python中scikit-learn机器代码实例


Posted in Python onAugust 05, 2018

我们给大家带来了关于学习python中scikit-learn机器代码的相关具体实例,以下就是全部代码内容:

# -*- coding: utf-8 -*-
 
import numpy
from sklearn import metrics
from sklearn.svm import LinearSVC
from sklearn.naive_bayes import MultinomialNB
from sklearn import linear_model
from sklearn.datasets import load_iris
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn import cross_validation
from sklearn import preprocessing
#import iris_data
 
def load_data():
  iris = load_iris()
  x, y = iris.data, iris.target
  x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.20, random_state=42)
  return x_train,y_train,x_test,y_test
 
def train_clf3(train_data, train_tags):
  clf = LinearSVC(C=1100.0)#default with 'rbf' 
  clf.fit(train_data,train_tags)
  return clf
 
def train_clf(train_data, train_tags):
  clf = MultinomialNB(alpha=0.01)
  print numpy.asarray(train_tags)
  clf.fit(train_data, numpy.asarray(train_tags))
  return clf
 
def evaluate(actual, pred):
  m_precision = metrics.precision_score(actual, pred)
  m_recall = metrics.recall_score(actual, pred)
  print 'precision:{0:.3f}'.format(m_precision)
  print 'recall:{0:0.3f}'.format(m_recall)
  print 'f1-score:{0:.8f}'.format(metrics.f1_score(actual,pred));
 
x_train,y_train,x_test,y_test = load_data()
 
clf = train_clf(x_train, y_train)
 
pred = clf.predict(x_test)
evaluate(numpy.asarray(y_test), pred)
print metrics.classification_report(y_test, pred)
 
 
使用自定义数据
# coding: utf-8
 
import numpy
from sklearn import metrics
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer,TfidfTransformer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.svm import LinearSVC
import codecs
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
from sklearn import linear_model
 
train_corpus = [
   '我们 我们 好孩子 认证 。 就是',
   '我们 好孩子 认证 。 中国',
   '我们 好孩子 认证 。 孤独',
   '我们 好孩子 认证 。',
 ]
 
test_corpus = [
   '我 菲律宾 韩国',
   '我们 好孩子 认证 。 中国',
 ]
 
def input_data(train_file, test_file):
  train_words = []
  train_tags = []
  test_words = []
  test_tags = []
  f1 = codecs.open(train_file,'r','utf-8','ignore')
  for line in f1:
    tks = line.split(':', 1)
    word_list = tks[1]
    word_array = word_list[1:(len(word_list)-3)].split(", ")
    train_words.append(" ".join(word_array))
    train_tags.append(tks[0])
  f2 = codecs.open(test_file,'r','utf-8','ignore')
  for line in f2:
    tks = line.split(':', 1)
    word_list = tks[1]
    word_array = word_list[1:(len(word_list)-3)].split(", ")
    test_words.append(" ".join(word_array))
    test_tags.append(tks[0])
  return train_words, train_tags, test_words, test_tags
 
 
def vectorize(train_words, test_words):
  #v = HashingVectorizer(n_features=25000, non_negative=True)
  v = HashingVectorizer(non_negative=True)
  #v = CountVectorizer(min_df=1)
  train_data = v.fit_transform(train_words)
  test_data = v.fit_transform(test_words)
  return train_data, test_data
 
def vectorize1(train_words, test_words):
  tv = TfidfVectorizer(sublinear_tf = False,use_idf=True);
  train_data = tv.fit_transform(train_words);
  tv2 = TfidfVectorizer(vocabulary = tv.vocabulary_);
  test_data = tv2.fit_transform(test_words);
  return train_data, test_data
  
def vectorize2(train_words, test_words):
  count_v1= CountVectorizer(stop_words = 'english', max_df = 0.5); 
  counts_train = count_v1.fit_transform(train_words); 
   
  count_v2 = CountVectorizer(vocabulary=count_v1.vocabulary_);
  counts_test = count_v2.fit_transform(test_words);
   
