貝葉斯理論
在我們有一大堆樣本（包含特徵和類別）的時候，我們非常容易通過統計得到 p(特徵|類別) .

大家又都很熟悉下述公式：

#coding: utf-8
import os
import time
import random
import jieba  #處理中文
#import nltk  #處理英文
import sklearn
from sklearn.naive_bayes import MultinomialNB
import numpy as np
import pylab as pl
import matplotlib.pyplot as plt

#粗暴的詞去重
 

def make_word_set(words_file):
    words_set = set()
    with open(words_file, 'r') as fp:
        for line in fp.readlines():
            word = line.strip().decode("utf-8")
            if len(word)>0 and word not in words_set: # 去重
                words_set.add(word)
    return words_set


# 文字處理，也就是樣本生成過程
 

def text_processing(folder_path, test_size=0.2):
    folder_list = os.listdir(folder_path)
    data_list = []
    class_list = []

    # 遍歷資料夾
    for folder in folder_list:
        new_folder_path = os.path.join(folder_path, folder)
        files = os.listdir(new_folder_path)
        # 讀取檔案
        j = 1
 

        for file in files:
            if j > 100: # 怕記憶體爆掉，只取100個樣本檔案，你可以註釋掉取完
                break
            with open(os.path.join(new_folder_path, file), 'r') as fp:
               raw = fp.read()
            ## 是的，隨處可見的jieba中文分詞
            jieba.enable_parallel(4) # 開啟並行分詞模式，引數為並行程序數，不支援windows
            word_cut = jieba.cut(raw, cut_all=False) # 精確模式，返回的結構是一個可迭代的genertor
            word_list = list(word_cut) # genertor轉化為list，每個詞unicode格式
            jieba.disable_parallel() # 關閉並行分詞模式

            data_list.append(word_list) #訓練集list
            class_list.append(folder.decode('utf-8')) #類別
            j += 1

    ## 粗暴地劃分訓練集和測試集
    data_class_list = zip(data_list, class_list)
    random.shuffle(data_class_list)
    index = int(len(data_class_list)*test_size)+1
    train_list = data_class_list[index:]
    test_list = data_class_list[:index]
    train_data_list, train_class_list = zip(*train_list)
    test_data_list, test_class_list = zip(*test_list)

    #其實可以用sklearn自帶的部分做
    #train_data_list, test_data_list, train_class_list, test_class_list = sklearn.cross_validation.train_test_split(data_list, class_list, test_size=test_size)


    # 統計詞頻放入all_words_dict
    all_words_dict = {}
    for word_list in train_data_list:
        for word in word_list:
            if all_words_dict.has_key(word):
                all_words_dict[word] += 1
            else:
                all_words_dict[word] = 1

    # key函式利用詞頻進行降序排序
    all_words_tuple_list = sorted(all_words_dict.items(), key=lambda f:f[1], reverse=True) # 內建函式sorted引數需為list
    all_words_list = list(zip(*all_words_tuple_list)[0])

    return all_words_list, train_data_list, test_data_list, train_class_list, test_class_list

def words_dict(all_words_list, deleteN, stopwords_set=set()):
    # 選取特徵詞
    feature_words = []
    n = 1
    for t in range(deleteN, len(all_words_list), 1):
        if n > 1000: # feature_words的維度1000
            break

        if not all_words_list[t].isdigit() and all_words_list[t] not in stopwords_set and 1<len(all_words_list[t])<5:
            feature_words.append(all_words_list[t])
            n += 1
    return feature_words


# 文字特徵
def text_features(train_data_list, test_data_list, feature_words, flag='nltk'):
    def text_features(text, feature_words):
        text_words = set(text)
        ## -----------------------------------------------------------------------------------
        if flag == 'nltk':
            ## nltk特徵 dict
            features = {word:1 if word in text_words else 0 for word in feature_words}
        elif flag == 'sklearn':
            ## sklearn特徵 list
            features = [1 if word in text_words else 0 for word in feature_words]
        else:
            features = []
        ## -----------------------------------------------------------------------------------
        return features
    train_feature_list = [text_features(text, feature_words) for text in train_data_list]
    test_feature_list = [text_features(text, feature_words) for text in test_data_list]
    return train_feature_list, test_feature_list



# 分類，同時輸出準確率等
def text_classifier(train_feature_list, test_feature_list, train_class_list, test_class_list, flag='nltk'):
    ## -----------------------------------------------------------------------------------
    if flag == 'nltk':
        ## 使用nltk分類器
        train_flist = zip(train_feature_list, train_class_list)
        test_flist = zip(test_feature_list, test_class_list)
        classifier = nltk.classify.NaiveBayesClassifier.train(train_flist)
        test_accuracy = nltk.classify.accuracy(classifier, test_flist)
    elif flag == 'sklearn':
        ## sklearn分類器
        classifier = MultinomialNB().fit(train_feature_list, train_class_list)
        test_accuracy = classifier.score(test_feature_list, test_class_list)
    else:
        test_accuracy = []
    return test_accuracy



print "start"

## 文字預處理
folder_path = './Database/SogouC/Sample'
all_words_list, train_data_list, test_data_list, train_class_list, test_class_list = text_processing(folder_path, test_size=0.2)

# 生成stopwords_set
stopwords_file = './stopwords_cn.txt'
stopwords_set = make_word_set(stopwords_file)

## 文字特徵提取和分類
# flag = 'nltk'
flag = 'sklearn'
deleteNs = range(0, 1000, 20)
test_accuracy_list = []
for deleteN in deleteNs:
    # feature_words = words_dict(all_words_list, deleteN)
    feature_words = words_dict(all_words_list, deleteN, stopwords_set)
    train_feature_list, test_feature_list = text_features(train_data_list, test_data_list, feature_words, flag)
    test_accuracy = text_classifier(train_feature_list, test_feature_list, train_class_list, test_class_list, flag)
    test_accuracy_list.append(test_accuracy)
print test_accuracy_list

# 結果評價
#plt.figure()
plt.plot(deleteNs, test_accuracy_list)
plt.title('Relationship of deleteNs and test_accuracy')
plt.xlabel('deleteNs')
plt.ylabel('test_accuracy')
plt.show()
#plt.savefig('result.png')

print "finished"