python sklearn常用分类算法模型的调用

yipeiwu_com6年前Python基础

本文实例为大家分享了python sklearn分类算法模型调用的具体代码,供大家参考,具体内容如下

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

# coding=gbk
 
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)]
  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_y
   
if __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')) 

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持【听图阁-专注于Python设计】。

相关文章

python Spyder界面无法打开的解决方法

python Spyder界面无法打开的解决方法

Spyder本来还用得好好的,能正常使用,后来再关闭打开时,出现下面的蜘蛛网界面后,就无法显示操作界面了: 后来在网上搜索了多种方法,甚至还将Adaconda2重装了都没有用。 后来找...

python实现多层感知器

python实现多层感知器

写了个多层感知器,用bp梯度下降更新,拟合正弦曲线,效果凑合。 # -*- coding: utf-8 -*- import numpy as np import matplotli...

python实现的各种排序算法代码

复制代码 代码如下:# -*- coding: utf-8 -*-# 测试各种排序算法# link:www.jb51.net# date:2013/2/2 #选择排序def select...

Python3多线程操作简单示例

本文实例讲述了Python3多线程操作。分享给大家供大家参考,具体如下: python3 线程中常用的两个模块为: _thread threading(推荐使用) thread 模块已被...

python、Matlab求定积分的实现

python、Matlab求定积分的实现

python求定积分 计算 from sympy import * x = symbols('x') print(integrate(sin(2*x)/(1+x**2), (x,...