adds final counter keywords

data/IN/counterKeywordsFinal.txt

@@ -0,0 +1,23 @@
+meth
+gun violence
+flu season
+vaping
+chd
+addiction
+indigenous women
+separating children
+tobacco
+e-cigarette
+muslim ban
+soleimani
+cocaine
+separating families
+muslim travel ban
+usmca trade deal
+shooting
+overdose
+separated children
+coronary heart disease
+gun-violence
+opioid
+flu-season

models/CovClass/2023-08-15_01-55-11/statsTopicClassification-2023-08-15_01-53-12.csv

@@ -0,0 +1,7 @@
+epoch,Training Loss,Valid. Loss,Valid. Accur.,Training Time,Validation Time
+1,0.39025546515679493,0.40877932761593355,0.9103260869565217,0:10:21,0:00:40
+2,0.3057803610952067,0.3502063500978377,0.9103260869565217,0:10:53,0:00:43
+3,0.17910970049364833,0.27903796154904464,0.9375,0:10:30,0:00:38
+4,0.09279396105943587,0.41342766528301267,0.904891304347826,0:11:03,0:00:43
+5,0.06132459050129317,0.4468563502887264,0.9239130434782609,0:12:07,0:00:44
+6,0.04195396880810895,0.4350045176675928,0.9266304347826086,0:11:21,0:00:40

repairmystupidity.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Aug 14 20:47:22 2023
+
+@author: michael
+"""
+import pandas as pd
+
+wd = "/home/michael/Documents/PS/Data/collectTweets/"
+
+# datafile input directory
+di = "data/IN/"
+
+# Tweet-datafile output directory
+ud = "data/OUT/"
+
+falsch = wd + ud + "SenatorsTweets-Training_WORKING-COPY-correct.csv"
+richtig = wd + ud + "SenatorsTweets-Training.csv"
+correct = wd + ud + "SenatorsTweets-Training_WORKING-COPY-correct2.csv"
+
+# Name of new datafile generated
+senCSVprep = "SenatorsTweets-Training_WORKING-COPY-prepared"
+
+# don't change this one
+falsch = pd.read_csv(falsch, dtype=(object), sep=";")
+richtig = pd.read_csv(richtig, dtype=(object))
+
+df = pd.merge(falsch,richtig[['tid','rawContent', 'date']],on='tid', how='left')
+df.drop(columns=['rawContent_x', 'date_x'], inplace=True)
+df.rename(columns={'tid_y':'tid', 'rawContent_y':'rawContent', 'date_y':'date'}, inplace=True)
+df = df[['tid','date','topicCovid','fake','rawContent','Unnamed: 6']]
+df.rename(columns={'Unnamed: 6':'comment'}, inplace=True)
+
+df.to_csv(correct, encoding='utf-8', sep=";")