Update app.py

app.py

@@ -7,38 +7,26 @@ import wandb
 import time
 import psutil
 import optuna
+import ast
 
-from huggingface_hub import login
-
-# Add this before model initialization
+# Authenticate Hugging Face
 hf_token = os.getenv("HF_TOKEN")
 login(token=hf_token, add_to_git_credential=True)
 
-# Then create model with explicit token
-model = HfApiModel(
-    "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    token=hf_token  # Pass token explicitly
-)
+# Initialize Model
+model = HfApiModel("mistralai/Mixtral-8x7B-Instruct-v0.1", token=hf_token)
 
-# Add this formatting function
 def format_analysis_report(raw_output, visuals):
     try:
-        # Check if raw_output is already a dictionary
-        if isinstance(raw_output, dict):
-            analysis_dict = raw_output
-        else:
-            # Attempt to convert string output to dictionary
-            analysis_dict = ast.literal_eval(str(raw_output))
+        analysis_dict = raw_output if isinstance(raw_output, dict) else ast.literal_eval(str(raw_output))
         
         report = f"""
         <div style="font-family: Arial, sans-serif; padding: 20px; color: #333;">
             <h1 style="color: #2B547E; border-bottom: 2px solid #2B547E; padding-bottom: 10px;">📊 Data Analysis Report</h1>
-            
             <div style="margin-top: 25px; background: #f8f9fa; padding: 20px; border-radius: 8px;">
                 <h2 style="color: #2B547E;">🔍 Key Observations</h2>
                 {format_observations(analysis_dict.get('observations', {}))}
             </div>
-            
             <div style="margin-top: 30px;">
                 <h2 style="color: #2B547E;">💡 Insights & Visualizations</h2>
                 {format_insights(analysis_dict.get('insights', {}), visuals)}
@@ -50,212 +38,92 @@ def format_analysis_report(raw_output, visuals):
         return raw_output, visuals
 
 def format_observations(observations):
-    items = []
-    for key, value in observations.items():
-        if 'proportions' in key:
-            items.append(f"""
-            <div style="margin: 15px 0; padding: 15px; background: white; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.05);">
-                <h3 style="margin: 0 0 10px 0; color: #4A708B;">{key.replace('_', ' ').title()}</h3>
-                <pre style="margin: 0; padding: 10px; background: #f8f9fa; border-radius: 4px;">{value}</pre>
-            </div>
-            """)
-    return '\n'.join(items)
+    return '\n'.join([
+        f"""
+        <div style="margin: 15px 0; padding: 15px; background: white; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.05);">
+            <h3 style="margin: 0 0 10px 0; color: #4A708B;">{key.replace('_', ' ').title()}</h3>
+            <pre style="margin: 0; padding: 10px; background: #f8f9fa; border-radius: 4px;">{value}</pre>
+        </div>
+        """ for key, value in observations.items() if 'proportions' in key
+    ])
 
 def format_insights(insights, visuals):
-    items = []
-    for idx, (key, insight) in enumerate(insights.items()):
-        img_tag = ""
-        if idx < len(visuals):
-            img_tag = f'<img src="/file={visuals[idx]}" style="max-width: 100%; height: auto; margin-top: 10px; border-radius: 6px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">'
-        
-        items.append(f"""
+    return '\n'.join([
+        f"""
         <div style="margin: 20px 0; padding: 20px; background: white; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.05);">
             <div style="display: flex; align-items: center; gap: 10px;">
                 <div style="background: #2B547E; color: white; width: 30px; height: 30px; border-radius: 50%; display: flex; align-items: center; justify-content: center;">{idx+1}</div>
                 <p style="margin: 0; font-size: 16px;">{insight}</p>
             </div>
-            {img_tag}
+            {f'<img src="/file={visuals[idx]}" style="max-width: 100%; height: auto; margin-top: 10px; border-radius: 6px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">' if idx < len(visuals) else ''}
         </div>
-        """)
-    return '\n'.join(items)
+        """ for idx, (key, insight) in enumerate(insights.items())
+    ])
 
 def analyze_data(csv_file, additional_notes=""):
-
-
-       # Start timing
     start_time = time.time()
-
-    # Get initial memory usage
     process = psutil.Process(os.getpid())
-    initial_memory = process.memory_info().rss / 1024 ** 2  # Convert to MB
+    initial_memory = process.memory_info().rss / 1024 ** 2
     
