Update app.py

app.py

@@ -7,8 +7,6 @@ from itertools import combinations
 import re
 from functools import cache
 from io import StringIO  # Corrected import for StringIO
-
-
 # Define function to cache model info from Hugging Face API
 @cache
 def cached_model_info(api, model):
@@ -20,12 +18,13 @@ def cached_model_info(api, model):
 # Convert markdown table to DataFrame and extract Hugging Face URLs
 def convert_markdown_table_to_dataframe(md_content):
     cleaned_content = re.sub(r'\|\s*$', '', re.sub(r'^\|\s*', '', md_content, flags=re.MULTILINE), flags=re.MULTILINE)
-    df = pd.read_csv(StringIO(cleaned_content), sep="\|", engine='python')  # Corrected use of StringIO
-    df = df.drop(0).reset_index(drop=True)
+    # Use StringIO for reading the cleaned_content
+    df = pd.read_csv(StringIO(cleaned_content), sep="\|", engine='python', skipinitialspace=True)
+    # Skip rows if needed or directly process without dropping
     df.columns = df.columns.str.strip()
     model_link_pattern = r'\[(.*?)\]\((.*?)\)\s*\[.*?\]\(.*?\)'
-    df['URL'] = df['Model'].apply(lambda x: re.search(model_link_pattern, x).group(2) if re.search(model_link_pattern, x) else None)
-    df['Model'] = df['Model'].apply(lambda x: re.sub(model_link_pattern, r'\1', x))
+    df['URL'] = df.apply(lambda x: re.search(model_link_pattern, x['Model']).group(2) if re.search(model_link_pattern, x['Model']) else None, axis=1)
+    df['Model'] = df.apply(lambda x: re.sub(model_link_pattern, r'\1', x['Model']), axis=1)
     return df
 
 # Function to get and update model info in the DataFrame
@@ -95,8 +94,8 @@ def main():
     st.title("Model Leaderboard")
     st.markdown("Displaying top combinations of models based on scores.")
 
-    # Placeholder for content fetching or upload
-    content = """Your markdown table content here"""  # Placeholder content
+    # Placeholder content - ensure you replace this with your actual markdown or method to fetch/create content
+    content = """Your markdown table content here"""
 
     if content:
         df = convert_markdown_table_to_dataframe(content)
@@ -105,12 +104,12 @@ def main():
         # Assuming your DataFrame has these score columns already or you've added them
         score_columns = ['Average', 'AGIEval', 'GPT4All', 'TruthfulQA', 'Bigbench']
         
-        # Make sure the score columns are numeric and handle NaNs or conversion issues
+        # Ensure the score columns are numeric and handle NaNs or conversion issues
         for col in score_columns:
             df[col] = pd.to_numeric(df[col], errors='coerce')
 
         display_highest_combined_scores(df, score_columns)
-    
+
     # Create tabs for leaderboard and about section
     content = create_yall()
     tab1, tab2 = st.tabs(["🏆 Leaderboard", "📝 About"])