Python基于基于sklearn库的分类算法简单应用示例库的分类算法简单应用示例
主要介绍了Python基于sklearn库的分类算法,结合简单实例形式分析了Python使用sklearn库封装朴素贝叶斯、K
近邻、逻辑回归、SVM向量机等常见机器学习算法的分类调用相关操作技巧,需要的朋友可以参考下
本文实例讲述了Python基于sklearn库的分类算法简单应用。分享给大家供大家参考,具体如下:
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
'''
Created on 2016年6月4日
@author: bryan
'''
import time
from sklearn import metrics
import pickle as pickle
import pandas as pd
# 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(data_file):
data = pd.read_csv(data_file)
train = data[:int(len(data)*0.9)]
评论5