Update app.py

app.py

@@ -4,11 +4,13 @@
 #
 # DESCRIPTION:  An enterprise-grade Gradio application that revolutionizes Exploratory
 #               Data Analysis (EDA). By integrating Google's Gemini Pro LLM, this
-#               tool transcends traditional data profiling. It automates the generation
-#               of statistical summaries, interactive visualizations, and, most
-#               importantly, a rich, narrative-driven analysis. It delivers
-#               executive summaries, data quality assessments, actionable insights,
-#               and strategic recommendations in a single, streamlined workflow.
+#               tool transcends traditional data profiling to deliver a rich,
+#               narrative-driven analysis, actionable insights, and strategic
+#               recommendations in a single, streamlined workflow.
+#
+# SETUP:        This application has external dependencies. Before running, install
+#               all required packages using the requirements.txt file:
+#               $ pip install -r requirements.txt
 #
 # ARCHITECTURE: The application is built upon a robust, object-oriented foundation.
 #               - DataAnalyzer (Core Engine): An encapsulated class that holds the
@@ -19,27 +21,19 @@
 #                 high-quality analytical narratives.
 #               - Gradio Interface (UI Layer): A multi-tabbed, interactive dashboard
 #                 that logically separates the AI narrative, data profiling, static
-#                 visuals, and interactive exploration tools. State is managed
-#                 efficiently to provide a responsive user experience.
-#
-# FEATURES:
-#   - AI-Powered Executive Summary: Generates a high-level overview for stakeholders.
-#   - Automated Data Quality Audit: Provides a quality score and actionable cleaning steps.
-#   - Insight Discovery Engine: Uncovers hidden patterns, correlations, and anomalies.
-#   - Strategic Recommendations: Suggests next steps, modeling approaches, and business use cases.
-#   - Comprehensive Profiling: Detailed statistical tables for all data types.
-#   - Interactive Visualization Suite: Dynamic plots for deep-dive analysis.
-#   - One-Click Report Export: Downloads the complete AI-generated analysis as a Markdown file.
+#                 visuals, and interactive exploration tools.
 #
 # AUTHOR:       An MCP Expert in Data & AI Solutions
-# VERSION:      3.0 (Enterprise Edition)
-# LAST-UPDATE:  2023-10-27
+# VERSION:      3.1 (Enterprise Edition)
+# LAST-UPDATE:  2023-10-28 (Added dependency check & requirements file)
 
 from __future__ import annotations
 
 import warnings
 import logging
 import os
+import sys
+import importlib.util
 from datetime import datetime
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -93,7 +87,6 @@ class DataAnalyzer:
         numeric_cols = self.df.select_dtypes(include=np.number).columns.tolist()
         categorical_cols = self.df.select_dtypes(include=['object', 'category']).columns.tolist()
         
-        # Advanced: High correlation pair detection
         high_corr_pairs = []
         if len(numeric_cols) > 1:
             corr_matrix = self.df[numeric_cols].corr().abs()
@@ -120,18 +113,15 @@ class DataAnalyzer:
     def get_profiling_tables(self) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
         """Generates structured DataFrames for data profiling."""
         logging.info("Generating profiling tables for missing, numeric, and categorical data.")
-        # Missing data profile
         missing = self.df.isnull().sum()
         missing_df = pd.DataFrame({
             'Missing Count': missing,
             'Missing Percentage (%)': (missing / len(self.df) * 100).round(2)
         }).reset_index().rename(columns={'index': 'Column'}).sort_values('Missing Count', ascending=False)
 
-        # Numeric features profile
         numeric_stats = self.df[self.metadata['numeric_cols']].describe(percentiles=[.01, .25, .5, .75, .99]).T
         numeric_stats_df = numeric_stats.round(3).reset_index().rename(columns={'index': 'Column'})
 
-        # Categorical features profile
         cat_stats = self.df[self.metadata['categorical_cols']].describe(include=['object', 'category']).T
         cat_stats_df = cat_stats.reset_index().rename(columns={'index': 'Column'})
 
@@ -174,7 +164,10 @@ class DataAnalyzer:
         logging.info("Generating AI narrative with the Gemini API.")
         meta = self.metadata
         
