kaggle_train.py

@@ -33,7 +33,7 @@ Usage
 # First time — creates the Kaggle dataset and notebook from scratch
 python kaggle_train.py \
     --dataset_dir   crops_dataset \
-    --notebook      2_product-classifier.ipynb \
+    --notebook      train_classifier_kaggle.ipynb \
     --dataset_name  my-product-crops \
     --kernel_name   product-classifier-train \
     --output_dir    runs/classify
@@ -41,16 +41,16 @@ python kaggle_train.py \
 # Subsequent runs — detects existing dataset/kernel and updates them
 python kaggle_train.py \
     --dataset_dir   crops_dataset \
-    --notebook      2_product-classifier.ipynb \
+    --notebook      train_classifier_kaggle.ipynb \
     --dataset_name  my-product-crops \
     --kernel_name   product-classifier-train
 
 Arguments
 ---------
 --dataset_dir   Local crops_dataset/ folder to upload      (default: crops_dataset)
---notebook      Kaggle notebook .ipynb file                 (default: 2_product-classifier.ipynb)
---dataset_name  Kaggle dataset slug (lowercase, hyphens)   (default: product-dataset)
---kernel_name   Kaggle kernel slug  (lowercase, hyphens)   (default: product-predection)
+--notebook      Kaggle notebook .ipynb file                 (default: train_classifier_kaggle.ipynb)
+--dataset_name  Kaggle dataset slug (lowercase, hyphens)   (default: product-crops)
+--kernel_name   Kaggle kernel slug  (lowercase, hyphens)   (default: product-classifier)
 --output_dir    Where to save downloaded weights            (default: runs/classify)
 --poll_interval Seconds between status checks              (default: 30)
 --timeout       Max minutes to wait for kernel             (default: 180)
@@ -79,10 +79,10 @@ def parse_args():
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
     p.add_argument("--dataset_dir",   default="crops_dataset")
-    p.add_argument("--notebook",      default="2_product-classifier.ipynb")
-    p.add_argument("--dataset_name",  default="product-dataset",
+    p.add_argument("--notebook",      default="train_classifier_kaggle.ipynb")
+    p.add_argument("--dataset_name",  default="product-crops",
                    help="Kaggle dataset slug — lowercase, hyphens, no spaces")
-    p.add_argument("--kernel_name",   default="product-predection",
+    p.add_argument("--kernel_name",   default="product-classifier",
                    help="Kaggle kernel slug — lowercase, hyphens, no spaces")
     p.add_argument("--output_dir",    default="runs/classify")
     p.add_argument("--poll_interval", type=int, default=30,
@@ -132,7 +132,6 @@ def _detect_auth_method() -> str:
     if os.getenv("KAGGLE_USERNAME") and os.getenv("KAGGLE_KEY"):
         return "env_legacy"
     if _ACCESS_TOKEN_PATH.exists():
-        #print(f"this is the PATH:  {_ACCESS_TOKEN_PATH}")
         return "access_token"
     if _KAGGLE_JSON_PATH.exists():
         return "kaggle_json"
@@ -321,7 +320,7 @@ def patch_notebook(notebook_path: Path, dataset_ref: str,
         DATA_DIR = Path("/kaggle/input/your-dataset-name")
     We replace the path to match the actual uploaded dataset slug.
     """
-    nb = json.loads(notebook_path.read_text(encoding="utf-8"))
+    nb = json.loads(notebook_path.read_text())
 
     # Extract the dataset slug from "username/slug" → "slug"
     ds_slug = dataset_ref.split("/")[-1]
@@ -352,7 +351,7 @@ def patch_notebook(notebook_path: Path, dataset_ref: str,
         log("⚠ DATA_DIR line not found in notebook — using notebook as-is", "⚠")
 
     out_path = tmp_dir / notebook_path.name
-    out_path.write_text(json.dumps(nb, indent=1), encoding="utf-8")
+    out_path.write_text(json.dumps(nb, indent=1))
     return out_path
 
