Python基于sklearn库的分类算法简单应用示例

# coding=gbk'''Created on 2016年6月4日@author: bryan'''import timefrom sklearn import metricsimport pickle as pickleimport pandas as pd# Multinomial Naive Bayes Classifierdef 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 Classifierdef knn_classifier(train_x, train_y):  from sklearn.neighbors import KNeighborsClassifier  model = KNeighborsClassifier()  model.fit(train_x, train_y)  return model# Logistic Regression Classifierdef 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 Classifierdef 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 Classifierdef 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) Classifierdef 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 Classifierdef 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 validationdef 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 list(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 modeldef read_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)  return train_x, train_y, test_x, test_yif __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('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))  if model_save_file != None:    pickle.dump(model_save, open(model_save_file, 'wb'))