-        # A more sophisticated, structured prompt for a better report
+        # NOTE: The .to_markdown() method requires the 'tabulate' library.
+        # This is handled by the pre-flight check in if __name__ == "__main__":
+        data_snippet_md = self.df.head(5).to_markdown(index=False)
+        
         prompt = f"""
         As "Cognitive Analyst," an elite AI data scientist, your task is to generate a comprehensive, multi-part data discovery report.
         Analyze the following dataset context and produce a professional, insightful, and clear analysis in Markdown format.
@@ -188,7 +181,7 @@ class DataAnalyzer:
         - **Total Missing Values:** {meta['total_missing']:,}
         - **High-Correlation Pairs (>{Config.CORR_THRESHOLD}):** {meta['high_corr_pairs'] if meta['high_corr_pairs'] else 'None detected.'}
         - **Data Snippet (First 5 Rows):**
-        {self.df.head(5).to_markdown(index=False)}
+        {data_snippet_md}
 
         **REQUIRED REPORT STRUCTURE (Strictly use this Markdown format):**
 
@@ -240,8 +233,6 @@ class DataAnalyzer:
 
 def create_ui():
     """Defines and builds the Gradio user interface."""
-    
-    # --- Interactive Plotting Functions (scoped inside UI creation for clarity) ---
     def create_histogram(analyzer: DataAnalyzer, col: str) -> go.Figure:
         if not col or not analyzer: return go.Figure()
         return px.histogram(analyzer.df, x=col, title=f"<b>Distribution of {col}</b>", marginal="box", template="plotly_white")
@@ -279,11 +270,8 @@ def create_ui():
             
         return stats_md, fig
 
-    # --- Main UI Blocks ---
     with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="cyan"), title=Config.APP_TITLE) as demo:
-        # Store for the main DataAnalyzer object
         state_analyzer = gr.State()
-
         gr.Markdown(f"<h1>{Config.APP_TITLE}</h1>")
         gr.Markdown("Upload a CSV file, provide your Gemini API key, and receive an instant, AI-driven analysis of your data.")
 
@@ -295,37 +283,30 @@ def create_ui():
             with gr.Column(scale=1, min_width=150):
                 analyze_button = gr.Button("✨ Generate Analysis", variant="primary")
         
-        with gr.Tabs() as tabs:
-            with gr.Tab("🤖 AI Narrative", id=0):
+        with gr.Tabs():
+            with gr.Tab("🤖 AI Narrative"):
                 ai_report_output = gr.Markdown("Your AI-generated report will appear here once analysis is complete...")
                 download_report_button = gr.Button("⬇️ Download Full Report", visible=False)
-
-            with gr.Tab(" Profile", id=1):
+            with gr.Tab("Profile"):
                 gr.Markdown("### **Detailed Data Profile**")
-                gr.Markdown("#### Missing Data Summary")
                 profile_missing_df = gr.DataFrame(interactive=False, label="Missing Values")
-                gr.Markdown("#### Numeric Features Summary")
                 profile_numeric_df = gr.DataFrame(interactive=False, label="Numeric Stats")
-                gr.Markdown("#### Categorical Features Summary")
                 profile_categorical_df = gr.DataFrame(interactive=False, label="Categorical Stats")
-                
-            with gr.Tab("📈 Overview Visuals", id=2):
+            with gr.Tab("📈 Overview Visuals"):
                 gr.Markdown("### **At-a-Glance Visualizations**")
                 with gr.Row():
                     plot_types = gr.Plot()
                     plot_missing = gr.Plot()
                 plot_correlation = gr.Plot()
-            
-            with gr.Tab("🎨 Interactive Explorer", id=3):
+            with gr.Tab("🎨 Interactive Explorer"):
                 gr.Markdown("### **Visually Explore Feature Relationships**")
-                with gr.Row():
+                with gr.Row(equal_height=False):
                     with gr.Column(scale=1):
                         gr.Markdown("#### Univariate Analysis")
                         dd_hist_col = gr.Dropdown(label="Select Column for Histogram", visible=False)
                     with gr.Column(scale=2):
                         plot_histogram = gr.Plot()
-
-                with gr.Row():
+                with gr.Row(equal_height=False):
                     with gr.Column(scale=1):
                         gr.Markdown("#### Bivariate Analysis (Scatter Plot)")
                         dd_scatter_x = gr.Dropdown(label="X-Axis (Numeric)", visible=False)
@@ -333,8 +314,7 @@ def create_ui():
                         dd_scatter_color = gr.Dropdown(label="Color By (Optional)", visible=False)
                     with gr.Column(scale=2):
                         plot_scatter = gr.Plot()
-
-            with gr.Tab("🔍 Column Deep-Dive", id=4):
+            with gr.Tab("🔍 Column Deep-Dive"):
                 gr.Markdown("### **Inspect a Single Column in Detail**")
                 dd_drilldown_col = gr.Dropdown(label="Select Column to Analyze", visible=False)
                 with gr.Row():
@@ -344,54 +324,29 @@ def create_ui():
         gr.HTML("""
         <div style="text-align: center; margin-top: 20px; font-family: sans-serif; color: #777;">
             <p>💡 Need an API key? Get one from <a href="https://aistudio.google.com/app/apikey" target="_blank">Google AI Studio</a>.</p>
-            <p>CognitiveEDA v3.0 | An MCP Expert System</p>
+            <p>CognitiveEDA v3.1 | An MCP Expert System</p>
         </div>
         """)
 
