Update app.py

app.py

@@ -13,46 +13,47 @@ from google import genai
 api_key = os.environ.get('GEMINI_API_KEY')
 client = genai.Client(api_key=api_key)
 
-# 2. Define the core data, plotting, and machine learning logic
+# 2. Define the core data and plotting logic
 def analyze_and_plot(uploaded_file, user_question):
     if uploaded_file is None:
-        return "⚠️ Please upload a CSV file first.", None, gr.update(visible=False), gr.update(visible=False)
+        # Return error message, hide chart, disable download button
+        return "⚠️ Please upload a CSV file first.", None, gr.update(visible=False)
         
     try:
-        # Clear previous session files
+        # Clear any previous figures and delete old reports to keep clean states
         plt.close('all')
-        for f in ["analysis_report.txt", "output_chart.png", "cleaned_dataset.csv"]:
-            if os.path.exists(f):
-                os.remove(f)
+        if os.path.exists("analysis_report.txt"):
+            os.remove("analysis_report.txt")
+        if os.path.exists("output_chart.png"):
+            os.remove("output_chart.png")
         
         # Read the uploaded CSV file using Pandas
         df = pd.read_csv(uploaded_file.name)
         
-        # Gather basic details about the dataset
+        # Gather basic details about the dataset to feed the AI context
         row_count = len(df)
         col_count = len(df.columns)
         column_names = ", ".join(df.columns.tolist())
         data_preview = df.head(3).to_string()
         data_types = df.dtypes.to_string()
-        missing_values = df.isnull().sum().to_string()
         
-        # Comprehensive system instructions enabling advanced Machine Learning tasks
+        # System instructions forcing Gemini to return structured code and metrics
         system_context = (
-            f"You are an expert Python Data Scientist and Machine Learning Engineer. The user has uploaded a dataset.\n"
+            f"You are an expert Python Data Analyst. The user has uploaded a dataset.\n"
             f"Dataset Statistics:\n"
             f"- Total Rows: {row_count}\n"
             f"- Total Columns: {col_count}\n"
             f"- Column Names: {column_names}\n\n"
             f"Data Types:\n{data_types}\n\n"
-            f"Missing Values per column:\n{missing_values}\n\n"
             f"Preview:\n{data_preview}\n\n"
             f"INSTRUCTIONS:\n"
             f"1. Answer the user's question clearly.\n"
-            f"2. You are fully capable of implementing: Linear/Logistic Regression, Random Forests, Decision Trees, K-Means Clustering, and SVMs using 'sklearn'.\n"
-            f"3. CRUCIAL FOR ML: If a model target or feature contains non-numeric text, write code using sklearn's 'LabelEncoder' or pandas 'get_dummies' to encode it to numeric values before fitting the model. Always drop or impute missing values inside the code block before training.\n"
-            f"4. For classification/regression models, explicitly output evaluation metrics (Accuracy, F1-Score, Mean Squared Error, R-squared, etc.) via Python 'print()' or text response.\n"
-            f"5. If a chart is requested (like a Decision Tree visual boundary, Feature Importance bar chart, K-Means scatter plot clusters, or Confusion Matrix), generate Python code using 'matplotlib.pyplot'. The LAST line must be: plt.savefig('output_chart.png')\n"
-            f"6. Do not include plt.show(). Only save outputs to files."
+            f"2. If performing a regression or statistical test, you MUST explicitly state the key numerical metrics "
+            f"(such as R-squared value, Slope/Coefficients, Intercept, or p-values) in your final written text response.\n"
+            f"3. If a chart is requested, include a clean Python code block using 'matplotlib.pyplot' and 'sklearn'. "
+            f"Assume the dataframe is loaded as 'df'.\n"
+            f"4. Crucial: The LAST line of your chart code block must save the image exactly as: plt.savefig('output_chart.png')\n"
+            f"5. Do not include plt.show(). Only save it to 'output_chart.png'."
         )
         
         # Send the metadata context and user query to Gemini
@@ -64,90 +65,74 @@ def analyze_and_plot(uploaded_file, user_question):
         text_response = response.text
         chart_path = None
         
-        # Extract and execute the python code block generated by Gemini
+        # Extract and execute the python code if Gemini generated a graph script
         if "```python" in text_response:
             try:
-                code_block = text_response.split("```python").split("```")
+                # Isolate the code inside the markdown blocks
+                code_block = text_response.split("```python")[1].split("```")[0]
                 
-                # Setup string buffer to trap code outputs (e.g. classification reports)
+                # Setup a string buffer to catch anything the executed script tries to print out
                 old_stdout = sys.stdout
                 redirected_output = sys.stdout = io.StringIO()
                 
-                # Create execution environment
+                # Create a safe execution environment containing the user's data
                 local_vars = {'df': df, 'plt': plt}
                 exec(code_block, {}, local_vars)
                 
+                # Restore normal system output
                 sys.stdout = old_stdout
                 printed_results = redirected_output.getvalue()
                 