-    # Clear previous figures
     if os.path.exists('./figures'):
         shutil.rmtree('./figures')
     os.makedirs('./figures', exist_ok=True)
-
-        # 🚨 Initialize W&B run
+    
     wandb.login(key=os.environ.get('WANDB_API_KEY'))
-    run = wandb.init(
-        project="huggingface-data-analysis",
-        config={
-            "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
-            "additional_notes": additional_notes,
-            "source_file": csv_file.name if csv_file else None
-        }
-    )
-
-    # Initialize model and agent
-    model = HfApiModel("mistralai/Mixtral-8x7B-Instruct-v0.1")  # Best overall
-    agent = CodeAgent(
-    tools=[],
-    model=model,
-    additional_authorized_imports=[
-        "numpy",
-        "pandas", 
-        "matplotlib.pyplot",
-        "seaborn"
-    ],
-    )
-    # Run analysis
-    analysis_result = agent.run(
-        """You are an expert data analyst. Perform comprehensive analysis including:
+    run = wandb.init(project="huggingface-data-analysis", config={
+        "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "additional_notes": additional_notes,
+        "source_file": csv_file.name if csv_file else None
+    })
+    
+    agent = CodeAgent(tools=[], model=model, additional_authorized_imports=["numpy", "pandas", "matplotlib.pyplot", "seaborn"])
+    analysis_result = agent.run("""
+        You are an expert data analyst. Perform comprehensive analysis including:
         1. Basic statistics and data quality checks
         2. 3 insightful analytical questions about relationships in the data
         3. Visualization of key patterns and correlations
         4. Actionable real-world insights derived from findings
-        
         Generate publication-quality visualizations and save to './figures/'
-        """,
-        additional_args={
-            "additional_notes": additional_notes,
-            "source_file": csv_file
-        }
-    )
+    """, additional_args={"additional_notes": additional_notes, "source_file": csv_file})
+    
+    execution_time = time.time() - start_time
+    final_memory = process.memory_info().rss / 1024 ** 2
+    memory_usage = final_memory - initial_memory
+    wandb.log({"execution_time_sec": execution_time, "memory_usage_mb": memory_usage})
+    
+    visuals = [os.path.join('./figures', f) for f in os.listdir('./figures') if f.endswith(('.png', '.jpg', '.jpeg'))]
+    for viz in visuals:
+        wandb.log({os.path.basename(viz): wandb.Image(viz)})
+    
+    run.finish()
+    return format_analysis_report(analysis_result, visuals)
 
-    analysis_result = agent.run(
-        f"""Perform comprehensive analysis with:
-        - Learning Rate: {learning_rate}
-        - Batch Size: {batch_size}
-        - Epochs: {num_epochs}
-        """,
-        additional_args={}
-    )
 def objective(trial):
     learning_rate = trial.suggest_loguniform("learning_rate", 1e-5, 5e-3)
     batch_size = trial.suggest_categorical("batch_size", [8, 16, 32])
     num_epochs = trial.suggest_int("num_epochs", 1, 5)
-    
+    return learning_rate * batch_size * num_epochs
+
 def tune_hyperparameters(n_trials: int):
     study = optuna.create_study(direction="minimize")
     study.optimize(objective, n_trials=n_trials)
-
     return f"Best Hyperparameters: {study.best_params}"
 
