Updated app.py to use the RetailRocket-Recommender-Data in huggingface datasets

scripts/app.py

@@ -3,8 +3,12 @@ import torch
 import numpy as np
 import pandas as pd
 from datetime import datetime, timedelta
+import os
+from huggingface_hub import hf_hub_download
+
+# Import from your project's modules
 from models import SASRec
-from data_prepare import SASRecDataset, SASRecDataModule, prepare_data
+from data_prepare import SASRecDataModule, prepare_data
 from utils import load_item_properties, load_category_tree, get_popular_items
 
 # --- Global variables to hold loaded artifacts ---
@@ -16,29 +20,49 @@ CATEGORY_PARENT_MAP = None
 POPULAR_ITEMS = None
 
 # --- Data Loading and Preparation Functions ---
-
 def load_artifacts():
     """
-    Loads all necessary artifacts (model, data, mappings) into global variables.
+    Downloads data from Hugging Face Hub, then loads all necessary artifacts 
+    (model, data, mappings) into global variables.
     This function is called only once when the app starts.
     """
     global MODEL, DATAMODULE, ITEM_CATEGORY_MAP, CATEGORY_PARENT_MAP, POPULAR_ITEMS
     
     print("--- Loading all artifacts for the Gradio app ---")
     
-    # HF-FRIENDLY: Path is relative, assuming the checkpoint is in the root of the Space repo.
+    # Configuration
     CHECKPOINT_PATH = "checkpoints/sasrec-epoch=06-val_hitrate@10=0.3629.ckpt"
     DATA_FOLDER = "data/"
+    DATA_REPO_ID = "Deathshot78/RetailRocket-Recommender-Data"
+
+    # --- Download Data from Hugging Face Hub ---
+    print(f"Downloading data from Hugging Face Hub repo: {DATA_REPO_ID}")
+    os.makedirs(DATA_FOLDER, exist_ok=True)
+    
+    files_to_download = [
+        "events.csv", "item_properties_part1.csv", 
+        "item_properties_part2.csv", "category_tree.csv"
+    ]
+    
+    for filename in files_to_download:
+        hf_hub_download(
+            repo_id=DATA_REPO_ID,
+            filename=f"data/{filename}", # Path within the dataset repo
+            local_dir=".",              # Download to the root of the Space
+            repo_type="dataset"
+        )
+    print("All data files downloaded successfully.")
+    # --- End of Download Logic ---
 
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     print(f"Using device: {device}")
-
+    
     print(f"Loading model from checkpoint: {CHECKPOINT_PATH}...")
     MODEL = SASRec.load_from_checkpoint(CHECKPOINT_PATH)
     MODEL.to(device)
     MODEL.eval()
 
-    print("Preparing data...")
+    print("Preparing data from downloaded files...")
     train_set, validation_set, test_set = prepare_data(data_folder=DATA_FOLDER)
     
     DATAMODULE = SASRecDataModule(train_set, validation_set, test_set)
@@ -156,7 +180,7 @@ if __name__ == "__main__":
             inputs=visitor_id_input,
             outputs=[history_output, recs_output, status_message]
         )
-
+    
     # For local testing, this creates a shareable link.
     # On Hugging Face Spaces, this is not strictly necessary but doesn't hurt.
     iface.launch(share=True)