Update app.py

app.py

@@ -96,12 +96,10 @@ def generate_synthetic_data(description, columns):
     return response_data[0]["generated_text"]
 
 def extract_valid_csv(csv_data, expected_columns):
-    # Attempt to extract valid CSV data from the response
     lines = csv_data.split('\n')
     valid_lines = []
-    
-    # Find the start of the valid CSV data by looking for the column headers
     header_found = False
+    
     for line in lines:
         if header_found:
             if line.strip() == '':
@@ -111,7 +109,6 @@ def extract_valid_csv(csv_data, expected_columns):
             header_found = True
             valid_lines.append(line)
     
-    # Combine valid lines into a single string
     valid_csv_data = '\n'.join(valid_lines)
     return valid_csv_data
 
@@ -120,30 +117,29 @@ def process_generated_data(csv_data, expected_columns):
         valid_csv_data = extract_valid_csv(csv_data, expected_columns)
         data = StringIO(valid_csv_data)
         
-        # Read the CSV data
         df = pd.read_csv(data, delimiter=',')
         
-        # Check if the DataFrame has the expected columns
         if set(df.columns) != set(expected_columns):
             return f"Unexpected columns in the generated data: {df.columns}"
         
         return df
     except pd.errors.ParserError as e:
+        logging.error(f"Failed to parse CSV data: {e}")
         return f"Failed to parse CSV data: {e}"
 
 def generate_large_synthetic_data(description, columns, num_rows=1000, rows_per_generation=100):
     csv_data_all = ""
     
-    for _ in tqdm(range(num_rows // rows_per_generation), desc="Generating Data"):
+    for _ in range(num_rows // rows_per_generation):
         generated_data = generate_synthetic_data(description, columns)
         if "Error" in generated_data:
-            return generated_data  # Return the error message
+            return generated_data
 
         df_synthetic = process_generated_data(generated_data, columns)
         if isinstance(df_synthetic, pd.DataFrame) and not df_synthetic.empty:
             csv_data_all += df_synthetic.to_csv(index=False, header=False)
         else:
-            print("Skipping invalid generation.")
+            logging.info("Skipping invalid generation.")
 
     if csv_data_all:
         return csv_data_all
@@ -159,7 +155,6 @@ def generate_data(request: DataGenerationRequest):
     if isinstance(generated_data, str) and "Error" in generated_data:
         return JSONResponse(content={"error": generated_data}, status_code=500)
     
-    # Create a streaming response to return the CSV data
     csv_buffer = StringIO(generated_data)
     return StreamingResponse(
         csv_buffer,