还有一个在实际中非常有效的方法，就是融合这些分类器，再进行决策。例如简单的投票，效果都非常不错。建议在实践中，大家都可以尝试下。

0
0 收藏

0 评论
0 收藏
0