python sklearn 分类算法简单调用（借鉴）

 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：

数据为近红外测试猕猴桃软硬和时间差异的数据，可以作为分类软硬以及前后时间差的分类。

[python]  view plain  copy

 

1. # coding=gbk  
2. ''''' 
3. Created on 2016年6月4日 
4.  
5. @author: bryan 
6. '''  
7.    
8. import time    
9. from sklearn import metrics    
10. import pickle as pickle    
11. import pandas as pd  
12.   
13.     
14. # Multinomial Naive Bayes Classifier    
15. def naive_bayes_classifier(train_x, train_y):    
16.     from sklearn.naive_bayes import MultinomialNB    
17.     model = MultinomialNB(alpha=0.01)    
18.     model.fit(train_x, train_y)    
19.     return model    
20.     
21.     
22. # KNN Classifier    
23. def knn_classifier(train_x, train_y):    
24.     from sklearn.neighbors import KNeighborsClassifier    
25.     model = KNeighborsClassifier()    
26.     model.fit(train_x, train_y)    
27.     return model    
28.     
29.     
30. # Logistic Regression Classifier    
31. def logistic_regression_classifier(train_x, train_y):    
32.     from sklearn.linear_model import LogisticRegression    
33.     model = LogisticRegression(penalty='l2')    
34.     model.fit(train_x, train_y)    
35.     return model    
36.     
37.     
38. # Random Forest Classifier    
39. def random_forest_classifier(train_x, train_y):    
40.     from sklearn.ensemble import RandomForestClassifier    
41.     model = RandomForestClassifier(n_estimators=8)    
42.     model.fit(train_x, train_y)    
43.     return model    
44.     
45.     
46. # Decision Tree Classifier    
47. def decision_tree_classifier(train_x, train_y):    
48.     from sklearn import tree    
49.     model = tree.DecisionTreeClassifier()    
50.     model.fit(train_x, train_y)    
51.     return model    
52.     
53.     
54. # GBDT(Gradient Boosting Decision Tree) Classifier    
55. def gradient_boosting_classifier(train_x, train_y):    
56.     from sklearn.ensemble import GradientBoostingClassifier    
57.     model = GradientBoostingClassifier(n_estimators=200)    
58.     model.fit(train_x, train_y)    
59.     return model    
60.     
61.     
62. # SVM Classifier    
63. def svm_classifier(train_x, train_y):    
64.     from sklearn.svm import SVC    
65.     model = SVC(kernel='rbf', probability=True)    
66.     model.fit(train_x, train_y)    
67.     return model    
68.     
69. # SVM Classifier using cross validation    
70. def svm_cross_validation(train_x, train_y):    
71.     from sklearn.grid_search import GridSearchCV    
72.     from sklearn.svm import SVC    
73.     model = SVC(kernel='rbf', probability=True)    
74.     param_grid = {'C': [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], 'gamma': [0.001, 0.0001]}    
75.     grid_search = GridSearchCV(model, param_grid, n_jobs = 1, verbose=1)    
76.     grid_search.fit(train_x, train_y)    
77.     best_parameters = grid_search.best_estimator_.get_params()    
78.     for para, val in list(best_parameters.items()):    
79.         print(para, val)    
80.     model = SVC(kernel='rbf', C=best_parameters['C'], gamma=best_parameters['gamma'], probability=True)    
81.     model.fit(train_x, train_y)    
82.     return model    
83.     
84. def read_data(data_file):    
85.     data = pd.read_csv(data_file)  
86.     train = data[:int(len(data)*0.9)]  
87.     test = data[int(len(data)*0.9):]  
88.     train_y = train.label  
89.     train_x = train.drop('label', axis=1)  
90.     test_y = test.label  
91.     test_x = test.drop('label', axis=1)  
92.     return train_x, train_y, test_x, test_y  
93.         
94. if __name__ == '__main__':    
95.         datafilename = 'softunion20_21.csv'
        
        data_file = "L:\\Python\\output\\"+datafilename    
        thresh = 0.5    
        model_save_file = 1    
        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('reading training and testing data...')    
        train_x, train_y, test_x, test_y = read_data(data_file)    
            
        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    
            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))
    
    
    
    
        import numpy as np
        model = classifiers['LR'](train_x, train_y)
        predict = model.predict(test_x)
        print "LR :"
        print "Predict：",test_x,predict.T
96.      
97.     
98.     if model_save_file != None:    
99.         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 finished
probability True
verbose False
coef0 0.0
degree 3
tol 0.001
shrinking True
cache_size 200
gamma 0.001
max_iter -1
C 1000
decision_function_shape None
random_state None
class_weight None
kernel rbf
training 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%

附上近红外测试数据集