89b4755c65
adds link to full package to readme
master
Michael Beck
2023-08-31 01:23:38 +02:00
01e58b1b99
adds html files to gitignore
Michael Beck
2023-08-31 01:21:31 +02:00
d0fcefedf4
data/OUT/profiles/CovTweets.html gelöscht
Michael Beck
2023-08-31 01:20:39 +02:00
71cf907249
data/OUT/profiles/AllTweets.html gelöscht
Michael Beck
2023-08-31 01:20:31 +02:00
a9018fedee
REALLY corrects the filetree
Michael Beck
2023-08-30 21:54:13 +02:00
d94a93295f
corrects filetree
Michael Beck
2023-08-30 21:53:05 +02:00
80b63b39df
adds readme
0.2.0
Michael Beck
2023-08-30 21:45:38 +02:00
d8136909c8
corrects import of own functions that didn't work anymore because of a newer python version.
Michael Beck
2023-08-30 21:45:27 +02:00
1c6d9d5415
cleans and renames files
Michael Beck
2023-08-30 21:18:55 +02:00
4e08cde317
finishes classification scripts
Michael Beck
2023-08-16 10:06:16 +02:00
2535683cdc
finishes classification scripts
Michael Beck
2023-08-15 14:51:28 +02:00
8f744a08be
adds final counter keywords
Michael Beck
2023-08-15 14:30:40 +02:00
df5fd51a5f
repairs stupid
Michael Beck
2023-08-15 14:30:13 +02:00
3d4f559d2d
adds model training stats
Michael Beck
2023-08-15 14:29:42 +02:00
2e067b6a64
adds both classification scripts. Corrects inclusion of CleanTweets functions.
Michael Beck
2023-08-15 14:23:56 +02:00
7a16526a97
adds dataset profiles
Michael Beck
2023-08-15 14:20:13 +02:00
b89b5969ec
adds typerror controls
Michael Beck
2023-08-15 14:19:33 +02:00
7c6b618272
adds both training scripts and evaluation files of topic classification
Michael Beck
2023-08-15 14:19:08 +02:00
90aa58239c
adds generation of model-training dataset
Michael Beck
2023-08-14 15:37:30 +02:00
1beff96ae9
adds model training code
Michael Beck
2023-08-14 15:37:05 +02:00
881d3d6d6d
adds tweet-text-cleaning functions
Michael Beck
2023-08-14 15:36:46 +02:00
5a63c478e9
adds dataset profiler
Michael Beck
2023-08-08 15:32:12 +02:00
ed61d52182
adds files to gitignore
Michael Beck
2023-08-08 00:07:42 +02:00
a26d150060
renames pretest classification file
Michael Beck
2023-08-08 00:06:18 +02:00
d791e4a293
adds classification file. adds removal of empty tweets after transormation for classification preparation
Michael Beck
2023-08-08 00:04:14 +02:00
d57b7a31b7
adds more counter keywords
Michael Beck
2023-08-08 00:03:30 +02:00
13d80124d3
adds lines with counterKeywords to remove non-covid tweets
Michael Beck
2023-08-07 23:45:11 +02:00
3de6d8f3ec
adds tweetLen column, converts keywords to lowercase and removes certain keywords
Michael Beck
2023-08-07 23:07:29 +02:00
817ec48478
corrects a lot of mistakes. adds keywords adds analyze.py adds pretest adds pretest ids
Michael Beck
2023-07-07 00:16:44 +02:00
c64904a64d
adds cleanTweets.py
Michael Beck
2023-06-26 23:51:32 +02:00
82830f13e2
„README.md“ ändern
Michael Beck
2023-06-26 13:12:16 +02:00
8c8a191952
„README.md“ hinzufügen
Michael Beck
2023-06-26 13:12:04 +02:00
71e10a62d3
adds senator data scraper
Michael Beck
2023-06-23 23:53:31 +02:00
90d5501ec8
adds comment
Michael Beck
2023-06-23 23:53:01 +02:00
340cca017c
corrects comments
0.1.5
Michael Beck
2023-06-23 20:59:14 +02:00
791cebc297
adds log folder
Michael Beck
2023-06-23 20:49:35 +02:00
6241484e83
adds gitkeep
Michael Beck
2023-06-23 20:47:32 +02:00
d73da8db98
Merge remote-tracking branch 'origin/master'
Michael Beck
2023-06-23 20:42:58 +02:00
6220c1841d
„collect.ipynb“ löschen
Michael Beck
2023-06-23 20:41:56 +02:00
27746cd886
changes folder structure of in- and output files
0.1.2
Michael Beck
2023-06-23 20:39:40 +02:00
02c3d055bd
adds comments. changes logfile format to .log
0.1.1
Michael Beck
2023-06-23 20:34:46 +02:00
dc2e17cc2f
adds docstrings to functions. adds several comments.
Michael Beck
2023-06-23 20:26:16 +02:00
e8ba02ca0f
fixes multiprocessing.
0.1.0
Michael Beck
2023-06-23 19:18:03 +02:00
b00f75e9fe
corrects some mistakes
Michael Beck
2023-06-23 18:09:09 +02:00
1b43b295ce
adds filechecks
Michael Beck
2023-06-23 17:47:23 +02:00
fb7a70cf66
adds missing file report
Michael Beck
2023-06-23 17:04:08 +02:00
1a19fd407a
adds alt_accounts check and removes NANs from alt_accounts. Prints accounts to output more beautifully.
Michael Beck
2023-06-23 16:54:57 +02:00
5d0c41407e
adds multiprocessing to scrape tweets.
Michael Beck
2023-06-23 16:41:20 +02:00
c675db9d00
adds python and lockfiles to gitignore
Michael Beck
2023-06-23 15:59:29 +02:00
88c016a2a6
adds
Michael Beck
2023-06-23 15:57:31 +02:00
599202ae4d
adds checks & logs
Michael Beck
2023-06-23 13:00:23 +02:00
7e8666f094
Merge remote-tracking branch 'origin/master'
Michael Beck
2023-06-21 19:08:14 +02:00
dd9155aec4
adds init for functions folder
Michael Beck
2023-06-21 19:07:32 +02:00
ea7fcc732e
Restructures. adds TimeSlice, ClearDupes and more comments.
Michael Beck
2023-06-21 19:07:07 +02:00
b1d19c4f1f
adds jupyter-notebookfile
Michael Beck
2023-06-08 11:00:49 +02:00
2e70d960a5
adds retry loop mechanism for api limit
Michael Beck
2023-06-07 20:42:47 +02:00
81db25a8b8
comments and reorders
Michael Beck
2023-06-07 20:36:35 +02:00
0bc42fa862
adds try except block for tweepy paginator
Michael Beck
2023-06-07 19:37:01 +02:00
632f504cc4
adds gitignore
Michael Beck
2023-06-07 18:03:46 +02:00
a0c8df6a36
adds collect script, keywords and senators csv
Michael Beck
2023-06-07 18:02:27 +02:00
08ea3b3f7f
initial commit
Michael Beck
2023-06-07 17:58:35 +02:00
Michael Beck