-
Notifications
You must be signed in to change notification settings - Fork 1
/
app.py
62 lines (47 loc) · 1.89 KB
/
app.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
import pandas
import re
import nltk
# nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from nltk.tokenize import RegexpTokenizer, word_tokenize
# nltk.download('wordnet')
from nltk.stem.wordnet import WordNetLemmatizer
# nltk.download('punkt')
# load the dataset
dataset = pandas.read_csv('sample-data/experience.csv')
# print("Top Occupations")
# occupationFrequency = pandas.Series(dataset['Profession'].apply(lambda x: x.lower()).value_counts()[:50])
# print(occupationFrequency)
# Creating a list of stop words and adding custom stopwords
stop_words = set(stopwords.words("english"))
# Creating a list of custom stopwords
new_words = ["using", "show", "result", "large", "also", "iv", "one", "two", "new", "previously", "shown", "well", "recently", "includes", "may", "im", "etc", "grad", "actually", "working", "worked"]
stop_words = stop_words.union(new_words)
corpus = []
for respondent in dataset.values:
try:
if respondent[2]:
data = str(respondent[2]).lower()
# Strip Links
data = re.sub(r'^https?://.*[\r\n]*', '', data, flags=re.MULTILINE)
# Strip out all characters except letters and spaces
data = re.sub('[^a-z\s]+', '', data)
data = word_tokenize(data)
# Convert to lowercase
# text = text.lower()
# remove tags
# text = re.sub("</?.*?>", " <> ", text)
# remove special characters and digits
# text = re.sub("(\\d|\\W)+", " ", text)
# Stemming
ps = PorterStemmer()
# Lemmatisation
lem = WordNetLemmatizer()
text = [lem.lemmatize(word) for word in data if word not in stop_words]
text = " ".join(text)
corpus.append(text)
except Exception as ex:
print(ex)
# Output result
print(corpus)