API

app.py

@@ -1,5 +1,5 @@
 #Fast APi Packages
-from fastapi import FastAPI,File, HTTPException
+from fastapi import FastAPI, File, HTTPException
 from pydantic import BaseModel
 import json
 from typing import List, Dict, Any
@@ -11,7 +11,8 @@ from datetime import datetime
 import warnings
 import os
 import logging
-import pathlib
+import requests
+import io
 
 warnings.filterwarnings('ignore')
 
@@ -21,43 +22,21 @@ logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-# Try multiple possible paths for the Excel file
-possible_paths = [
-    'datasetsample.xlsx',  # Same directory
-    './datasetsample.xlsx',  # Explicit current directory
-    '../datasetsample.xlsx',  # Parent directory
-    '/home/user/app/datasetsample.xlsx',  # Hugging Face default path
-    os.path.join(os.path.dirname(os.path.abspath(__file__)), 'datasetsample.xlsx'),  # Absolute path
-]
-
-logger.info("Checking directory contents:")
-current_dir = os.path.dirname(os.path.abspath(__file__))
-logger.info(f"Current directory: {current_dir}")
-try:
-    for item in os.listdir(current_dir):
-        logger.info(f"Found file: {item}")
-except Exception as e:
-    logger.error(f"Error listing directory: {str(e)}")
-
-# Try each possible path
-purchase_history = None
-for path in possible_paths:
-    try:
-        logger.info(f"Attempting to load Excel file from: {path}")
-        purchase_history = pd.read_excel(path, sheet_name='Transaction History', 
-                                       parse_dates=['Purchase_Date'])
-        logger.info(f"Successfully loaded Excel file from: {path}")
-        break
-    except Exception as e:
-        logger.warning(f"Failed to load from {path}: {str(e)}")
-        continue
-
-if purchase_history is None:
-    error_msg = "Failed to load Excel file from any location"
-    logger.error(error_msg)
-    raise FileNotFoundError(error_msg)
+# URL of the Excel file
+EXCEL_URL = "https://huggingface.co/spaces/Vaibhav84/RecommendationAPI/resolve/main/DataSetSample.xlsx"
 
 try:
+    # Download the file from URL
+    logger.info(f"Attempting to download Excel file from: {EXCEL_URL}")
+    response = requests.get(EXCEL_URL)
+    response.raise_for_status()  # Raises an HTTPError if the status is 4xx, 5xx
+    
+    # Read the Excel file from the downloaded content
+    excel_content = io.BytesIO(response.content)
+    purchase_history = pd.read_excel(excel_content, sheet_name='Transaction History', 
+                                   parse_dates=['Purchase_Date'])
+    logger.info("Successfully downloaded and loaded Excel file")
+    
     # Process the data
     purchase_history['Customer_Id'] = purchase_history['Customer_Id'].astype(str)
     product_categories = purchase_history[['Product_Id', 'Category']].drop_duplicates().set_index('Product_Id')['Category'].to_dict()
@@ -68,7 +47,7 @@ try:
     logger.info("Data processing completed successfully")
     
 except Exception as e:
-    logger.error(f"Error processing data: {str(e)}")
+    logger.error(f"Error downloading or processing data: {str(e)}")
     raise
 
 def get_customer_items_and_recommendations(user_id: str, n: int = 5) -> tuple[List[Dict], List[Dict]]:
@@ -148,24 +127,14 @@ async def get_recommendations(customer_id: str, n: int = 5):
         logger.error(f"Error processing request for customer {customer_id}: {str(e)}")
         raise HTTPException(status_code=404, detail=f"Error processing customer ID: {customer_id}. {str(e)}")
 
-# Add a health check endpoint that includes file system information
 @app.get("/health")
 async def health_check():
     """
     Health check endpoint that returns system information
     """
-    try:
-        current_dir = os.path.dirname(os.path.abspath(__file__))
-        files = os.listdir(current_dir)
-        
-        return {
-            "status": "healthy",
-            "current_directory": current_dir,
-            "files_found": files,
-            "data_loaded": purchase_history is not None
-        }
-    except Exception as e:
-        return {
-            "status": "unhealthy",
-            "error": str(e)
-        }
+    return {
+        "status": "healthy",
+        "data_loaded": purchase_history is not None,
+        "number_of_customers": len(purchase_counts.index) if purchase_history is not None else 0,
+        "number_of_products": len(purchase_counts.columns) if purchase_history is not None else 0
+    }