怎么在Python中利用sklearn库实现一个分类算法

怎么在Python中利用sklearn库实现一个分类算法？很多新手对此不是很清楚，为了帮助大家解决这个难题，下面小编将为大家详细讲解，有这方面需求的人可以来学习下，希望你能有所收获。

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：

#coding=gbk
'''
Createdon2016年6月4日
@author:bryan
'''
importtime
fromsklearnimportmetrics
importpickleaspickle
importpandasaspd
#MultinomialNaiveBayesClassifier
defnaive_bayes_classifier(train_x,train_y):
fromsklearn.naive_bayesimportMultinomialNB
model=MultinomialNB(alpha=0.01)
model.fit(train_x,train_y)
returnmodel
#KNNClassifier
defknn_classifier(train_x,train_y):
fromsklearn.neighborsimportKNeighborsClassifier
model=KNeighborsClassifier()
model.fit(train_x,train_y)
returnmodel
#LogisticRegressionClassifier
deflogistic_regression_classifier(train_x,train_y):
fromsklearn.linear_modelimportLogisticRegression
model=LogisticRegression(penalty='l2')
model.fit(train_x,train_y)
returnmodel
#RandomForestClassifier
defrandom_forest_classifier(train_x,train_y):
fromsklearn.ensembleimportRandomForestClassifier
model=RandomForestClassifier(n_estimators=8)
model.fit(train_x,train_y)
returnmodel
#DecisionTreeClassifier
defdecision_tree_classifier(train_x,train_y):
fromsklearnimporttree
model=tree.DecisionTreeClassifier()
model.fit(train_x,train_y)
returnmodel
#GBDT(GradientBoostingDecisionTree)Classifier
defgradient_boosting_classifier(train_x,train_y):
fromsklearn.ensembleimportGradientBoostingClassifier
model=GradientBoostingClassifier(n_estimators=200)
model.fit(train_x,train_y)
returnmodel
#SVMClassifier
defsvm_classifier(train_x,train_y):
fromsklearn.svmimportSVC
model=SVC(kernel='rbf',probability=True)
model.fit(train_x,train_y)
returnmodel
#SVMClassifierusingcrossvalidation
defsvm_cross_validation(train_x,train_y):
fromsklearn.grid_searchimportGridSearchCV
fromsklearn.svmimportSVC
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()
forpara,valinlist(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)
returnmodel
defread_data(data_file):
data=pd.read_csv(data_file)
train=data[:int(len(data)*0.9)]
test=data[int(len(data)*0.9):]
train_y=train.label
train_x=train.drop('label',axis=1)
test_y=test.label
test_x=test.drop('label',axis=1)
returntrain_x,train_y,test_x,test_y
if__name__=='__main__':
data_file="H:\\Research\\data\\trainCG.csv"
thresh=0.5
model_save_file=None
model_save={}
test_classifiers=['NB','KNN','LR','RF','DT','SVM','SVMCV','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,
'GBDT':gradient_boosting_classifier
}
print('readingtrainingandtestingdata...')
train_x,train_y,test_x,test_y=read_data(data_file)
forclassifierintest_classifiers:
print('*******************%s********************'%classifier)
start_time=time.time()
model=classifiers[classifier](train_x,train_y)
print('trainingtook%fs!'%(time.time()-start_time))
predict=model.predict(test_x)
ifmodel_save_file!=None:
model_save[classifier]=model
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))
ifmodel_save_file!=None:
pickle.dump(model_save,open(model_save_file,'wb'))

测试结果如下：

reading training and testing data...******************* NB ********************training took 0.004986s!precision: 78.08%, recall: 71.25%accuracy: 74.17%******************* KNN ********************training took 0.017545s!precision: 97.56%, recall: 100.00%accuracy: 98.68%******************* LR ********************training took 0.061161s!precision: 89.16%, recall: 92.50%accuracy: 90.07%******************* RF ********************training took 0.040111s!precision: 96.39%, recall: 100.00%accuracy: 98.01%******************* DT ********************training took 0.004513s!precision: 96.20%, recall: 95.00%accuracy: 95.36%******************* SVM ********************training took 0.242145s!precision: 97.53%, recall: 98.75%accuracy: 98.01%******************* SVMCV ********************Fitting 3 folds for each of 14 candidates, totalling 42 fits[Parallel(n_jobs=1)]: Done 42 out of 42 | elapsed: 6.8s finishedprobability Trueverbose Falsecoef0 0.0degree 3tol 0.001shrinking Truecache_size 200gamma 0.001max_iter -1C 1000decision_function_shape Nonerandom_state Noneclass_weight Nonekernel rbftraining took 7.434668s!precision: 98.75%, recall: 98.75%accuracy: 98.68%******************* GBDT ********************training took 0.521916s!precision: 97.56%, recall: 100.00%accuracy: 98.68%

看完上述内容是否对您有帮助呢？如果还想对相关知识有进一步的了解或阅读更多相关文章，请关注恰卡编程网行业资讯频道，感谢您对恰卡编程网的支持。