Upload E-Commerce Product Intelligence Dashboard

app.py

@@ -18,8 +18,15 @@ def load_data():
     if not LOCAL_CSV_PATH.exists():
         raise FileNotFoundError(f"CSV not found: {LOCAL_CSV_PATH}")
 
-    logger.info(f"Loading CSV from: {LOCAL_CSV_PATH}")
-    return pd.read_csv(LOCAL_CSV_PATH)
+    file_size = LOCAL_CSV_PATH.stat().st_size
+    logger.info(f"Loading CSV from: {LOCAL_CSV_PATH} (size: {file_size} bytes)")
+
+    if file_size == 0:
+        raise ValueError(f"CSV file is empty: {LOCAL_CSV_PATH}")
+
+    df = pd.read_csv(LOCAL_CSV_PATH)
+    logger.info(f"Loaded {len(df)} rows, columns: {list(df.columns)}")
+    return df
 
 
 @app.get("/")
@@ -36,18 +43,24 @@ def get_data():
 @app.get("/stats/categories")
 def stats_categories():
     df = load_data()
+    if "category" not in df.columns:
+        raise ValueError("Missing 'category' column")
     return df["category"].value_counts().head(10).to_dict()
 
 
 @app.get("/stats/brands")
 def stats_brands():
     df = load_data()
+    if "brand" not in df.columns:
+        raise ValueError("Missing 'brand' column")
     return df["brand"].value_counts().head(10).to_dict()
 
 
 @app.get("/stats/price")
 def stats_price():
     df = load_data()
+    if "category" not in df.columns or "price" not in df.columns:
+        raise ValueError("Missing 'category' or 'price' column")
     return df.groupby("category")["price"].agg(["mean", "median", "min", "max", "count"]).reset_index().to_dict(
         "records")
 
@@ -55,6 +68,8 @@ def stats_price():
 @app.get("/stats/rating")
 def stats_rating():
     df = load_data()
+    if "category" not in df.columns or "rating" not in df.columns:
+        raise ValueError("Missing 'category' or 'rating' column")
     return df.groupby("category")["rating"].agg(["mean", "median", "min", "max", "count"]).reset_index().to_dict(
         "records")
 
@@ -64,10 +79,10 @@ def insights():
     df = load_data()
     return JSONResponse(content={
         "total_products": len(df),
-        "categories": df["category"].nunique(),
-        "brands": df["brand"].nunique(),
-        "avg_price": df["price"].mean(),
-        "avg_rating": df["rating"].mean(),
+        "categories": df["category"].nunique() if "category" in df.columns else 0,
+        "brands": df["brand"].nunique() if "brand" in df.columns else 0,
+        "avg_price": df["price"].mean() if "price" in df.columns else 0,
+        "avg_rating": df["rating"].mean() if "rating" in df.columns else 0,
     })
 
 
@@ -75,18 +90,30 @@ def insights():
 def search(query: str):
     df = load_data()
     q = query.lower()
-    mask = (
-            df["title"].str.contains(q, case=False, na=False) |
-            df["description"].str.contains(q, case=False, na=False)
-    )
+
+    # Find text columns
+    text_cols = df.select_dtypes(include=["object"]).columns.tolist()
+
+    mask = pd.Series([False] * len(df), index=df.index)
+    for col in text_cols[:5]:  # Check first 5 text columns
+        try:
+            mask |= df[col].str.contains(q, case=False, na=False)
+        except:
+            pass
+
     return df[mask].head(100).to_dict("records")
 
 
 @app.get("/recommend")
 def recommend(category: str):
     df = load_data()
+    if "category" not in df.columns:
+        raise ValueError("Missing 'category' column")
+
     subset = df[df["category"] == category]
-    return subset.sort_values("rating", ascending=False).head(10).to_dict("records")
+    if "rating" in df.columns:
+        return subset.sort_values("rating", ascending=False).head(10).to_dict("records")
+    return subset.head(10).to_dict("records")
 
 
 @app.post("/run-scraper")