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
| import pandas as pd
import math
commonWords = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', 'your', 'yours', 'yourself',
'yourselves', 'he', 'him', 'his', 'himself', 'she', 'her', 'hers', 'herself', 'it', 'its', 'itself',
'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', 'these',
'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do',
'does', 'did', 'doing', 'a', 'an',
'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with',
'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to',
'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once',
'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most',
'other', 'some', 'such', 'no', 'nor',
'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don',
'should', 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', 'couldn', 'didn', 'doesn', 'hadn',
'hasn', 'haven', 'isn', 'ma', 'mightn', 'mustn', 'needn', 'shan', 'shouldn', 'wasn', 'weren', 'won',
'wouldn']
class myNaiveBayesAbstract:
def __init__(self, trainingSetName: str, labelName: str, abstractName: str):
print('init trainingSet')
self.trainingSet = self.readTrainingSet(trainingSetName)
self.trainingLabels = self.trainingSet[labelName]
self.trainingAbstract = self.trainingSet[abstractName]
self.trainingSize = len(self.trainingSet)
print('init labelData')
labelSet = list(set(self.trainingLabels))
self.trLabelDic = {}
for i in labelSet:
self.trLabelDic[i] = {}
self.trLabelDic[i]['count'] = 0
self.trLabelDic[i]['word'] = []
print(self.trLabelDic)
def isCommonWord(self, word):
if word in commonWords:
return True
else:
return False
def readTrainingSet(self, name: str):
print('readTrainSet: ', name)
return pd.read_csv(name)
def collectAbstract(self, words, label):
if label in self.trLabelDic:
self.trLabelDic[label]['count'] += 1
self.trLabelDic[label]['word'] += words
else:
print("error can't find " + label + " in trLabelDic.")
def calculateProbability(self, testData):
tempDic = {}
for key in self.trLabelDic.keys():
tempDic[key] = {}
for key in self.trLabelDic.keys():
wordsCollection = self.trLabelDic[key]['word']
for word in wordsCollection:
if not self.isCommonWord(word):
if word in tempDic[key]:
tempDic[key][word] += 1
else:
tempDic[key][word] = 1
uniqueWords = []
for key in self.trLabelDic.keys():
for tempword in tempDic[key]:
if tempword not in uniqueWords:
uniqueWords.append(tempword)
testSize = len(testData)
testUniSize = 0
for i in range(0, testSize):
words = testData[i].split(" ")
for word in words:
if not self.isCommonWord(word):
if word not in uniqueWords:
testUniSize += 1
totalUniCount = testUniSize + len(uniqueWords)
testLabels = []
for i in range(0, testSize):
words = testData[i].split(" ")
probability = {}
for key in self.trLabelDic.keys():
probability[key] = math.log(
self.trLabelDic[key]['count'] / self.trainingSize, 10)
for word in words:
if not self.isCommonWord(word):
for key in self.trLabelDic.keys():
totalCount = len(
self.trLabelDic[key]['word']) + totalUniCount
if word in tempDic[key]:
probability[key] = probability[key] + math.log(
(tempDic[key][word] + 1) / (totalCount), 10)
else:
probability[key] = probability[key] + math.log(
1 / (totalCount), 10)
max_num = max(probability, key=probability.get)
for key in self.trLabelDic.keys():
if probability[max_num] == probability[key]:
testLabels = testLabels + [key]
return testLabels
def classify(self, testData):
print('classify')
testLabels = self.calculateProbability(testData)
return testLabels
def predict(self, abstracts):
for i in range(0, self.trainingSize):
words = self.trainingAbstract[i].split(' ')
tempLabel = self.trainingLabels[i]
self.collectAbstract(words, tempLabel)
return self.calculateProbability(abstracts)
naiveBayesAbstract = myNaiveBayesAbstract('trg.csv', 'class', 'abstract')
test_set = pd.read_csv("tst.csv")
test_set['class'] = naiveBayesAbstract.predict(test_set["abstract"])
test_set.drop(['abstract'], axis=1).to_csv('out.csv', index=False)
test_labels = list(set(test_set['class']))
for key in test_labels:
print(key + ': ' + str(len(test_set[test_set['class'] == key])))
|