  tfidftransformer = TfidfTransformer();
   
  train_data = tfidftransformer.fit(counts_train).transform(counts_train); 
  test_data = tfidftransformer.fit(counts_test).transform(counts_test);
  return train_data, test_data
 
def evaluate(actual, pred):
  m_precision = metrics.precision_score(actual, pred)
  m_recall = metrics.recall_score(actual, pred)
  print 'precision:{0:.3f}'.format(m_precision)
  print 'recall:{0:0.3f}'.format(m_recall)
  print 'f1-score:{0:.8f}'.format(metrics.f1_score(actual,pred));
 
 
def train_clf(train_data, train_tags):
  clf = MultinomialNB(alpha=0.01)
  clf.fit(train_data, numpy.asarray(train_tags))
  return clf
 
 
def train_clf1(train_data, train_tags):
  #KNN Classifier
  clf = KNeighborsClassifier()#default with k=5 
  clf.fit(train_data, numpy.asarray(train_tags)) 
  return clf
 
def train_clf2(train_data, train_tags):
  clf = linear_model.LogisticRegression(C=1e5) 
  clf.fit(train_data,train_tags)
  return clf
 
def train_clf3(train_data, train_tags):
  clf = LinearSVC(C=1100.0)#default with 'rbf' 
  clf.fit(train_data,train_tags)
  return clf
 
def train_clf4(train_data, train_tags):
  """
  随机森林,不可使用稀疏矩阵
  """
  clf = RandomForestClassifier(n_estimators=10)
  clf.fit(train_data.todense(),train_tags)
  return clf
 
#使用codecs逐行读取
def codecs_read_label_line(filename):
  label_list=[]
  f = codecs.open(filename,'r','utf-8','ignore')
  line = f.readline()
  while line:
    #label_list.append(line[0:len(line)-2])
    label_list.append(line[0:len(line)-1])
    line = f.readline()
  f.close()
  return label_list
 
def save_test_features(test_url, test_label):
  test_feature_list = codecs_read_label_line('test.dat')
  fw = open('test_labeded.dat',"w+")
  
  for (url,label) in zip(test_feature_list,test_label):
    fw.write(url+'\t'+label)
    fw.write('\n')
  fw.close()
 
def main():
  train_file = u'..\\file\\py_train.txt'
  test_file = u'..\\file\\py_test.txt'
  train_words, train_tags, test_words, test_tags = input_data(train_file, test_file)
  #print len(train_words), len(train_tags), len(test_words), len(test_words), 
  
  train_data, test_data = vectorize1(train_words, test_words)
  print type(train_data)
  print train_data.shape
  print test_data.shape
  print test_data[0].shape
  print numpy.asarray(test_data[0])
  
  clf = train_clf3(train_data, train_tags)
  
  scores = cross_validation.cross_val_score(
  clf, train_data, train_tags, cv=5, scoring="f1_weighted")
  print scores
 
  #predicted = cross_validation.cross_val_predict(clf, train_data,train_tags, cv=5)  
  '''
  
  '''
  pred = clf.predict(test_data)
  error_list=[]
  for (true_tag,predict_tag) in zip(test_tags,pred):
    if true_tag != predict_tag:
      print true_tag,predict_tag
      error_list.append(true_tag+' '+predict_tag)
  print len(error_list)
  evaluate(numpy.asarray(test_tags), pred)
  '''
  #输出打标签结果
  test_feature_list = codecs_read_label_line('test.dat')
  save_test_features(test_feature_list, pred)
  '''
  