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("## 📊 AI Data Analysis Agent with Hyperparameter Optimization")
-
-with gr.Row():
+    with gr.Row():
         with gr.Column():
             file_input = gr.File(label="Upload CSV Dataset", type="filepath")
             notes_input = gr.Textbox(label="Dataset Notes (Optional)", lines=3)
             analyze_btn = gr.Button("Analyze", variant="primary")
             optuna_trials = gr.Number(label="Number of Hyperparameter Tuning Trials", value=10)
             tune_btn = gr.Button("Optimize Hyperparameters", variant="secondary")
-
         with gr.Column():
             analysis_output = gr.Markdown("### Analysis results will appear here...")
             optuna_output = gr.Textbox(label="Best Hyperparameters")
             gallery = gr.Gallery(label="Data Visualizations", columns=2)
-
-    analyze_btn.click(
-        fn=analyze_data,
-        inputs=[file_input, notes_input],
-        outputs=[analysis_output, gallery]
-    )
-
-    tune_btn.click(
-        fn=tune_hyperparameters,
-        inputs=[optuna_trials],
-        outputs=[optuna_output]
-    )
-
-demo.launch(debug=True)
-
-
-   # Assume we minimize some loss value (replace with actual metric)
-    loss = analysis_result.get("loss", 0.1)  # Mock value
-    return loss  # Optuna minimizes the loss
-       # Measure execution time and memory usage
-    execution_time = time.time() - start_time
-    final_memory = process.memory_info().rss / 1024 ** 2  # Convert to MB
-    memory_usage = final_memory - initial_memory  # Calculate memory consumed
-
-    # 🚨 Log Performance Metrics
-    wandb.log({
-        "execution_time_sec": execution_time,
-        "memory_usage_mb": memory_usage
-    })
-
-    # Log analysis results to W&B
-    if isinstance(analysis_result, dict):
-        wandb.log({
-            "observations": analysis_result.get('observations', {}),
-            "insights": analysis_result.get('insights', {}),
-            "num_visuals": len(os.listdir('./figures'))  # Ensure visuals are counted
-        })
-
-    # Log generated visualizations
-    visuals = [os.path.join('./figures', f) for f in os.listdir('./figures') 
-               if f.endswith(('.png', '.jpg', '.jpeg'))]
-    for viz in visuals:
-        wandb.log({os.path.basename(viz): wandb.Image(viz)})
-
-
-     # 🚨 Log visualizations to W&B
-    if visuals:
-        try:
-            for viz in visuals:
-                wandb.log({os.path.basename(viz): wandb.Image(viz)})
-        except Exception as e:
-            print(f"Error logging visuals: {e}")
-
-            # 🚨 Log CSV as artifact
-    if csv_file:
-        try:
-            artifact = wandb.Artifact(
-                name="source_data",
-                type="dataset",
-                description="Uploaded CSV for analysis"
-            )
-            artifact.add_file(csv_file.name)
-            wandb.log_artifact(artifact)
-        except Exception as e:
-            print(f"Error logging CSV: {e}")
-            
-    # 🚨 Finish W&B run
-    run.finish()
     
-    return format_analysis_report(analysis_result, visuals)
+    analyze_btn.click(fn=analyze_data, inputs=[file_input, notes_input], outputs=[analysis_output, gallery])
+    tune_btn.click(fn=tune_hyperparameters, inputs=[optuna_trials], outputs=[optuna_output])
 
-# Create Gradio interface
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("## 📊 AI Data Analysis Agent")
-    
-    with gr.Row():
-        with gr.Column():
-            file_input = gr.File(label="Upload CSV Dataset", type="filepath")
-            notes_input = gr.Textbox(label="Dataset Notes (Optional)", lines=3)
-            analyze_btn = gr.Button("Analyze", variant="primary")
-        
-        with gr.Column():
-            analysis_output = gr.Markdown("### Analysis results will appear here...")
-            gallery = gr.Gallery(label="Data Visualizations", columns=2)
-
-    analyze_btn.click(
-        fn=analyze_data,
-        inputs=[file_input, notes_input],
-        outputs=[analysis_output, gallery]
-    )
-
-demo.launch(debug=True)
+demo.launch(debug=True)