adds readme

README.md

@@ -1,7 +1,127 @@
-# How to use
+# Requirements
 
-Execute collect.py to scrape tweets and generate the ´ALL-SENATORS-TWEETS.csv´.
+- python 3.10+
+- snscrape 0.6.2.20230321+ (see git repo in this folder)
+- transformers 4.31.0
+- numpy 1.23.5
+- pandas 2.0.3
+- scikit-learn 1.3.0
+- torch 2.0.1
 
-Execute collectSenData.py to scrape senator data and generate ´ALL-SENATORS.csv´.
+# About
 
-All new files will be written to ´data/OUT/´. Necessary data has to be located in ´data/IN/´
+This collection of scripts scrapes tweets of US-senators in the time from 2020-01-01T00:00:00Z to 2023-01-03T00:00:00Z, scrapes account data of the senators, prepares the tweets for the training of a NLP-model, trains two models to (1) classify the tweets topic as covid or non-covid and (2) the tweets as either "fake news" tweets or "non-fake news" tweets.
+Training only works with a prepared dataset in which the tweets are pre classified.
+More info in the comments of the scripts.
+Due to time constraints, most of the code is procedurally coded and ugly but effective.
+
+# How to
+
+Tested on Ubuntu 22.04. 
+If needed, the virual environment can be exported and send to you.
+
+All files in the folder data/in have to exist in order to execute the scripts.
+Execute in the following order:
+
+01 collect.py (see more for further info on scraping)
+02 collectSenData.py
+03 cleanTweets
+04 preTestClassification.py
+05 trainTopic.py
+06 trainFake.py
+07 ClassificationFake.py
+08 ClassificationTopic.py
+
+# Files & Folders
+
+├── data
+│   ├── IN
+│   │   ├── counterKeywordsFinal.txt
+│   │   ├── counterKeywords.txt
+│   │   ├── keywords-raw.txt
+│   │   ├── keywords.txt
+│   │   ├── own_keywords.txt
+│   │   ├── pretest-tweets_fake.txt				contains tweet ids for pretest
+│   │   ├── pretest-tweets_not_fake.txt			contains tweet ids for pretest
+│   │   └── senators-raw.csv					senator datafile
+│   ├── OUT
+│   │   ├── ALL-SENATORS-TWEETS.csv
+│   │   ├── graphs
+│   │   │   ├── Timeline.png
+│   │   │   ├── Wordcloud-All.png
+│   │   │   └── Wordcloud-Cov.png
+│   │   ├── Pretest-Prep.csv
+│   │   ├── Pretest-Results.csv
+│   │   ├── Pretest-SENATORS-TWEETS.csv
+│   │   ├── profiles							dataset profiles
+│   │   │   ├── AllTweets.html
+│   │   │   └── CovTweets.html
+│   │   ├── SenatorsTweets-Final.csv
+│   │   ├── SenatorsTweets-OnlyCov.csv
+│   │   ├── SenatorsTweets-train-CovClassification.csv
+│   │   ├── SenatorsTweets-train-CovClassificationTRAIN.csv
+│   │   ├── SenatorsTweets-train-CovClassification.tsv
+│   │   ├── SenatorsTweets-train-FakeClassification.csv
+│   │   ├── SenatorsTweets-train-FakeClassificationTRAIN.csv
+│   │   ├── SenatorsTweets-train-FakeClassification.tsv
+│   │   ├── SenatorsTweets-Training.csv
+│   │   ├── SenatorsTweets-Training_WORKING-COPY.csv
+│   │   ├── topClass-PRETEST-Prep.csv
+│   │   ├── topClass-PRETEST-Results.csv
+│   │   ├── Tweets-All-slices.zip
+│   │   ├── Tweets-Classified-Fake-Prep.csv
+│   │   ├── Tweets-Classified-Fake-Results.csv
+│   │   ├── Tweets-Classified-Prep.csv
+│   │   ├── Tweets-Classified-Topic-Prep.csv
+│   │   ├── Tweets-Classified-Topic-Results.csv
+│   │   └── Tweets-Stub.csv
+├── funs
+│   ├── CleanTweets.py					2023-01-03T00:00:00Z		multiple functions to clean tweet contents for NLN-processing
+│   ├── ClearDupes.py							function for deletion of duplicate keywords
+│   ├── __init__.py
+│   ├── Scrape.py								scraper functions to be used for multiprocessing
+│   └── TimeSlice.py							time slice script to slice the time span in 24 slices, speeds up scraping through multiprocessing
+├── log											logs of the scraping process
+│   ├── log_2023-06-23_21-06-10_err.log
+│   ├── log_2023-06-23_21-06-10.log
+│   └── log_2023-06-23_21-06-10_missing.log
+├── models
+│   ├── CovClass								Covid tweet classification model
+│   │   └── 2023-08-15_05-56-50
+│   │       ├── 2023-08-15_05-56-50.csv			training output
+│   │       ├── config.json
+│   │       ├── pytorch_model.bin
+│   │       ├── special_tokens_map.json
+│   │       ├── tokenizer_config.json
+│   │       ├── tokenizer.json
+│   │       └── vocab.txt
+│   └── FakeClass								Fake tweet classification model
+│       └── 2023-08-15_14-35-43
+│           ├── 2023-08-15_14-35-43.csv			training output
+│           ├── config.json
+│           ├── pytorch_model.bin
+│           ├── special_tokens_map.json
+│           ├── tokenizer_config.json
+│           ├── tokenizer.json
+│           └── vocab.txt
+├── snscrape									contains snscrape 0.6.2.20230321+ git repo
+├── ClassificationFake.py						classifies tweets as fake or non-fake, saves:
+│													Tweets-Classified-Fake-Prep.csv		- prepared training dataset
+│													Tweets-Classified-Fake-Results.csv	- Tweets-Classified-Topic-Results.csv with cov classification results
+├── ClassificationTopic.py						classifies tweet topic, saves: 
+│													Tweets-Classified-Topic-Prep.csv 	- prepared training dataset
+│													Tweets-Classified-Topic-Results.csv	- SenatorsTweets-OnlyCov.csv with cov classification results
+├── cleanTweets.py								Curates keywordlists 
+│												Merges senator and tweet datasets
+│												Creates multiple datasets:
+│													SenatorsTweets-Final.csv	- all tweets with keyword columns
+│													SenatorsTweets-OnlyCov.csv	- only covid tweets, filtered by keywordlist
+│													SenatorsTweets-Training.csv	- training dataset, containing ~1800 randomly selected tweets from SenatorsTweets-OnlyCov.csv
+├── collect.py									scrapes tweets, saves to ALL-SENATORS-TWEETS.csv
+├── collectSenData.py							scrapes senator account data, saves to ALL-SENATORS.csv
+├── createGraphs.py								creates wordcloud & timeline graphs
+├── preTestClassification.py					pretest script that uses bvrau/covid-twitter-bert-v2-struth to analyze 100 preclassified tweets
+├── profiler.py									creates dataset profiles
+├── README.md									readme
+├── trainFake.py								training script for the fake tweet classification model
+└── trainTopic.py								training script for the tweet topic classification model