+                # If the script printed extra statistical text, add it to the final display
                 if printed_results:
-                    text_response += f"\n\n### 🖥️ Machine Learning Execution Output:\n```text\n{printed_results}\n```"
+                    text_response += f"\n\n### 🖥️ Calculated Execution Output:\n```text\n{printed_results}\n```"
                 
-                # Check for rendered chart image
+                # Check if the chart image file was successfully written
                 if os.path.exists("output_chart.png"):
                     chart_path = "output_chart.png"
-                    
             except Exception as e:
-                # Restore output settings if it crashes during script execution
-                sys.stdout = old_stdout
-                text_response += f"\n\n*(Note: ML execution script error: {str(e)})*"
+                text_response += f"\n\n*(Note: There was a background error rendering the chart: {str(e)})*"
         
-        # Save the text report
+        # Save the finalized text analysis into a downloadable file on the server
         with open("analysis_report.txt", "w", encoding="utf-8") as f:
             f.write(text_response)
             
-        # Check if a newly cleaned dataset CSV file was generated
-        csv_update = gr.update(visible=False)
-        if os.path.exists("cleaned_dataset.csv"):
-            csv_update = gr.update(value="cleaned_dataset.csv", visible=True)
-            text_response += "\n\n✅ **Success:** A processed dataset file has been generated. Use the download button below to grab it!"
-            
-        return text_response, chart_path, gr.update(value="analysis_report.txt", visible=True), csv_update
+        # Return text, chart path, and make the download button visible with the report file attached
+        return text_response, chart_path, gr.update(value="analysis_report.txt", visible=True)
         
     except Exception as e:
-        return f"❌ An error occurred processing the file: {str(e)}", None, gr.update(visible=False), gr.update(visible=False)
+        return f"❌ An error occurred processing the file: {str(e)}", None, gr.update(visible=False)
 
-# 3. Design the expanded Machine Learning layout using Gradio Blocks
+# 3. Design the custom layout using Gradio Blocks
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🤖 Cloud Machine Learning & Data Workspace")
-    gr.Markdown("Upload a CSV file to automatically clean your data, train advanced Machine Learning models, and visually analyze results.")
+    gr.Markdown("# 📊 Visual Cloud AI Data Analyst")
+    gr.Markdown("Upload a CSV file, ask a question, and download your final text reports easily.")
     
     with gr.Row():
         with gr.Column(scale=1):
             file_input = gr.File(label="Step 1: Upload CSV Dataset", file_types=[".csv"])
             question_input = gr.Textbox(
-                label="Step 2: Define your Machine Learning or Data workflow", 
-                placeholder="e.g., 'Train a Random Forest classifier to predict...' or 'Cluster my data into 3 groups'..."
-            )
-            submit_btn = gr.Button("Execute ML Pipeline", variant="primary")
-            
-            # Clickable Example Prompts Section covering brand new models
-            gr.Examples(
-                examples=[
-                    ["Train a Random Forest model to predict [Target Column] using all other columns. Print out the model accuracy and display a feature importance bar chart."],
-                    ["Run a K-Means clustering algorithm on [Column X] and [Column Y] to group the data into 3 clusters. Plot the clusters in different colors with their centroids."],
-                    ["Build a Decision Tree classifier to predict [Target Column]. Print the classification report and plot a visual graph of the top nodes of the tree."],
-                    ["Train a Support Vector Machine (SVM) to classify [Target Column] using [Feature 1] and [Feature 2]. Show model metrics."]
-                ],
-                inputs=question_input,
-                label="💡 Advanced Machine Learning Templates"
+                label="Step 2: Ask a question or request a model", 
+                placeholder="e.g., 'Run a linear regression between ColumnA and ColumnB'..."
             )
+            submit_btn = gr.Button("Analyze & Generate Chart", variant="primary")
             
         with gr.Column(scale=1):
-            output_text = gr.Markdown(label="AI Analysis & Model Metrics")
+            output_text = gr.Markdown(label="AI Written Insights")
             
-            with gr.Row():
-                download_report_btn = gr.DownloadButton("📥 Download Model Report", visible=False)
-                download_csv_btn = gr.DownloadButton("💾 Download Processed CSV", visible=False, variant="secondary")
-                
-            output_image = gr.Image(label="Model Visualization Chart", type="filepath")
+            # The download button is hidden until an analysis runs successfully
+            download_btn = gr.DownloadButton("📥 Download Text Report", visible=False)
+            
+            output_image = gr.Image(label="Generated Data Visualization", type="filepath")
             
-    # Connect inputs to execution function and distribute interface updates
+    # Connect inputs to the execution function and distribute the 3 outputs
     submit_btn.click(
         fn=analyze_and_plot, 
         inputs=[file_input, question_input], 
-        outputs=[output_text, output_image, download_report_btn, download_csv_btn]
+        outputs=[output_text, output_image, download_btn]
     )
 
+# 4. Launch the public cloud server
 if __name__ == "__main__":
     demo.launch()
+