chunked content to 512
This commit is contained in:
parent
3864d7e93c
commit
679f1bd941
@ -44,33 +44,41 @@ if __name__ == "__main__":
|
||||
|
||||
Base.metadata.create_all(engine)
|
||||
|
||||
result = analyzer.classify_article_finbert("Strong earning growth and expending market shares have positionned the company for long term success.")
|
||||
print(f'result {result}')
|
||||
# result = analyzer.classify_article_finbert("Strong earning growth and expending market shares have positionned the company for long term success.")
|
||||
# print(f'result {result}')
|
||||
|
||||
for file, content in html_files.items():
|
||||
chunk_size = 512
|
||||
chunks = [content[i:i+chunk_size] for i in range(0, len(content), chunk_size)]
|
||||
|
||||
# for file, content in html_files.items():
|
||||
# result = analyzer.classify_article_finbert(content)
|
||||
results = []
|
||||
for chunk in chunks:
|
||||
if chunk.strip():
|
||||
chunk_result = analyzer.classify_article_finbert(chunk)
|
||||
results.extend(chunk_result)
|
||||
|
||||
# filename = os.path.basename(file)
|
||||
# print(f'result {result}')
|
||||
result = results if results else [{'label': 'neutral', 'score': 0.0}]
|
||||
|
||||
# label = result[0]['label']
|
||||
# score = result[0]['score']
|
||||
filename = os.path.basename(file)
|
||||
print(f'result {result}')
|
||||
|
||||
# analysis = ArticleAnalysis(filename=filename, label=label, score=score)
|
||||
# label = result[0]['label']
|
||||
# score = result[0]['score']
|
||||
|
||||
# try:
|
||||
# session.add(analysis)
|
||||
# session.commit()
|
||||
# except:
|
||||
# session.rollback()
|
||||
# analysis = ArticleAnalysis(filename=filename, label=label, score=score)
|
||||
|
||||
# existing = session.query(ArticleAnalysis).filter_by(filename=filename).first()
|
||||
# if existing:
|
||||
# existing.label = label
|
||||
# existing.score = score
|
||||
# session.commit()
|
||||
# finally:
|
||||
# session.close()
|
||||
# try:
|
||||
# session.add(analysis)
|
||||
# session.commit()
|
||||
# except:
|
||||
# session.rollback()
|
||||
|
||||
# print(f"article [{file}] - analyzed as [{result}]\n")
|
||||
# existing = session.query(ArticleAnalysis).filter_by(filename=filename).first()
|
||||
# if existing:
|
||||
# existing.label = label
|
||||
# existing.score = score
|
||||
# session.commit()
|
||||
# finally:
|
||||
# session.close()
|
||||
|
||||
# print(f"article [{file}] - analyzed as [{result}]\n")
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user