cleanTweets.py

@@ -9,7 +9,8 @@ Created on Mon Jun 26 20:36:43 2023
 import pandas as pd
 # import pyreadstat
 import numpy as np
-from funs.ClearDupes import deDupe
+import sys
+
 
 # Seet for training dataset generation
 seed = 86431891
@@ -49,6 +50,11 @@ senDatasetPath = wd + di + senDataset
 
 df = pd.read_csv(senCSVPath, dtype=(object))
 
+## Import own functions
+funs = wd+"funs"
+sys.path.insert(1, funs)
+from ClearDupes import deDupe
+
 mixed_columns = df.columns[df.nunique() != len(df)]
 print(mixed_columns)
 

collect.py

@@ -66,7 +66,6 @@ which is the final output.
 import os
 import pandas as pd
 import glob
-import time
 import sys
 from datetime import datetime
 import concurrent.futures
@@ -149,10 +148,12 @@ tweetDFColumns = [
 ################## do NOT change anything below this line ###################
 #############################################################################
 
-## Import functions
-from funs.TimeSlice import *
-from funs.ClearDupes import deDupe
-from funs.Scrape import scrapeTweets
+## Import own functions
+funs = wd+"funs"
+sys.path.insert(1, funs)
+from TimeSlice import get_Tslices
+from ClearDupes import deDupe
+from Scrape import scrapeTweets
 
 ################### 
 # Create logfile & log all outputs

preTestClassification.py

@@ -1,13 +1,8 @@
-import re
-import string
-import numpy as np
 import pandas as pd
 from datetime import datetime
 from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
 from datasets import load_dataset
 from transformers.pipelines.pt_utils import KeyDataset
-from funs.CleanTweets import remove_URL, remove_emoji, remove_html, remove_punct
-
 
 #%%
 # prepare
@@ -40,7 +35,6 @@ senCSVPretest = "Pretest.csv"
 senCSVPretestPrep = "Pretest-Prep.csv"
 senCSVPretestResult = "Pretest-Results.csv"
 
-
 # don't change this one
 senCSVPath = wd + ud + senCSV
 senCSVcPath = wd + ud + senCSVc
@@ -50,6 +44,11 @@ senCSVcPretestResultPath = wd + ud + senCSVPretestResult
 preTestIDsFakePath = wd + di + preTestIDsFake
 preTestIDsNotPath = wd + di + preTestIDsNot
 
+import sys
+funs = wd+"funs"
+sys.path.insert(1, funs)
+import CleanTweets
+
 # List of IDs to select
 # Read the IDs from a file
 preTestIDsFakeL = []
@@ -85,11 +84,7 @@ tokenizer = AutoTokenizer.from_pretrained("bvrau/covid-twitter-bert-v2-struth")
 
 # Source https://www.kaggle.com/code/daotan/tweet-analysis-with-transformers-bert
 
-dfPreTest['cleanContent'] = dfPreTest['rawContent'].apply(remove_URL)
-dfPreTest['cleanContent'] = dfPreTest['cleanContent'].apply(remove_emoji)
-dfPreTest['cleanContent'] = dfPreTest['cleanContent'].apply(remove_html)
-dfPreTest['cleanContent'] = dfPreTest['cleanContent'].apply(remove_punct)
-dfPreTest['cleanContent'] = dfPreTest['cleanContent'].apply(lambda x: x.lower())
+dfPreTest['cleanContent'] = dfPreTest['rawContent'].apply(CleanTweets.preprocess_text)
 
 #%%
 timeStart = datetime.now() # start counting execution time