-
Notifications
You must be signed in to change notification settings - Fork 0
/
MalaysiaCode.py
178 lines (134 loc) · 5.84 KB
/
MalaysiaCode.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
# String matching algorithm - Trie Algorithm
import plotly.express as px
# TrieNode: to represent a node in the trie
class TrieNode:
# create instance of nodes in Trie
def __init__(self, letter):
self.letter = letter
self.children = {}
self.is_the_end_of_word = False
# Create Trie
class Trie:
def __init__(self): # creating an instance of TrieNode
self.root = TrieNode("") #create root node with no value
def add(self, word):
curr_node = self.root
for ch in word:
if ch not in curr_node.children:
curr_node.children[ch] = TrieNode(ch)
curr_node = curr_node.children[ch]
curr_node.is_the_end_of_word = True #return true when it reaches the last node in the Trie
#search matching pattern in Trie
def search(self, word):
if word == "":
return True #return True if no words checked
curr_node = self.root
for ch in word:
if ch not in curr_node.children:
return False # return false to terminate loop - pattern does not match
curr_node = curr_node.children[ch]
return curr_node.is_the_end_of_word # return true if pattern matched until search is done until last node
# Read text file imported from website
def readArticle(originalText):
with open('Text Files - Country Articles\Malaysia.txt', 'r', encoding="utf-8") as file:
for line in file:
for word in line.split():
originalText.append(word)
def readPositive(positive_words):
with open('Text Files - Positive, Negative, Neutral, Stop Words\positive.txt', 'r', encoding="utf-8") as file:
for line in file:
for word in line.split(', '):
positive_words.append(word)
def readNegative(negative_words):
with open('Text Files - Positive, Negative, Neutral, Stop Words\\negative.txt', 'r', encoding="utf-8") as file:
for line in file:
for word in line.split(', '):
negative_words.append(word)
def readNeutral(neutral_words):
with open('Text Files - Positive, Negative, Neutral, Stop Words\\neutral.txt', 'r', encoding="utf-8") as file:
for line in file:
for word in line.split(', '):
neutral_words.append(word)
def readStop(stop_words):
with open('Text Files - Positive, Negative, Neutral, Stop Words\stop.txt', 'r', encoding="utf-8") as file:
for line in file:
for word in line.split('\n'):
stop_words.append(word)
def refined(lst):
formatted = []
for Line in lst:
words = Line.split()
for i in range(len(words)):
formatted.append(words[i].replace("\n",""))
return formatted
# Driver code
# Call function to read from text file
originalText = []
positive_words = []
negative_words = []
neutral_words = []
stop_words = []
readArticle(originalText)
readPositive(positive_words)
readNegative(negative_words)
readNeutral(neutral_words)
readStop(stop_words)
# To display the article
articleText = refined(originalText) #maybe boleh buang
print("\nList", articleText)
trieStop = Trie()
# Add stop words into the TRIE
for i in range(len(stop_words)):
trieStop.add(stop_words[i].lower())
stopMatch = []
extractedArticle = [] #articles with no stop words
# Remove stop word
for i in range(len(articleText)):
if trieStop.search(articleText[i].lower()):
stopMatch.append(articleText[i])
else:
extractedArticle.append(articleText[i])
#call function to create TRIE for each positive, negative and neutral words
triePositive = Trie()
trieNegative = Trie()
trieNeutral = Trie()
# Add positive words into the positive TRIE
for i in range(len(positive_words)):
triePositive.add(positive_words[i].lower()) #add positive words in lower case
# Add negative words into the negative TRIE
for i in range(len(negative_words)):
trieNegative.add(negative_words[i].lower()) #add negative words in lower case
# Add neutral words into the neutral TRIE
for i in range(len(neutral_words)):
trieNeutral.add(neutral_words[i].lower()) #add neutral words in lower case
#array for matching pattern
positiveMatch = []
negativeMatch = []
neutralMatch = []
#search word from extracted article in the TRIE
for i in range(len(extractedArticle)):
if triePositive.search(extractedArticle[i].lower()): #search word from extracted article in the positive TRIE
positiveMatch.append(extractedArticle[i])
elif trieNegative.search(extractedArticle[i].lower()): #search word from extracted article in the negative TRIE
negativeMatch.append(extractedArticle[i])
elif trieNeutral.search(extractedArticle[i].lower()): #search word from extracted article in the neutral TRIE
neutralMatch.append(extractedArticle[i])
# calculate sentiment score
sentiment_score = round(((len(positiveMatch) - len(negativeMatch)) / (len(neutralMatch) + len(negativeMatch) + len(positiveMatch))) * 100 , 2)
print("\nSentence: ", extractedArticle, "\n")
print("Positive: ", positiveMatch, "\n")
print("Negative: ", negativeMatch, "\n")
print("Neutral: ", neutralMatch, "\n")
# Count Word
print("Positive Word: ", len(positiveMatch))
print("Negative Word: ", len(negativeMatch))
print("Neutral Word: ", len(neutralMatch))
print("Sentiment Score: ", sentiment_score)
a = [len(positiveMatch)]
b = [len(negativeMatch)]
c = [len(neutralMatch)]
number_count = [a,b,c]
type_word = ["Positive", "Negative", "Neutral"]
country_name = ["Malaysia"]
fig = px.bar(x=["Positive", "Negative", "Neutral"], y=[len(positiveMatch), len(negativeMatch), len(neutralMatch)], title="Malaysia Bar Plot")
fig.write_html('Malaysia_bar.html', auto_open=True)