Upload E-Commerce Product Intelligence Dashboard

app.py

@@ -11,17 +11,17 @@ logger = logging.getLogger(__name__)
 
 app = FastAPI(title="E-Commerce Product Intelligence Platform")
 
-# ==================== Load data (local parquet) ====================
-LOCAL_PARQUET_PATH = Path("data/ecommerce_products.parquet")
+# ==================== Load data (local CSV) ====================
+LOCAL_CSV_PATH = Path("data/ecommerce_products.csv")
 
 
 def load_data():
-    """Load parquet từ local."""
-    if not LOCAL_PARQUET_PATH.exists():
-        raise FileNotFoundError(f"Parquet not found: {LOCAL_PARQUET_PATH}")
+    """Load CSV từ local."""
+    if not LOCAL_CSV_PATH.exists():
+        raise FileNotFoundError(f"CSV not found: {LOCAL_CSV_PATH}")
 
-    logger.info(f"Loading parquet from: {LOCAL_PARQUET_PATH}")
-    return pd.read_parquet(LOCAL_PARQUET_PATH)
+    logger.info(f"Loading CSV from: {LOCAL_CSV_PATH}")
+    return pd.read_csv(LOCAL_CSV_PATH)
 
 
 # ==================== API Routes ====================

backend/scraper.py

@@ -16,7 +16,7 @@ logger = logging.getLogger(__name__)
 
 DATASET_SLUG = "anujsaha0123456789/e-commerce-product-intelligence-dataset"
 TEMP_DIR = Path("data/temp_kaggle")
-OUTPUT_PARQUET = Path("data/ecommerce_products.parquet")
+OUTPUT_CSV = Path("data/ecommerce_products.csv")
 
 os.makedirs("data", exist_ok=True)
 
@@ -59,19 +59,19 @@ def load_and_concatenate(csv_files):
     return pd.concat(dfs, ignore_index=True)
 
 
-def save_parquet(df: pd.DataFrame):
-    """Save to Parquet."""
-    df.to_parquet(OUTPUT_PARQUET, index=False)
-    logger.info(f"Saved to: {OUTPUT_PARQUET}")
+def save_csv(df: pd.DataFrame):
+    """Save to CSV."""
+    df.to_csv(OUTPUT_CSV, index=False)
+    logger.info(f"Saved to: {OUTPUT_CSV}")
 
 
 def run_scraper():
-    """Full pipeline: download Kaggle → save parquet."""
+    """Full pipeline: download Kaggle → save CSV."""
     try:
         download_dataset()
         csv_files = find_csv_files(TEMP_DIR)
         df = load_and_concatenate(csv_files)
-        save_parquet(df)
+        save_csv(df)
     finally:
         shutil.rmtree(TEMP_DIR, ignore_errors=True)
 

requirements.txt

@@ -1,4 +1,5 @@
 fastapi==0.109.2
 uvicorn
 pandas
-kaggle
+kaggle
+pyarrow