added a bunch of helper scripts

batch_analysis_analysis.py

@@ -27,6 +27,9 @@ def main():
     # Group data by chain
     chain_groups = df.groupby('chain')
 
+    # Prepare list to collect summary data for CSV export
+    summary_data = []
+
     # For each chain, create a figure with five subplots for boxplots (mean, std, min, max, count)
     for chain_name, chain_data in chain_groups:
         fig, axs = plt.subplots(1, 5, figsize=(18, 6), constrained_layout=True)
@@ -38,6 +41,17 @@ def main():
         plot_data = chain_data[['mean', 'std', 'min', 'max', 'count']].copy()
         plot_data.columns = ['Mean', 'Std', 'Min', 'Max', 'Count']
 
+        # Calculate summary statistics for CSV export
+        chain_summary = {
+            'chain': chain_name,
+            'mean_count': plot_data['Count'].mean(),
+            'mean_mean': plot_data['Mean'].mean(),
+            'mean_std': plot_data['Std'].mean(),
+            'mean_min': plot_data['Min'].mean(),
+            'mean_max': plot_data['Max'].mean()
+        }
+        summary_data.append(chain_summary)
+
         # Make all plots have the same color palette
         palette = sns.color_palette("husl", 4)
         # Add a distinct color for the 'Count' plot, as it is a different metric
@@ -114,7 +128,13 @@ def main():
         print(f"\nSummary for chain: {chain_name}")
         print(summary[['mean', 'std', 'min', 'max', 'count']])
 
+    # Create and save the summary CSV
+    summary_df = pd.DataFrame(summary_data)
+    summary_csv_file = args.input.replace('.csv', '_summary.csv')
+    summary_df.to_csv(summary_csv_file, index=False)
+
     print(f"\nAnalysis complete. Plots saved with base name: {args.input.replace('.csv', '_chain_*_analysis.png')}")
+    print(f"Summary CSV saved as: {summary_csv_file}")
 
 if __name__ == "__main__":
     main()