-
Notifications
You must be signed in to change notification settings - Fork 0
/
preprocessor.py
44 lines (34 loc) · 1.47 KB
/
preprocessor.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
import re
import pandas as pd
import nltk
nltk.downloader.download('vader_lexicon')
from nltk.sentiment.vader import SentimentIntensityAnalyzer
def preprocess(data):
messages = re.findall('(\d+/\d+/\d+, \d+:\d+\d+ [A-Z]*) - (.*?): (.*)', data)
df = pd.DataFrame(messages, columns=['date', 'user', 'message'])
df['date'] = pd.to_datetime(df['date'], format="%m/%d/%y, %I:%M %p")
df['only_date'] = df['date'].dt.date
df['year'] = df['date'].dt.year
df['month_num'] = df['date'].dt.month
df['month'] = df['date'].dt.month_name()
df['day'] = df['date'].dt.day
df['day_name'] = df['date'].dt.day_name()
df['hour'] = df['date'].dt.hour
df['minute'] = df['date'].dt.minute
period = []
for hour in df[['day_name', 'hour']]['hour']:
if hour == 23:
period.append(str(hour) + "-" + str('00'))
elif hour == 0:
period.append(str('00') + "-" + str(hour + 1))
else:
period.append(str(hour) + "-" + str(hour + 1))
df['period'] = period
# Sentiment Analysis works
data = df.dropna()
sentiments = SentimentIntensityAnalyzer()
df["positive"] = [sentiments.polarity_scores(i)["pos"] for i in data["message"]]
df["negative"] = [sentiments.polarity_scores(i)["neg"] for i in data["message"]]
df["neutral"] = [sentiments.polarity_scores(i)["neu"] for i in data["message"]]
df["compound"] = [sentiments.polarity_scores(i)["compound"] for i in data["message"]]
return df