add code for analysis of data

1 files changed, 87 insertions, 0 deletions

diff --git a/analysis.py b/analysis.py
index 15ba0ef..912eb0a 100644
--- a/analysis.py
+++ b/analysis.py
@@ -1,5 +1,92 @@
 import json
 import datetime
+import os
+
+def summarize_results(batch_name):
+    """
+    Summarizes the results of the backtesting by calculating average percent gain/loss,
+    and finding the best stock order.
+    """
+    
+    # get the result data json files under batches
+    batch_folder = f'batches/{batch_name}'
+    result_files = [f for f in os.listdir(batch_folder) if f.endswith('.json')]
+
+    results_summary = []
+
+    # make a dict for the algo table
+    algos_to_results = {}
+    print(len(result_files), "results found in", batch_folder)
+    for result in result_files:
+        file_path = os.path.join(batch_folder, result)
+        with open(file_path, 'r') as fd:
+            result_data = json.load(fd)
+        
+        # extract the relevant data
+        result = result_data['backtest_results']
+        if not result:
+            continue
+
+        algo_name = result['algo_name']
+        algo_params = result['algo_params']
+        algo_key = f"{algo_name}_{algo_params}"
+
+        if algo_key not in algos_to_results:
+            algos_to_results[algo_key] = {
+                'percent_gains': [],
+                'stock_orders': []
+            }
+
+        algos_to_results[algo_key]['percent_gains'].append(result['percent_gain'])
+
+        stock_ticker = result_data['url_params']['ticker']
+        algos_to_results[algo_key]['stock_orders'].append(stock_ticker)
+
+    # summarize the results for each algo
+    for algo_name, result in algos_to_results.items():
+        algo_params = algo_name.split('_')[1]  # Extract params from the key
+        if not result['percent_gains'] and not result['percent_losses']:
+            continue  # Skip if no gains or losses
+
+        # calculate average percent gain/loss
+        avg_percent_gain = sum(result['percent_gains']) / len(result['percent_gains']) if result['percent_gains'] else 0
+
+        # calculate which stock ticker produced the best result
+        stock_orders = result['stock_orders']
+        if stock_orders:
+            best_stock_order = max(set(stock_orders), key=stock_orders.count)
+        else:
+            best_stock_order = "N/A"
+
+        # Append the summarized data
+        results_summary.append([
+            algo_name, 
+            algo_params,
+            avg_percent_gain, 
+            best_stock_order
+        ])
+    
+    # Sort the results by average percent gain in descending order
+    results_summary.sort(key=lambda x: x[2], reverse=True)
+
+    print(algos_to_results)
+    
+    return results_summary 
+
+def test():
+    """
+    Test function to summarize results from a specific batch.
+    """
+    batch_name = 'test-1-ema'
+    results = summarize_results(batch_name)
+    if results:
+        print("Results Summary:")
+        for row in results:
+            print(row)
+    else:
+        print("No results found.")    
+
+test()
 
 # pull stock data from json files
 # timestamps_file = open('timestamps.json', 'r')