mgaughan/mw-lifecycle-analysis
1
0
Fork 0
Code

updating some scripts

Browse Source
This commit is contained in:
mgaughan 2025-09-14 11:14:16 -05:00
parent f9c12bb445
commit f68372572f
2 changed files with 12 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
p2/quest/python_scripts/090425_batched_olmo_cat.py
View File

@ -71,7 +71,7 @@ with open("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_pp_biberplus_
text_dict['task_title'] = row[1]
text_dict['comment_text'] = row[2]
text_dict['comment_type'] = row[12]
raw_text = text_dict['comment_text']
raw_text = text_dict['task_title']
# comment_text preprocessing per https://arxiv.org/pdf/1902.07093
# 1. replace code with CODE
@ -91,6 +91,7 @@ with open("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_pp_biberplus_
comment_text = re.sub(r'(^|\s)@\w+', 'SCREEN_NAME', comment_text)
# 5. split into an array of sentences
comment_sentences = nltk.sent_tokenize(comment_text)
text_dict['cleaned_sentences'] = comment_sentences
results = []
batch_size = 2
@ -118,7 +119,7 @@ with open("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_pp_biberplus_
array_of_categorizations.append(text_dict)
df = pd.DataFrame(array_of_categorizations)
#print(df.head())
df.to_csv('090425_olmo_batched_categorized.csv', index=False)
df.to_csv('titles_090725_olmo_batched_categorized.csv', index=False)

16
p2/quest/python_scripts/biberplus_labeling.py
View File

@ -77,14 +77,16 @@ if __name__ == "__main__":
#loading in the discussion data from the universal CSV
first_discussion_df = pd.read_csv("/home/nws8519/git/mw-lifecycle-analysis/p2/071425_master_discussion_data.csv")
#formatting for the neurobiber model
docs = first_discussion_df["comment_text"].astype(str).tolist()
#docs = first_discussion_df["comment_text"].astype(str).tolist()
task_description_df = first_discussion_df[first_discussion_df['comment_type'] == "task_description"]
docs = task_description_df['task_title'].astype(str).tolist()
#load model and run
#model, tokenizer = load_model_and_tokenizer()
preds_df = biberplus_labeler(docs)
#new columns in the df for the predicted neurobiber items
#preds_cols = [f"neurobiber_{i+1}" for i in range(96)]
#preds_df = pd.DataFrame(preds, columns=preds_cols, index=first_discussion_df.index)
final_discussion_df = pd.concat([first_discussion_df, preds_df], axis=1)
final_discussion_df = pd.concat([task_description_df, preds_df], axis=1)
#print(type(preds))
#assigning the preditions as a new column
'''
@ -95,18 +97,18 @@ if __name__ == "__main__":
how='inner'
)
'''
print(first_discussion_df)
print(final_discussion_df)
#print(first_discussion_df)
#print(final_discussion_df)
#final_discussion_df["biberplus_preds"] = list(preds)
#assert that order has been preserved
for _ in range(1000):
random_index = random.randrange(len(final_discussion_df))
assert first_discussion_df.iloc[random_index]["id"] == final_discussion_df.iloc[random_index]["id"]
assert task_description_df.iloc[random_index]["id"] == final_discussion_df.iloc[random_index]["id"]
#assert first_discussion_df.loc[random_index, "comment_text"] == final_discussion_df.loc[random_index, "comment_text"]
#assert that there are the same number of rows in first_discussion_df and second_discussion_df
assert len(first_discussion_df) == len(final_discussion_df)
assert len(task_description_df) == len(final_discussion_df)
final_discussion_df = final_discussion_df.drop(columns=["message"])
# if passing the prior asserts, let's write to a csv
final_discussion_df.to_csv("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_biberplus_labels.csv", index=False)
final_discussion_df.to_csv("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/090725_biberplus_title_labels.csv", index=False)
print('biberplus labeling pau')