From 4e08cde317a7b79f81efb09f44a9d2d2bbf6e51a Mon Sep 17 00:00:00 2001
From: Michael Beck <ich@mischbeck.de>
Date: Wed, 16 Aug 2023 10:06:16 +0200
Subject: [PATCH] finishes classification scripts

---
 ClassificationFake.py  | 10 ++++++++++
 ClassificationTopic.py | 11 +++++++++++
 2 files changed, 21 insertions(+)

diff --git a/ClassificationFake.py b/ClassificationFake.py
index b48aa9e..dd0cda7 100644
--- a/ClassificationFake.py
+++ b/ClassificationFake.py
@@ -43,6 +43,16 @@ import CleanTweets
 #%%
 # get datafra,e
 dfClassify = pd.read_csv(senCSVPath, dtype=(object))
+def encode_labels(label):
+    if label == 'True':
+        return 'False'
+    elif label == 'False':
+        return 'True'
+    return 0
+dfClassify['output_label_topicCov'] = dfClassify['output_label_topicCov'].apply(encode_labels)
+dfClassify.to_csv("/home/michael/Documents/PS/Data/collectTweets/data/OUT/Tweets-Classified-Topic-Results.csv", encoding='utf-8')
+
+dfClassify = dfClassify[dfClassify['output_label_topicCov']=='True'] 
 
 # dataframe from csv
 dfClassify['fake'] = False
diff --git a/ClassificationTopic.py b/ClassificationTopic.py
index 4605834..b00a94f 100644
--- a/ClassificationTopic.py
+++ b/ClassificationTopic.py
@@ -110,3 +110,14 @@ print(f"Time per tweet classification: {timePerTweet}")
 dfClassify.to_csv(senCSVcClassificationResultPath, encoding='utf-8')
 
 # %%
+## corrections
+def encode_labels(label):
+    if label == 'real':
+        return 'True'
+    elif label == 'fake':
+        return 'False'
+    return 0
+dfClassify['output_label_topicCov'] = dfClassify['output_label_topicCov'].apply(encode_labels)
+dfClassify.to_csv(senCSVcClassificationResultPath, encoding='utf-8')
+#still wrong, will be corrected in ClassificationFake.py
+