Compare commits

..

No commits in common. "885f51b83d45477309d60905bb00408964d647e2" and "ef4fd624e4d018c47dcfb1f249ea8fcbf3190169" have entirely different histories.

2 changed files with 4 additions and 11 deletions

4
.gitignore vendored
View File

@ -3,8 +3,8 @@
.idea/* .idea/*
data/ data/
*.zip .zip
*.db .db
plots/ plots/
results/ results/

View File

@ -74,12 +74,5 @@ class ArticleAnalyzer:
def classify_article_finbert(self, article_html): def classify_article_finbert(self, article_html):
article_md = self.convert_to_markdown(article_html) article_md = self.convert_to_markdown(article_html)
chunk_size = 512 result = self.classifier(article_md)
chunks = [article_md[i:i + chunk_size] for i in range(0, len(article_md), chunk_size)] return result
results = []
for chunk in chunks:
result = self.classifier(chunk)
results.append(result)
return results