-        # --- Event Listeners & Control Flow ---
-
         outputs_for_main_analysis = [
             state_analyzer, ai_report_output, download_report_button,
             profile_missing_df, profile_numeric_df, profile_categorical_df,
             plot_types, plot_missing, plot_correlation,
             dd_hist_col, dd_scatter_x, dd_scatter_y, dd_scatter_color, dd_drilldown_col
         ]
-        
-        analyze_button.click(
-            fn=run_full_analysis,
-            inputs=[upload_button, api_key_input],
-            outputs=outputs_for_main_analysis
-        )
-        
-        # Interactive plot triggers
+        analyze_button.click(fn=run_full_analysis, inputs=[upload_button, api_key_input], outputs=outputs_for_main_analysis)
         dd_hist_col.change(fn=create_histogram, inputs=[state_analyzer, dd_hist_col], outputs=plot_histogram)
-        
         scatter_inputs = [state_analyzer, dd_scatter_x, dd_scatter_y, dd_scatter_color]
-        dd_scatter_x.change(fn=create_scatterplot, inputs=scatter_inputs, outputs=plot_scatter)
-        dd_scatter_y.change(fn=create_scatterplot, inputs=scatter_inputs, outputs=plot_scatter)
-        dd_scatter_color.change(fn=create_scatterplot, inputs=scatter_inputs, outputs=plot_scatter)
-        
-        dd_drilldown_col.change(
-            fn=analyze_single_column,
-            inputs=[state_analyzer, dd_drilldown_col],
-            outputs=[md_drilldown_stats, plot_drilldown]
-        )
-        
-        download_report_button.click(
-            fn=download_report_file,
-            inputs=[state_analyzer, ai_report_output],
-            outputs=gr.File(label="Download Report")
-        )
-
+        for dd in [dd_scatter_x, dd_scatter_y, dd_scatter_color]:
+            dd.change(fn=create_scatterplot, inputs=scatter_inputs, outputs=plot_scatter)
+        dd_drilldown_col.change(fn=analyze_single_column, inputs=[state_analyzer, dd_drilldown_col], outputs=[md_drilldown_stats, plot_drilldown])
+        download_report_button.click(fn=download_report_file, inputs=[state_analyzer, ai_report_output], outputs=gr.File(label="Download Report"))
     return demo
 
 # --- Main Application Logic ---
 
 def run_full_analysis(file_obj: gr.File, api_key: str) -> Dict[gr.component, Any]:
-    """
-    Orchestrates the entire analysis pipeline upon button click.
-    Returns a dictionary to update all relevant UI components at once.
-    """
+    """Orchestrates the entire analysis pipeline upon button click."""
     if file_obj is None:
         raise gr.Error("CRITICAL: No file uploaded. Please select a CSV file.")
     if not api_key:
@@ -402,43 +357,30 @@ def run_full_analysis(file_obj: gr.File, api_key: str) -> Dict[gr.component, Any
         df = pd.read_csv(file_obj.name)
         analyzer = DataAnalyzer(df)
 
