Updating another attempt. currently there are errors

src/MidasHL/output/logs/futures_trading_ai.log

@@ -1,3 +1,18 @@
 2025-04-12 20:44:28,103 - __main__ - INFO - Starting FuturesTradingAI application...
 2025-04-12 20:44:28,104 - __main__ - INFO - Loading data from /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv...
 2025-04-12 20:44:28,107 - src.data.loader - ERROR - Data file not found: /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv
+2025-04-12 20:59:23,967 - __main__ - INFO - Starting FuturesTradingAI application...
+2025-04-12 20:59:23,968 - __main__ - INFO - Loading data from /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv...
+2025-04-12 20:59:23,968 - root - INFO - Loading data from: /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv
+2025-04-12 20:59:23,968 - root - ERROR - Data file not found: /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv
+2025-04-12 21:23:12,967 - __main__ - INFO - Starting FuturesTradingAI application...
+2025-04-12 21:23:12,968 - __main__ - INFO - Loading data from /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv...
+2025-04-12 21:23:12,968 - root - INFO - Loading data from: /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv
+2025-04-12 21:23:12,968 - root - ERROR - Data file not found: /home/midas/codeWS/Projects/MidasTechnologiesINC/MidasEngine/src/MidasHL/data/sample_data.csv
+2025-04-12 21:25:01,971 - __main__ - INFO - Starting FuturesTradingAI application...
+2025-04-12 21:25:01,972 - __main__ - INFO - Loading data from src/data/cleaned_MES_data.csv...
+2025-04-12 21:25:01,972 - root - INFO - Loading data from: src/data/cleaned_MES_data.csv
+2025-04-12 21:25:01,972 - root - INFO - Detected CSV file format.
+2025-04-12 21:25:02,058 - root - INFO - Data columns after renaming: ['Date', 'Open', 'High', 'Low', 'Close', 'Volume']
+2025-04-12 21:25:02,063 - root - INFO - Data loaded and sorted successfully.
+2025-04-12 21:25:02,063 - __main__ - INFO - Calculating technical indicators on dataset...

src/MidasHL/src/data/loader.py

@@ -1,59 +1,75 @@
 """
 src/data/loader.py
 
-This module provides functions to load and clean CSV market data.
+This module provides functions to load and clean market data from various file types.
+It now supports both CSV and JSON files. When a file path is passed (for example,
+using the --mode testing flag), the function detects the file extension and loads
+the data with the appropriate Pandas reader.
+
+The expected columns are: time, open, high, low, close, volume.
+After loading, columns are renamed for consistency and the data is sorted chronologically.
 """
 
 import pandas as pd
 import logging
+import sys
+import os
 
 def load_data(file_path):
     """
-    Load CSV data from the specified file path.
+    Load market data from a specified file, supporting both CSV and JSON formats.
     
     Parameters:
-    - file_path (str): Path to the CSV file.
+    - file_path (str): Path to the data file (CSV or JSON).
     
     Returns:
-    - pandas.DataFrame: Loaded and cleaned data.
+    - pandas.DataFrame: Loaded and cleaned data with standardized column names.
     """
-    logger = logging.getLogger(__name__)
+    logging.info(f"Loading data from: {file_path}")
+
+    # Check if the file exists
+    if not os.path.exists(file_path):
+        logging.error(f"Data file not found: {file_path}")
+        sys.exit(1)
+    
+    # Determine file type based on extension (case-insensitive)
+    file_ext = os.path.splitext(file_path)[1].lower()
     try:
-        # Attempt to read the CSV with proper parsing of date columns
+        if file_ext == '.csv':
-        df = pd.read_csv(file_path, parse_dates=['time'])
+            logging.info("Detected CSV file format.")
-        logger.info(f"Successfully loaded data from {file_path}")
+            df = pd.read_csv(file_path, parse_dates=['time'])
+        elif file_ext == '.json':
+            logging.info("Detected JSON file format.")
+            # For JSON files, we assume a records-oriented format.
+            df = pd.read_json(file_path, convert_dates=['time'])
+        else:
+            logging.error("Unsupported file format. Only CSV and JSON are supported.")
+            sys.exit(1)
     except FileNotFoundError:
-        logger.error(f"Data file not found: {file_path}")
+        logging.error(f"File not found: {file_path}")
-        raise
+        sys.exit(1)
     except pd.errors.ParserError as e:
-        logger.error(f"Error parsing the CSV file: {e}")
+        logging.error(f"Error parsing file: {e}")
-        raise
+        sys.exit(1)
     except Exception as e:
-        logger.error(f"Unexpected error loading data: {e}")
+        logging.error(f"Unexpected error: {e}")
-        raise
+        sys.exit(1)
     
-    # Standardize column names (e.g., time, open, high, low, close, volume)
+    # Standardize column names. Adjust this mapping if your JSON/CSV keys differ.
-    expected_cols = ['time', 'open', 'high', 'low', 'close', 'volume']
-    df.columns = [col.strip().lower() for col in df.columns]
-    if not all(col in df.columns for col in expected_cols):
-        logger.warning("Input data does not contain all expected columns. Attempting to map columns.")
-    # Rename columns if necessary (this can be extended based on the actual CSV structure)
     rename_mapping = {
-        'time': 'time',
+        'time': 'Date',
-        'open': 'open',
+        'open': 'Open',
-        'high': 'high',
+        'high': 'High',
-        'low': 'low',
+        'low': 'Low',
-        'close': 'close',
+        'close': 'Close',
-        'volume': 'volume'
+        'volume': 'Volume'
     }
-    df = df.rename(columns=rename_mapping)
+    df.rename(columns=rename_mapping, inplace=True)
     
-    # Sort data chronologically and reset index
+    logging.info(f"Data columns after renaming: {df.columns.tolist()}")
-    df.sort_values(by='time', inplace=True)
+    df.sort_values('Date', inplace=True)
     df.reset_index(drop=True, inplace=True)
-    
+    logging.info("Data loaded and sorted successfully.")
-    # Handle missing values by forward filling
-    df.fillna(method='ffill', inplace=True)
     
     return df