from numpy import *
import re
import operator
import feedparser
def loadDataSet():
posting_ist = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
['stop', 'posting', 'stupid', 'worthless', 'garbage'],
['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
class_vec = [0, 1, 0, 1, 0, 1]
return posting_ist, class_vec
def createVocabList(data_set): # 将矩阵内所有词放入set中去重
vocab_set = set([]) # 创建空集
for document in data_set:
vocab_set = vocab_set | set(document) # 并集
return list(vocab_set)
def setOfWords2Vec(vocab_list, input_set): # 统计每个词的出现次数
return_vec = [0] * len(vocab_list) # 创建一个所含元素都为0的向量
for word in input_set:
if word in vocab_list:
return_vec[vocab_list.index(word)] = 1 # vocab_list是没有重复值的
else:
print(print('the word : %s is not in my vocabulary!' % word))
return return_vec
def trainNB0(train_matrix, train_category):
'''
朴素贝叶斯训练函数
:param train_matrix: 文档矩阵
:param train_category: 文档对应标签构成的向量
:return:
'''
num_train_docs = len(train_matrix) # 矩阵行数
num_words = len(train_matrix[0]) # 矩阵数列
p_abusive = sum(train_category) / float(num_train_docs) # 总侮辱语言概率
p0_num = ones(num_words) # 初始化概率
p1_num = ones(num_words)
p0_denom = 2.0
p1_denom = 2.0
for i in range(num_train_docs):
if train_category[i] == 1:
p1_num += train_matrix[i] # 向量相加
p1_denom += sum(train_matrix[i]) # 统计1的个数
else:
p0_num += train_matrix[i]
p0_denom += sum(train_matrix[i])
p1_vect = log(p1_num / p1_denom)
p0_vect = log(p0_num / p0_denom)
return p0_vect, p1_vect, p_abusive
def classifyNB(vec2_classify, p0_vec, p1_vec, p_class1):
p1 = sum(vec2_classify * p1_vec) + log(p_class1)
p0 = sum(vec2_classify * p0_vec) + log(1 - p_class1)
if p1 > p0:
return 1
else:
return 0
def testingNB():
list_oposts, list_classes = loadDataSet() # 拿到矩阵和标签
my_vocab_list = createVocabList(list_oposts) # 将矩阵内所有词放入set中去重
train_mat = []
for postin_doc in list_oposts:
train_mat.append(setOfWords2Vec(my_vocab_list, postin_doc)) # 返回值为统计值的向量
p0V, p1V, pAb = trainNB0(array(train_mat), array(list_classes))
test_entry = ['love', 'my', 'dalmation']
this_doc = array(setOfWords2Vec(my_vocab_list, test_entry))
print(test_entry, 'classified as:', classifyNB(this_doc, p0V, p1V, pAb))
test_entry = ['stupid', 'garbage']
this_doc = array(setOfWords2Vec(my_vocab_list, test_entry))
print(test_entry, 'classified as:', classifyNB(this_doc, p0V, p1V, pAb))
def bagOfWords2Vec(vocab_list, input_set): # 统计每个词的出现次数
return_vec = [0] * len(vocab_list) # 创建一个所含元素都为0的向量
for word in input_set:
if word in vocab_list:
return_vec[vocab_list.index(word)] += 1 # vocab_list是没有重复值的
return return_vec
def textParse(big_string):
list_of_tokens = re.split(r'w*', big_string)
return [tok.lower for tok in list_of_tokens if len(tok) > 1]
def spamTest():
doc_list = []
class_list = []
full_text = []
for i in range(1, 26): # 导入文本文件 应为有25个文件，所以取26
word_list = textParse(open(r'emailspam\%d.txt' % i).read()) # 导入文件解析成列表
doc_list.append(word_list) # 矩阵
full_text.extend(word_list) # 列表
class_list.append(1) # 垃圾邮件
print(i)
word_list = textParse(open(r'emailham\%d.txt' % i).read())
doc_list.append(word_list)
full_text.extend(word_list)
class_list.append(0)
vocab_list = createVocabList(doc_list) # 将矩阵内所有词放入set中去重
training_set = list(range(50)) # 共50邮件
test_set = []
for i in range(10): # 选十个测试
rand_index = int(random.uniform(0, len(training_set))) # 随机选10个
test_set.append(training_set[rand_index])
del (training_set[rand_index]) # 删除已选数字，防止重复选邮件
train_mat = []
train_classes = []
for doc_index in training_set: # 训练剩余40个
train_mat.append(bagOfWords2Vec(vocab_list, doc_list[doc_index])) # 统计训练邮件每个词的出现次数
train_classes.append(class_list[doc_index])
p0V, p1V, p_spam = trainNB0(array(train_mat), array(train_classes))
error_count = 0
for doc_index in test_set:
word_vector = bagOfWords2Vec(vocab_list, doc_list[doc_index])
if classifyNB(array(word_vector), p0V, p1V, p_spam) != class_list[doc_index]:
error_count += 1
print('the error rate is : ', float(error_count) / len(test_set))
def calcMostFreq(vocab_list,full_text):
freq_dict = {}
for token in vocab_list:
freq_dict[token] = full_text.count(token)
sorted_freq = sorted(freq_dict.items(),key=operator.itemgetter(1),reverse=True)
return sorted_freq[:30]
def localWords(feed1,feed0):
doc_list= []
class_list = []
full_text = []
min_len = min(len(feed1.entries),len(feed0.entries))
for i in range(min_len):
word_list =textParse(feed1.entries[i]['summary'])
doc_list.append(word_list)
full_text.extend(word_list)
class_list.append(1)
word_list = textParse(feed0.entries[i]['summary'])
doc_list.append(word_list)
full_text.extend(word_list)
class_list.append(0)
vocab_list = createVocabList(doc_list) # 将矩阵内所有词放入set中去重
top30_words = calcMostFreq(vocab_list,full_text)
for pair_w in top30_words:
if pair_w[0] in vocab_list:
vocab_list.remove(pair_w[0])
training_set = list(range(2*min_len))
test_set = []
for i in range(20):
rand_index = int(random.uniform(0,len(training_set)))
test_set.append(training_set[rand_index])
del training_set[rand_index]
train_mat = []
train_classes = []
for doc_index in training_set:
train_mat.append(bagOfWords2Vec(vocab_list,doc_list[doc_index]))
train_classes.append(class_list[doc_index])
p0v,p1v,p_spam = trainNB0(array(train_mat),array(train_classes))
error_count = 0
for doc_index in test_set:
word_vector = bagOfWords2Vec(vocab_list,doc_list[doc_index])
if classifyNB(array(word_vector),p0v,p1v,p_spam) != class_list[doc_index]:
error_count += 1
print('the error rate is : ',float(error_count)/len(test_set))
return vocab_list,p0v,p1v
def getTopwords(nf,sf):
vocab_list,p0v,p1v = localWords(nf,sf)
top_ny = []
top_sf = []
for i in range(len(p0v)):
if p0v[i] > -6.0:
top_sf.append((vocab_list[i],p0v[i]))
if p1v[i] > -6.0:
top_ny.append((vocab_list[i],p1v[i]))
sorted_sf = sorted(top_sf,key=lambda pair:pair[1],reverse=True)
print('sf**sf**sf**sf**sf**')
for item in sorted_sf:
print(item[0])
sorted_ny = sorted(top_ny,key=lambda pair:pair[1],reverse=True)
print('ny**ny**ny**ny**ny**')
for item in sorted_ny:
print(item[0])