1 文本编码技术简介 

sample = ["Machine learning is fascinating, it is wonderful"
         ,"Machine learning is a sensational techonology"
         ,"Elsa is a popular character"]
from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer()
X = vec.fit_transform(sample) 
X#使用接口get_feature_names()调用每个列的名称
import pandas as pd
#注意稀疏矩阵是无法输入pandas的
CVresult = pd.DataFrame(X.toarray(),columns = vec.get_feature_names())
CVresult

from sklearn.feature_extraction.text import TfidfVectorizer as TFIDF
vec = TFIDF()
X = vec.fit_transform(sample) 
X
#同样使用接口get_feature_names()调用每个列的名称
TFIDFresult = pd.DataFrame(X.toarray(),columns=vec.get_feature_names())
TFIDFresult
#使用TF-IDF编码之后，出现得多的单词的权重被降低了么？
CVresult.sum(axis=0)/CVresult.sum(axis=0).sum()
TFIDFresult.sum(axis=0) / TFIDFresult.sum(axis=0).sum()

2 探索文本数据 

from sklearn.datasets import fetch_20newsgroups
#初次使用这个数据集的时候，会在实例化的时候开始下载
data = fetch_20newsgroups()
#通常我们使用data来查看data里面到底包含了什么内容，但由于fetch_20newsgourps这个类加载出的数据巨大，数
据结构中混杂很多文字，因此很难去看清
#不同类型的新闻
data.target_names
#其实fetch_20newsgroups也是一个类，既然是类，应该就有可以调用的参数
#面对简单数据集，我们往往在实例化的过程中什么都不写，但是现在data中数据量太多，不方便探索
#因此我们需要来看看我们的类fetch_20newsgroups都有什么样的参数可以帮助我们

import numpy as np
import pandas as pd
categories = ["sci.space" #科学技术 - 太空
             ,"rec.sport.hockey" #运动 - 曲棍球
             ,"talk.politics.guns" #政治 - 枪支问题
             ,"talk.politics.mideast"] #政治 - 中东问题
train = fetch_20newsgroups(subset="train",categories = categories)
test = fetch_20newsgroups(subset="test",categories = categories)
train
#可以观察到，里面依然是类字典结构，我们可以通过使用键的方式来提取内容
train.target_names
#查看总共有多少篇文章存在
len(train.data) #随意提取一篇文章来看看
train.data[0] #查看一下我们的标签
np.unique(train.target)
len(train.target) #是否存在样本不平衡问题？
for i in [1,2,3]:
 print(i,(train.target == i).sum()/len(train.target))

3 使用TF-IDF将文本数据编码

from sklearn.feature_extraction.text import TfidfVectorizer as TFIDF
Xtrain = train.data
Xtest = test.data
Ytrain = train.target
Ytest = test.target
tfidf = TFIDF().fit(Xtrain)
Xtrain_ = tfidf.transform(Xtrain)
Xtest_ = tfidf.transform(Xtest)
Xtrain_
tosee = pd.DataFrame(Xtrain_.toarray(),columns=tfidf.get_feature_names())
tosee.head()
tosee.shape

4 在贝叶斯上分别建模，查看结果

from sklearn.naive_bayes import MultinomialNB, ComplementNB, BernoulliNB
from sklearn.metrics import brier_score_loss as BS
name = ["Multinomial","Complement","Bournulli"] #注意高斯朴素贝叶斯不接受稀疏矩阵
models = [MultinomialNB(),ComplementNB(),BernoulliNB()]
for name,clf in zip(name,models):
    clf.fit(Xtrain_,Ytrain)
    y_pred = clf.predict(Xtest_)
    proba = clf.predict_proba(Xtest_)
    score = clf.score(Xtest_,Ytest)
    print(name)
    
    #4个不同的标签取值下的布里尔分数
    Bscore = []
    for i in range(len(np.unique(Ytrain))):
        bs = BS(Ytest,proba[:,i],pos_label=i)
        Bscore.append(bs)
        print("\tBrier under {}:{:.3f}".format(train.target_names[i],bs))
        
    print("\tAverage Brier:{:.3f}".format(np.mean(Bscore)))
    print("\tAccuracy:{:.3f}".format(score))
    print("\n")

from sklearn.calibration import CalibratedClassifierCV
name = ["Multinomial"
       ,"Multinomial + Isotonic"
       ,"Multinomial + Sigmoid"
       ,"Complement"
       ,"Complement + Isotonic"
       ,"Complement + Sigmoid"
       ,"Bernoulli"
       ,"Bernoulli + Isotonic"
       ,"Bernoulli + Sigmoid"]
models = [MultinomialNB()
         ,CalibratedClassifierCV(MultinomialNB(), cv=2, method='isotonic')
         ,CalibratedClassifierCV(MultinomialNB(), cv=2, method='sigmoid')
         ,ComplementNB()
         ,CalibratedClassifierCV(ComplementNB(), cv=2, method='isotonic')
         ,CalibratedClassifierCV(ComplementNB(), cv=2, method='sigmoid')
         ,BernoulliNB()
         ,CalibratedClassifierCV(BernoulliNB(), cv=2, method='isotonic')
         ,CalibratedClassifierCV(BernoulliNB(), cv=2, method='sigmoid')
         ]
for name,clf in zip(name,models):
    clf.fit(Xtrain_,Ytrain)
    y_pred = clf.predict(Xtest_)
    proba = clf.predict_proba(Xtest_)
    score = clf.score(Xtest_,Ytest)
    print(name)
    Bscore = []
    for i in range(len(np.unique(Ytrain))):
        bs = BS(Ytest,proba[:,i],pos_label=i)
        Bscore.append(bs)
        print("\tBrier under {}:{:.3f}".format(train.target_names[i],bs))
    print("\tAverage Brier:{:.3f}".format(np.mean(Bscore)))
    print("\tAccuracy:{:.3f}".format(score))
    print("\n")