-
Notifications
You must be signed in to change notification settings - Fork 0
/
ClassificationMain.py
82 lines (64 loc) · 2.24 KB
/
ClassificationMain.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
import Preprocessing as pre
import TermWeighting as termW
import MultiNomialNaiveBayesClassification as mul
from MultiNomialNaiveBayesClassification import Document
# read csv file
# each row contains text and its classification
def read_file(filename):
documents = []
with open(filename) as inputfile:
for line in inputfile:
line = line.split(",")
document = ""
for i in range(len(line) - 1):
document += line[i]
classification = line[len(line)-1]
documents.append(Document(document, classification))
return documents
def read_test_data(filename):
# read csv file
documents = []
with open(filename) as inputfile:
for line in inputfile:
# line = line.split(",")
# document = ""
# for i in range(len(line) - 1):
# document += line[i]
# classification = line[len(line)-1]
documents.append(line)
return documents
def print_documents(documents):
for document in documents:
print(document.frequencies, document.classification)
def return_processed_data(documents, data):
for i in range(len(documents)):
documents[i].frequencies = data[i]
def print_array(documents):
for document in documents:
print(document)
documents = read_file("sms.csv")
print(len(documents))
# Preprocessing
texts = pre.tokenization([document.frequencies for document in documents])
texts = pre.advanced_filtering(texts)
texts = pre.filtering(texts)
texts = pre.stemming(texts)
texts = pre.filtering(texts)
terms = pre.termFromDocuments(texts)
# Term Weighting
rawWeight = termW.rawTermWeighting(terms, texts)
# Insert term frequencies to each document
for i in range(len(documents)):
documents[i].frequencies = rawWeight[i]
# Read test data
test_data = read_test_data("test_data.csv")
test_data = pre.tokenization(test_data)
test_data = pre.advanced_filtering(test_data)
test_data = pre.filtering(test_data)
test_data = pre.stemming(test_data)
test_data = pre.filtering(test_data)
# Classification
i = 1
for test in test_data:
print(i, mul.decision(test, terms, documents))
i+=1