Update app.py

app.py

@@ -1,4 +1,3 @@
-# app.py
 import streamlit as st
 import pandas as pd
 import numpy as np
@@ -13,7 +12,7 @@ import tempfile
 import base64
 import io
 
-# Custom Groq Model Class for smolagents integration
+# Custom Groq Model Class remains unchanged
 class GroqModel:
     def __init__(self, model_name="llama2-70b-4096"):
         self.client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
@@ -30,15 +29,14 @@ class GroqModel:
         )
         return response.choices[0].message.content
 
-# Analysis Tools
 @tool
-def analyze_basic_stats(data: pd.DataFrame) -> Dict:
+def analyze_basic_stats(data: pd.DataFrame) -> str:
     """Calculate basic statistics for numerical columns.
     
     Args:
         data: Input DataFrame
     Returns:
-        Dictionary containing basic statistics
+        String containing formatted basic statistics
     """
     stats = {}
     numeric_cols = data.select_dtypes(include=[np.number]).columns
@@ -52,7 +50,7 @@ def analyze_basic_stats(data: pd.DataFrame) -> Dict:
             'missing': data[col].isnull().sum()
         }
     
-    return stats
+    return str(stats)
 
 @tool
 def generate_correlation_matrix(data: pd.DataFrame) -> str:
@@ -75,13 +73,13 @@ def generate_correlation_matrix(data: pd.DataFrame) -> str:
     return base64.b64encode(buf.getvalue()).decode()
 
 @tool
-def analyze_categorical_columns(data: pd.DataFrame) -> Dict:
+def analyze_categorical_columns(data: pd.DataFrame) -> str:
     """Analyze categorical columns in the dataset.
     
     Args:
         data: Input DataFrame
     Returns:
-        Dictionary containing categorical analysis
+        String containing formatted categorical analysis
     """
     categorical_cols = data.select_dtypes(include=['object', 'category']).columns
     analysis = {}
@@ -93,16 +91,16 @@ def analyze_categorical_columns(data: pd.DataFrame) -> Dict:
             'missing': data[col].isnull().sum()
         }
     
-    return analysis
+    return str(analysis)
 
 @tool
-def suggest_features(data: pd.DataFrame) -> List[str]:
+def suggest_features(data: pd.DataFrame) -> str:
     """Suggest potential feature engineering steps.
     
     Args:
         data: Input DataFrame
     Returns:
-        List of feature engineering suggestions
+        String containing feature engineering suggestions
     """
     suggestions = []
     numeric_cols = data.select_dtypes(include=[np.number]).columns
@@ -118,7 +116,7 @@ def suggest_features(data: pd.DataFrame) -> List[str]:
         if data[col].skew() > 1 or data[col].skew() < -1:
             suggestions.append(f"Consider log transformation for {col} due to skewness")
     
-    return suggestions
+    return '\n'.join(suggestions)
 
 # Streamlit App
 def main():