 
@@ -390,15 +389,11 @@ def push_kernel(api, username: str, kernel_name: str, notebook_path: Path,
         "competition_sources": [],
         "kernel_sources":      [],
         "model_sources":       [],
-        "machine_shape":       "t4" if gpu else None,
     }
     (kernel_dir / "kernel-metadata.json").write_text(json.dumps(meta, indent=2))
 
     log(f"Pushing kernel to Kaggle: {ref}  (GPU={'yes' if gpu else 'no'})", "🚀")
-    try:
-        api.kernels_push(str(kernel_dir), timeout=None, acc="t4" if gpu else None)
-    except TypeError:
-        api.kernels_push(str(kernel_dir))
+    api.kernels_push(str(kernel_dir))
     log(f"Kernel pushed — run started: https://www.kaggle.com/code/{ref}", "✓")
     return ref
 
@@ -410,11 +405,12 @@ def poll_kernel(api, kernel_ref: str, poll_interval: int, timeout_minutes: int)
     Poll the kernel until it reaches a terminal status.
     Returns True if successful, False if failed or timed out.
     """
+    username, slug = kernel_ref.split("/")
     deadline = time.time() + timeout_minutes * 60
     attempt  = 0
 
-    TERMINAL   = {"complete", "error", "cancelled", "cancel_acknowledged"}
-    RUNNING    = {"running", "queued", "initializing", "pending"}
+    TERMINAL   = {"complete", "error", "cancelled"}
+    RUNNING    = {"running", "queued"}
 
     log(f"Polling kernel status every {poll_interval}s "
         f"(timeout {timeout_minutes} min) …", "⏳")
@@ -422,27 +418,16 @@ def poll_kernel(api, kernel_ref: str, poll_interval: int, timeout_minutes: int)
     while time.time() < deadline:
         attempt += 1
         try:
-            # kernels_status takes the full kernel ref "username/slug"
-            status_obj = api.kernels_status(kernel_ref)
-            # Extract status from the response object
-            raw_status = getattr(status_obj, "status", None)
-            if raw_status is not None:
-                if hasattr(raw_status, 'name'):
-                    status = raw_status.name.lower()
-                else:
-                    status = str(raw_status).lower()
-            else:
-                status = str(status_obj).lower()
-            
-            # Clean up enum prefixes
-            status = status.replace("kernelworkerstatus.", "")
+            status_obj = api.kernel_status(username, slug)
+            # The API returns an object with a .status attribute
+            status = getattr(status_obj, "status", str(status_obj)).lower()
         except Exception as e:
             log(f"Poll error (will retry): {e}", "⚠")
             time.sleep(poll_interval)
             continue
 
-        elapsed_min = (time.time() + timeout_minutes * 60 - deadline) / 60
-        print(f"  [{attempt:>3}]  status={status:<20}  elapsed={elapsed_min:.1f} min",
+        elapsed_min = (time.time() + timeout_minutes * 60 - deadline) / 60 + timeout_minutes
+        print(f"  [{attempt:>3}]  status={status:<12}  elapsed={elapsed_min:.1f} min",
               end="\r", flush=True)
 
         if status == "complete":
@@ -456,7 +441,7 @@ def poll_kernel(api, kernel_ref: str, poll_interval: int, timeout_minutes: int)
                 f"https://www.kaggle.com/code/{kernel_ref}", "✗")
             return False
 
-        if "cancel" in status:
+        if status == "cancelled":
             print()
             log("Kernel was cancelled.", "✗")
             return False
@@ -530,8 +515,8 @@ def main():
 
     # Import here so missing kaggle package gives a clean error
     try:
-        from kaggle.api.kaggle_api_extended import KaggleApi
-        api = KaggleApi()
+        from kaggle.api.kaggle_api_extended import KaggleApiExtended
+        api = KaggleApiExtended()
         api.authenticate()
     except ImportError:
         fatal("kaggle package not installed.\n  Run: pip install kaggle")

run_prod.py

@@ -1,12 +0,0 @@
-"""
-pip install hypercorn
-"""
-
-import asyncio
-from hypercorn.config import Config
-from hypercorn.asyncio import serve
-from api_server import app
-
-config = Config()
-config.bind = ["0.0.0.0:2000"]
-asyncio.run(serve(app, config))