-        # --- Execute all analysis tasks concurrently (conceptually) ---
         ai_report = analyzer.generate_ai_narrative(api_key)
         missing_df, num_df, cat_df = analyzer.get_profiling_tables()
         fig_types, fig_missing, fig_corr = analyzer.get_overview_visuals()
         
-        # --- Prepare UI component updates ---
         meta = analyzer.metadata
-        all_cols, num_cols, cat_cols = meta['columns'], meta['numeric_cols'], meta['categorical_cols']
+        all_cols, num_cols = meta['columns'], meta['numeric_cols']
         
-        # Return a dictionary mapping components to their new state/value
         return {
-            # State & AI Report
-            state_analyzer: analyzer,
-            ai_report_output: ai_report,
+            state_analyzer: analyzer, ai_report_output: ai_report,
             download_report_button: gr.Button(visible=True),
-            # Profiling Tab
-            profile_missing_df: missing_df,
-            profile_numeric_df: num_df,
-            profile_categorical_df: cat_df,
-            # Overview Visuals Tab
-            plot_types: fig_types,
-            plot_missing: fig_missing,
-            plot_correlation: fig_corr,
-            # Interactive Explorer & Drilldown Dropdown Updates
+            profile_missing_df: missing_df, profile_numeric_df: num_df,
+            profile_categorical_df: cat_df, plot_types: fig_types,
+            plot_missing: fig_missing, plot_correlation: fig_corr,
             dd_hist_col: gr.Dropdown(choices=num_cols, label="Select Numeric Column", visible=True),
             dd_scatter_x: gr.Dropdown(choices=num_cols, label="X-Axis (Numeric)", visible=True),
             dd_scatter_y: gr.Dropdown(choices=num_cols, label="Y-Axis (Numeric)", visible=True),
             dd_scatter_color: gr.Dropdown(choices=all_cols, label="Color By (Optional)", visible=True),
             dd_drilldown_col: gr.Dropdown(choices=all_cols, label="Select Column to Analyze", visible=True)
         }
-
     except Exception as e:
         logging.error(f"A critical error occurred during file processing: {e}", exc_info=True)
         raise gr.Error(f"Analysis Failed! The process stopped due to: {str(e)}")
 
-
-def download_report_file(analyzer: DataAnalyzer, ai_report_text: str) -> str:
+def download_report_file(analyzer: DataAnalyzer, ai_report_text: str) -> Optional[str]:
     """Generates a comprehensive Markdown file for download."""
     if not analyzer:
         logging.warning("Download attempted without a valid analyzer object.")
@@ -446,8 +388,6 @@ def download_report_file(analyzer: DataAnalyzer, ai_report_text: str) -> str:
         
     filename = f"CognitiveEDA_Report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.md"
     meta = analyzer.metadata
-
-    # Assemble the full report
     full_report = f"# CognitiveEDA - Data Discovery Report\n"
     full_report += f"**Generated:** {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
     full_report += f"## Dataset Overview\n"
@@ -459,11 +399,27 @@ def download_report_file(analyzer: DataAnalyzer, ai_report_text: str) -> str:
     
     with open(filename, "w", encoding="utf-8") as f:
         f.write(full_report)
-        
     logging.info(f"Report file generated successfully: {filename}")
     return filename
 
+def perform_pre_flight_checks():
+    """Checks for critical dependencies before launching the app."""
+    logging.info("Performing pre-flight dependency checks...")
+    required_packages = ["pandas", "gradio", "plotly", "google.generativeai", "tabulate"]
+    missing_packages = [pkg for pkg in required_packages if importlib.util.find_spec(pkg) is None]
+
+    if missing_packages:
+        logging.critical(f"Missing critical packages: {', '.join(missing_packages)}")
+        print("\n" + "="*80)
+        print("ERROR: Your environment is missing critical dependencies.")
+        print(f"Missing package(s): {', '.join(missing_packages)}")
+        print("Please install all required packages using the requirements.txt file:")
+        print("pip install -r requirements.txt")
+        print("="*80 + "\n")
+        sys.exit(1)
+    logging.info("All dependencies are satisfied. Proceeding with launch.")
 
 if __name__ == "__main__":
+    perform_pre_flight_checks()
     app_instance = create_ui()
     app_instance.launch(debug=True, server_name="0.0.0.0")