-
Notifications
You must be signed in to change notification settings - Fork 0
/
MNB.py
198 lines (164 loc) · 5.67 KB
/
MNB.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
# -*- coding: utf-8 -*-
__author__ = 'Nghiep'
import json
from time import sleep
from DB import DB
import math
import hashlib
from tokenizer.VnTokenizer import VnTokenizer
import logging.handlers
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn import metrics
from operator import itemgetter
from sklearn.metrics import classification_report
import csv
import os
import numpy as np
formatter = logging.Formatter('%(asctime)s\t%(process)-6d\t%(levelname)-6s\t%(name)s\t%(message)s')
logger = logging.getLogger('CRAWLER')
logger.setLevel(logging.DEBUG)
file_handler = logging.handlers.RotatingFileHandler('logs/leraner.txt', 'a', 5000000, 5) # 5M - 5 files
file_handler.setFormatter(formatter)
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.DEBUG)
console_handler.setFormatter(formatter)
logger.addHandler(file_handler)
logger.addHandler(console_handler)
logging.getLogger('pika').setLevel(logging.INFO)
logging.getLogger('pika.frame').setLevel(logging.INFO)
# Load URL --> redis
import redis
rc = redis.Redis('localhost')
NUM_DOCS = 10735 # Tong so van ban
TABLE = 'site_content_2'
LIST_CATE = [3, 6, 8, 11, 12, 13, 14]
TF_THRESHOLD = 2 # chi lay cac tu co term frequency > 1
WORDS = {} # Nhan tu trong tap du lieu hoc
NUMWORDS = {'total_word': 0}
WORD_INCATE = {}
mapCategoryCounter = {}
NUM_DOCS_IN_CATE = {}
DOC_TRAIN = np.array([])
CLASS_TRAIN = np.array([])
def getWords():
WINDOW_SIZE = 1000 # so luong item muon fetch
WINDOW_INDEX = 0
NUMBER_OF_DOC = 0
db = DB()
# STEP 1: tính tổng trọng số của các lớp
# Đọc toàn bộ db, khi nào ko còn row nào thì thôi
while True:
start = WINDOW_SIZE * WINDOW_INDEX + 1
stop = WINDOW_SIZE * (WINDOW_INDEX + 1)
# things = query.slice(start, stop).all()
query = "select id, cate_id, tf from " + TABLE + " order by id limit " + str(start) + ", " + str(WINDOW_SIZE)
logger.info(query)
cursor = db.cursor()
# logger.info(query)
cursor.execute(query)
rows = cursor.fetchall()
#import pdb
#pdb.set_trace()
if rows == None or len(rows) == 0:
break
else:
logger.info("Query size: " + str(len(rows)))
for row in rows:
content = row['tf']
cateId = row['cate_id']
docId = row["id"]
# print content
try :
mapWeightInDoc = json.loads(content)
except:
continue
for word in mapWeightInDoc:
if(str(type(word)) == '<type \'unicode\'>'):
word = word.encode('utf-8')
if WORDS.has_key(word) == False:
WORDS[word] = 0
rc.hset('words', 'data', json.dumps(WORDS, ensure_ascii=False, encoding='utf-8'))
# sleep(2)
WINDOW_INDEX += 1
# print WORD_INCATE
return WORD_INCATE
def convertData():
print "Converting..."
WINDOW_SIZE = 10 # so luong item muon fetch
WINDOW_INDEX = 0
NUMBER_OF_DOC = 0
db = DB()
# STEP 1: tính tổng trọng số của các lớp
# Đọc toàn bộ db, khi nào ko còn row nào thì thôi
while True:
start = WINDOW_SIZE * WINDOW_INDEX + 1
stop = WINDOW_SIZE * (WINDOW_INDEX + 1)
# things = query.slice(start, stop).all()
query = "select id, cate_id, tf from " + TABLE + " order by id limit " + str(start) + ", " + str(WINDOW_SIZE)
logger.info(query)
cursor = db.cursor()
# logger.info(query)
cursor.execute(query)
rows = cursor.fetchall()
#import pdb
#pdb.set_trace()
if rows == None or len(rows) == 0:
break
else:
logger.info("Query size: " + str(len(rows)))
for row in rows:
content = row['tf']
cateId = row['cate_id']
docId = row["id"]
# print content
try :
mapWeightInDoc = json.loads(content)
except:
continue
trainItem = np.array([])
for word in mapWeightInDoc:
if WORDS.has_key(word):
trainItem = np.append([mapWeightInDoc[word]])
else:
trainItem = np.append([0])
DOC_TRAIN = np.append([trainItem])
trainItem = np.fill(0)
CLASS_TRAIN = np.append([cateId])
print CLASS_TRAIN
return None
def classifier():
nb = MultinomialNB(alpha=0)
nb.fit(DOC_TRAIN, CLASS_TRAIN)
db = DB()
query = 'select cate_id, tf, url, content from site_content_3'
cursor = db.cursor()
logger.info(query)
cursor.execute(query)
rows = cursor.fetchall()
for row in rows:
currentCateId = row['cate_id']
print 'rowID => ', row['cate_id'];
url = row['url']
tf = row['tf']
content = row['content']
termFrequencyDict = {}
# continue
try:
termFrequencyDict = json.loads(tf)
except:
print 'error => ', url
continue
testItem = np.array([])
for word in termFrequencyDict:
tf = termFrequencyDict[word]
if WORDS.has_key(word):
testItem = np.append([tf])
else:
testItem = np.append([0])
print "CURRENT CATE ", currentCateId
print "NEW ", nb.predict(testItem)
if __name__ == '__main__':
getWords()
print 'MultinomialNB'
convertData()