Python机器学习库scikit-learn实践

用Anaconda的spyder:新建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  
  
reload(sys)  
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  
def gradient_boosting_classifier(train_x, train_y):  
    from sklearn.ensemble import GradientBoostingClassifier  
    model = GradientBoostingClassifier(n_estimators=200)  
    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  
  
def read_data(data_file):  
    import gzip  
    f = gzip.open(data_file, "rb")  
    train, val, test = pickle.load(f)  
    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,  
                 'GBDT':gradient_boosting_classifier  
    }  
      
    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'))  

结果：

reading training and testing data...
******************** Data Info *********************
#training data: 50000, #testing_data: 10000, dimension: 784
******************* NB ********************
training took 0.558000s!
accuracy: 83.69%
******************* KNN ********************
training took 29.467000s!
accuracy: 96.64%
******************* LR ********************
training took 104.605000s!
accuracy: 91.98%
******************* RF ********************
training took 4.401000s!
accuracy: 93.91%
******************* DT ********************
training took 26.923000s!
accuracy: 87.07%
******************* SVM ********************
training took 3831.564000s!
accuracy: 94.35%
******************* GBDT ********************

在这个数据集中，由于数据分布的团簇性较好（如果对这个数据库了解的话，看它的t-SNE映射图就可以看出来。由于任务简单，其在deep learning界已被认为是toy dataset），因此KNN的效果不赖。GBDT是个非常不错的算法，在kaggle等大数据比赛中，状元探花榜眼之列经常能见其身影。