Spaces:
Runtime error
Runtime error
removed unnecessary file in TextClassifier
Browse files
textclassifier/TextClassifier.py
CHANGED
@@ -4,19 +4,16 @@ import regex as re
|
|
4 |
from twitterscraper import TwitterScraper
|
5 |
from datetime import date
|
6 |
import os
|
7 |
-
|
8 |
|
9 |
# Set one directory up into ROOT_PATH
|
10 |
ROOT_PATH = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
11 |
|
12 |
-
from dotenv import find_dotenv, load_dotenv
|
13 |
-
|
14 |
dotenv_path = find_dotenv()
|
15 |
load_dotenv(dotenv_path)
|
16 |
OPENAI_AUTHTOKEN = os.environ.get("OPENAI_AUTHTOKEN")
|
17 |
|
18 |
|
19 |
-
|
20 |
class TextClassifier:
|
21 |
def __init__(self, model_name="text-davinci-002", from_date='2022-01-01', to_date=str(date.today()),
|
22 |
|
@@ -48,12 +45,6 @@ class TextClassifier:
|
|
48 |
# self.api_key = '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'
|
49 |
openai.api_key = OPENAI_AUTHTOKEN
|
50 |
|
51 |
-
def scrape_tweets(self):
|
52 |
-
"""
|
53 |
-
Scrapes tweets from the given date range.
|
54 |
-
"""
|
55 |
-
self.ts.scrape_tweets()
|
56 |
-
|
57 |
@staticmethod
|
58 |
def cleanup_sentiment_results(classification_unclean):
|
59 |
"""
|
@@ -220,8 +211,6 @@ class TextClassifier:
|
|
220 |
df_topic['topic'] = df_topic['tweet'].apply(self.classify_topic)
|
221 |
return df_topic
|
222 |
|
223 |
-
|
224 |
-
|
225 |
@staticmethod
|
226 |
def cleanup_topic_results(prediction_dict, text):
|
227 |
new_item = text.replace("\n", " ")
|
@@ -252,7 +241,6 @@ class TextClassifier:
|
|
252 |
return row
|
253 |
return None
|
254 |
|
255 |
-
|
256 |
def __repr__(self):
|
257 |
"""
|
258 |
Gives a string that describes which user is classified
|
@@ -260,7 +248,6 @@ class TextClassifier:
|
|
260 |
"""
|
261 |
return "Classifier for user: " + self.user_name + " with model: " + self.model_name + "."
|
262 |
|
263 |
-
|
264 |
# if __name__ == "__main__":
|
265 |
# import pandas as pd
|
266 |
# from datetime import datetime
|
@@ -276,4 +263,3 @@ class TextClassifier:
|
|
276 |
# print(df)
|
277 |
# # save to csv in a folder under politweet with timestamp in name
|
278 |
# df.to_csv(f"{datetime.now().strftime('%Y-%m-%d %H-%M-%S')}_tweets.csv")
|
279 |
-
|
|
|
4 |
from twitterscraper import TwitterScraper
|
5 |
from datetime import date
|
6 |
import os
|
7 |
+
from dotenv import find_dotenv, load_dotenv
|
8 |
|
9 |
# Set one directory up into ROOT_PATH
|
10 |
ROOT_PATH = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
11 |
|
|
|
|
|
12 |
dotenv_path = find_dotenv()
|
13 |
load_dotenv(dotenv_path)
|
14 |
OPENAI_AUTHTOKEN = os.environ.get("OPENAI_AUTHTOKEN")
|
15 |
|
16 |
|
|
|
17 |
class TextClassifier:
|
18 |
def __init__(self, model_name="text-davinci-002", from_date='2022-01-01', to_date=str(date.today()),
|
19 |
|
|
|
45 |
# self.api_key = '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'
|
46 |
openai.api_key = OPENAI_AUTHTOKEN
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
@staticmethod
|
49 |
def cleanup_sentiment_results(classification_unclean):
|
50 |
"""
|
|
|
211 |
df_topic['topic'] = df_topic['tweet'].apply(self.classify_topic)
|
212 |
return df_topic
|
213 |
|
|
|
|
|
214 |
@staticmethod
|
215 |
def cleanup_topic_results(prediction_dict, text):
|
216 |
new_item = text.replace("\n", " ")
|
|
|
241 |
return row
|
242 |
return None
|
243 |
|
|
|
244 |
def __repr__(self):
|
245 |
"""
|
246 |
Gives a string that describes which user is classified
|
|
|
248 |
"""
|
249 |
return "Classifier for user: " + self.user_name + " with model: " + self.model_name + "."
|
250 |
|
|
|
251 |
# if __name__ == "__main__":
|
252 |
# import pandas as pd
|
253 |
# from datetime import datetime
|
|
|
263 |
# print(df)
|
264 |
# # save to csv in a folder under politweet with timestamp in name
|
265 |
# df.to_csv(f"{datetime.now().strftime('%Y-%m-%d %H-%M-%S')}_tweets.csv")
|
|