idk

run_cci_analysis.py

@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+"""
+California Climate Investments (CCI) Collaboration Analysis Workflow
+
+This script runs the complete workflow for analyzing collaboration patterns
+in California's Climate Investments program and their impact on greenhouse
+gas reduction efficiency and equity outcomes.
+
+Usage:
+    python run_cci_analysis.py --data_path data/cci_programs_data_reduced.csv --output_dir output
+"""
+
+import os
+import argparse
+import logging
+from pathlib import Path
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, 
+                   format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logger = logging.getLogger("cci_workflow")
+
+def main():
+    """Run the complete CCI collaboration analysis workflow."""
+    parser = argparse.ArgumentParser(description='Run CCI Collaboration Analysis Workflow')
+    parser.add_argument('--data_path', type=str, required=True, help='Path to the raw CCI data CSV file')
+    parser.add_argument('--output_dir', type=str, default='./output', help='Directory to save all outputs')
+    parser.add_argument('--skip_cleaning', action='store_true', help='Skip the data cleaning step')
+    parser.add_argument('--skip_analysis', action='store_true', help='Skip the detailed analysis step')
+    parser.add_argument('--skip_research', action='store_true', help='Skip the research questions analysis')
+    
+    args = parser.parse_args()
+    
+    # Create output directory
+    output_dir = Path(args.output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    
+    # File paths
+    raw_data_path = args.data_path
+    cleaned_data_path = output_dir / "cleaned_cci_data.csv"
+    data_summary_path = output_dir / "data_summary.json"
+    
+    # Create subdirectories for different analysis outputs
+    cleaned_output_dir = output_dir / "cleaned"
+    analysis_output_dir = output_dir / "analysis"
+    research_output_dir = output_dir / "research"
+    
+    for directory in [cleaned_output_dir, analysis_output_dir, research_output_dir]:
+        directory.mkdir(parents=True, exist_ok=True)
+    
+    # Step 1: Clean and prepare the data
+    if not args.skip_cleaning:
+        logger.info("Step 1: Cleaning and preparing the CCI data")
+        
+        try:
+            from data_cleaning_script import clean_and_prepare_cci_data, generate_data_summary
+            
+            # Clean and prepare the data
+            cleaned_df = clean_and_prepare_cci_data(raw_data_path, cleaned_data_path)
+            
+            # Generate data summary
+            generate_data_summary(cleaned_df, data_summary_path)
+            
+            logger.info(f"Data cleaning complete. Cleaned data saved to {cleaned_data_path}")
+            logger.info(f"Data summary saved to {data_summary_path}")
+            
+        except Exception as e:
+            logger.error(f"Error in data cleaning step: {e}")
+            return
+    else:
+        logger.info("Skipping data cleaning step")
+        # Check if cleaned data exists
+        if not cleaned_data_path.exists():
+            logger.error(f"Cleaned data file {cleaned_data_path} not found. Cannot proceed without data.")
+            return
+    
+    # Step 2: Run the detailed collaboration analysis
+    if not args.skip_analysis:
+        logger.info("Step 2: Running detailed collaboration analysis")
+        
+        try:
+            from cci_collaboration_analysis import CCICollaborationAnalyzer
+            
+            # Initialize the analyzer
+            analyzer = CCICollaborationAnalyzer(cleaned_data_path, str(analysis_output_dir))
+            
+            # Run full analysis
+            analyzer.run_full_analysis()
+            
+            logger.info(f"Detailed analysis complete. Results saved to {analysis_output_dir}")
+            
+        except Exception as e:
+            logger.error(f"Error in detailed analysis step: {e}")
+            logger.error("Continuing to research analysis with available data...")
+    else:
+        logger.info("Skipping detailed analysis step")
+    
+    # Step 3: Analyze specific research questions
+    if not args.skip_research:
+        logger.info("Step 3: Analyzing research questions")
+        
+        try:
+            from research_analysis_script import analyze_research_questions
+            
+            # Run research analysis
+            findings = analyze_research_questions(cleaned_data_path, str(research_output_dir))
+            
+            if findings:
+                logger.info(f"Research analysis complete. Results saved to {research_output_dir}")
+            else:
+                logger.error("Research analysis failed to complete successfully")
+            
+        except Exception as e:
+            logger.error(f"Error in research analysis step: {e}")
+    else:
+        logger.info("Skipping research analysis step")
+    
+    logger.info("CCI Collaboration Analysis Workflow complete!")
+
+
+if __name__ == "__main__":
+    main()