 
if __name__ == '__main__':
  main()
Python 相关文章推荐
Python json 错误xx is not JSON serializable解决办法
Mar 15 Python
numpy.random.seed()的使用实例解析
Feb 03 Python
python3利用venv配置虚拟环境及过程中的小问题小结
Aug 01 Python
Python实现FTP弱口令扫描器的方法示例
Jan 31 Python
python对数组进行排序,并输出排序后对应的索引值方式
Feb 28 Python
python实现五子棋程序
Apr 24 Python
Python利用Pillow(PIL)库实现验证码图片的全过程
Oct 04 Python
浅析Python的命名空间与作用域
Nov 25 Python
用ldap作为django后端用户登录验证的实现
Dec 07 Python
Python 中Operator模块的使用
Jan 30 Python
python sleep和wait对比总结
Feb 03 Python
pytorch 如何把图像数据集进行划分成train,test和val
May 31 Python
解决使用pycharm提交代码时冲突之后文件丢失找回的方法
Aug 05 #Python
Python字符串、整数、和浮点型数相互转换实例
Aug 04 #Python
python与caffe改变通道顺序的方法
Aug 04 #Python
Python爬虫PyQuery库基本用法入门教程
Aug 04 #Python
python list转矩阵的实例讲解
Aug 04 #Python
Python 生成 -1~1 之间的随机数矩阵方法
Aug 04 #Python
Python爬虫框架scrapy实现downloader_middleware设置proxy代理功能示例
Aug 04 #Python
You might like
如何在PHP中进行身份认证
2006/10/09 PHP
PHP+JS无限级可伸缩菜单详解(简单易懂)
2007/01/02 PHP
PHP防注入安全代码
2008/04/09 PHP
PHP以及MYSQL日期比较方法
2012/11/29 PHP
phpstorm配置Xdebug进行调试PHP教程
2014/12/01 PHP
PHP输入流php://input实例讲解
2015/12/22 PHP
PHP面向对象自动加载机制原理与用法分析
2016/10/14 PHP
Laravel如何友好的修改.env配置文件详解
2017/06/07 PHP
php中字符串和整数比较的操作方法
2019/06/06 PHP
jquery 关于event.target使用的几点说明介绍
2013/04/26 Javascript
jquery $.each 和for怎么跳出循环终止本次循环
2013/09/27 Javascript
浅析js中的浮点型运算问题
2014/01/06 Javascript
JS实现黑色风格的网页TAB选项卡效果代码
2015/10/09 Javascript
vue.js通过自定义指令实现数据拉取更新的实现方法
2016/10/18 Javascript
简单理解vue中实例属性vm.$els
2016/12/01 Javascript
JavaScript数据结构之二叉树的遍历算法示例
2017/04/13 Javascript
Bootstrap弹出框(Popover)被挤压的问题小结
2017/07/11 Javascript
详解Layer弹出层样式
2017/08/21 Javascript
bootstrap-Treeview实现级联勾选
2017/11/23 Javascript
elementUI同一页面展示多个Dialog的实现
2020/11/19 Javascript
[40:03]DOTA2上海特级锦标赛主赛事日 - 1 败者组第一轮#1EHOME VS Archon
2016/03/02 DOTA
Python开发的实用计算器完整实例
2017/05/10 Python
浅谈python中requests模块导入的问题
2018/05/18 Python
Django获取该数据的上一条和下一条方法
2019/08/12 Python
pytorch使用 to 进行类型转换方式
2020/01/08 Python
python GUI库图形界面开发之PyQt5时间控件QTimer详细使用方法与实例
2020/02/26 Python
python实现电子词典
2020/03/03 Python
python3 中使用urllib问题以及urllib详解
2020/08/03 Python
Django使用django-simple-captcha做验证码的实现示例
2021/01/07 Python
利用CSS3动画实现圆圈由小变大向外扩散的效果实例
2018/09/10 HTML / CSS
幼儿园春季开学寄语
2014/04/03 职场文书
119消防日活动总结
2014/08/29 职场文书
党的群众路线教育实践活动心得体会(企业)
2014/11/03 职场文书
抗洪救灾感谢信
2015/01/22 职场文书
自定义函数实现单词排序并运用于PostgreSQL(实现代码)
2021/04/22 PostgreSQL
Mybatis-Plus进阶分页与乐观锁插件及通用枚举和多数据源详解
2022/03/21 Java/Android