mischbeck/CollectUSSenatorTweets
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

finishes classification scripts

Browse Source
This commit is contained in:
Michael Beck 2023-08-16 10:06:16 +02:00
parent 2535683cdc
commit 4e08cde317
2 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
ClassificationFake.py
View File

@ -43,6 +43,16 @@ import CleanTweets
#%% #%%
# get datafra,e # get datafra,e
dfClassify = pd.read_csv(senCSVPath, dtype=(object)) 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 # dataframe from csv
dfClassify['fake'] = False dfClassify['fake'] = False

11
ClassificationTopic.py
View File

@ -110,3 +110,14 @@ print(f"Time per tweet classification: {timePerTweet}")
dfClassify.to_csv(senCSVcClassificationResultPath, encoding='utf-8') 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