调用sklearn的各个算法

# coding=gbk

import time
from sklearn import metrics
import pickle as pickle
import pandas as pd
import  sys
sys.path.append(r'C:/Users/Documents/6、play/')
import xlwt

##实现对'NB', 'KNN', 'LR', 'RF', 'DT', 'SVM','SVMCV', 'GBDT'模型的简单调用

# 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 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 model


def read_data():
    label = pd.read_csv('label.csv', header=None)
    label = label.values
    data = []
    for i in label:
        for j in i:
            data.append(j)
    label = data
    dataset = pd.read_csv('dataset.csv', header=None)
    dataset = dataset.values
    test = pd.read_csv('test.csv', header=None)
    test = test.values
    return dataset, label,test


if __name__ == '__main__':
    thresh = 0.5
    model_save_file = None
    model_save = {}
    book = xlwt.Workbook(encoding='utf-8', style_compression=0)


    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 = read_data()


try:
    for classifier in test_classifiers:
        sheet = book.add_sheet(str(classifier), cell_overwrite_ok=True)
        print('******************* %s ********************' % classifier)
        start_time = time.time()
        model = classifiers[classifier](train_x, train_y)
        print('training took %fs!' % (time.time() - start_time))
        start_time = time.time()
        predict = model.predict(test_x)
        print('predicting took %fs!' % (time.time() - start_time))

        n=0
        for i in predict:
            sheet.write(n, 0, str(i))
            if n%10000==0:
                print(str(classifier),str(n))
            n=n+1

        print('result is writed sucessfully')

        if model_save_file != None:
            model_save[classifier] = model

except Exception as e:
    print(e)
    pass

finally:
    book.save('out1.xls')