特征提升

特征提取

目的：将数字化的信号数据、符号化的文本转化成特征向量。

1. 字典储存的数据，用DictVectorizer进行特征抽取与向量化。

from sklearn.feature_extraction import DictVectorizer
measurements = [{'city':'Dubai','temperature':33},{'city':'London','temperature':12},{'city':'San Fransisco','temperature':18}]
vec = DictVectorizer()
print vec.fit_transform(measurements).toarray()
print vec.get_feature_names()

2. 文本数据
   （1）. 文本特征表示方法--词袋法（Bag of Words）
   将不重复的词汇集合成词表，每条训练文本都可以在词表上映射一个特征向量。
   （2）. 特征数值的计算方法
   CountVectorizer
   考虑每种词汇在该条训练文本中的频率。

#coding:utf-8
from sklearn.datasets import fetch_20newsgroups
from sklearn.cross_validation import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report

news = fetch_20newsgroups(subset='all')
x_train,x_test,y_train,y_test = train_test_split(news.data,news.target,test_size=0.25,random_state=33)
#默认不去除英文停用词
count_vec = CountVectorizer()
#训练特征向量
x_count_train = count_vec.fit_transform(x_train)
x_count_test = count_vec.transform(x_test)

#对朴素贝叶斯分类器进行初始化
mnb_count = MultinomialNB()
#对训练样本参数学习
mnb_count.fit(x_count_train,y_train)

print '20组新闻数据使用朴素贝叶斯count',mnb_count.score(x_count_test,y_test)

y_count_predict = mnb_count.predict(x_count_test)

print classification_report(y_test,y_count_predict,target_names=news.target_names)

TfidfVectorizer
不仅关注本条训练数据，还关注其他数据。

#coding:utf-8
from sklearn.datasets import fetch_20newsgroups
from sklearn.cross_validation import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report

news = fetch_20newsgroups(subset='all')
x_train,x_test,y_train,y_test =train_test_split(news.data,news.target,test_size=0.25,random_state=33)

tfidf_vec = TfidfVectorizer()
x_tfidf_train = tfidf_vec.fit_transform(x_train)
x_tfidf_test = tfidf_vec.transform(x_test)

mnb_tfidf = MultinomialNB()
mnb_tfidf.fit(x_tfidf_train,y_train)

print '20组新闻数据使用朴素贝叶斯tfidf:',mnb_tfidf.score(x_tfidf_test,y_test)
y_tfidf_predict = mnb_tfidf.predict(x_tfidf_test)
print classification_report(y_test,y_tfidf_predict,target_names=news.target_names)

在训练文本量较多的时候，利用Tfidf提升模型性能作用。