Update app.py

app.py

@@ -56,22 +56,29 @@ def process_file(file, instructions, api_key):
         for plot in plots[:3]:  # Ensure max 3 plots
             fig, ax = plt.subplots(figsize=(10, 6))
             
-            # Apply preprocessing if any
-            if plot['preprocessing']:
-                exec(plot['preprocessing'])
+            # Apply preprocessing
+            plot_df = df.copy()
+            if 'Group data by' in plot['preprocessing']:
+                group_by = plot['x']
+                agg_column = plot['y'][0] if isinstance(plot['y'], list) else plot['y']
+                plot_df = plot_df.groupby(group_by)[agg_column].sum().reset_index()
+            if 'Sort' in plot['preprocessing']:
+                plot_df = plot_df.sort_values(by=plot['y'][0] if isinstance(plot['y'], list) else plot['y'], ascending=False)
+            if 'Filter to keep only the top 5' in plot['preprocessing']:
+                plot_df = plot_df.head(5)
             
             if plot['plot_type'] == 'bar':
-                df.plot(kind='bar', x=plot['x'], y=plot['y'], ax=ax)
+                plot_df.plot(kind='bar', x=plot['x'], y=plot['y'], ax=ax)
             elif plot['plot_type'] == 'line':
-                df.plot(kind='line', x=plot['x'], y=plot['y'], ax=ax)
+                plot_df.plot(kind='line', x=plot['x'], y=plot['y'], ax=ax)
             elif plot['plot_type'] == 'scatter':
-                df.plot(kind='scatter', x=plot['x'], y=plot['y'], ax=ax)
+                plot_df.plot(kind='scatter', x=plot['x'], y=plot['y'], ax=ax)
             elif plot['plot_type'] == 'hist':
-                df[plot['x']].hist(ax=ax)
+                plot_df[plot['x']].hist(ax=ax)
             
             ax.set_title(plot['title'])
             ax.set_xlabel(plot['x'])
-            ax.set_ylabel(plot['y'] if plot['y'] else 'Frequency')
+            ax.set_ylabel(plot['y'][0] if isinstance(plot['y'], list) else plot['y'])
             plt.tight_layout()
             
             buf = io.BytesIO()
@@ -91,23 +98,4 @@ def process_file(file, instructions, api_key):
         draw.text((10, 10), error_message, fill=(255, 0, 0))
         return [error_image] * 3
 
-with gr.Blocks(theme=gr.themes.Default()) as demo:
-    gr.Markdown("# Data Analysis Dashboard")
-    
-    with gr.Row():
-        file = gr.File(label="Upload Dataset", file_types=[".csv", ".xlsx"])
-        instructions = gr.Textbox(label="Analysis Instructions", placeholder="Describe the analysis you want...")
-    
-    api_key = gr.Textbox(label="Gemini API Key", type="password")
-    submit = gr.Button("Generate Insights", variant="primary")
-    
-    output_images = [gr.Image(label=f"Visualization {i+1}") for i in range(3)]
-
-    submit.click(
-        process_file,
-        inputs=[file, instructions, api_key],
-        outputs=output_images
-    )
-
-if __name__ == "__main__":
-    demo.launch()
+# The rest of your code remains unchanged