nextrec 0.4.7__py3-none-any.whl → 0.4.9__py3-none-any.whl

nextrec/cli.py

@@ -14,12 +14,14 @@ Examples:
     nextrec --mode=predict --predict_config=nextrec_cli_preset/predict_config.yaml
 
 Date: create on 06/12/2025
+Checkpoint: edit on 18/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
 import argparse
 import logging
 import pickle
+import sys
 import time
 from pathlib import Path
 from typing import Any, Dict, List
@@ -27,6 +29,7 @@ from typing import Any, Dict, List
 import pandas as pd
 
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.loggers import setup_logger
 from nextrec.data.data_utils import split_dict_random
 from nextrec.data.dataloader import RecDataLoader
 from nextrec.data.preprocessor import DataProcessor
@@ -37,14 +40,14 @@ from nextrec.utils.config import (
     resolve_path,
     select_features,
 )
-from nextrec.utils.feature import normalize_to_list
-from nextrec.utils.file import (
+from nextrec.utils.console import get_nextrec_version
+from nextrec.utils.data import (
     iter_file_chunks,
     read_table,
     read_yaml,
     resolve_file_paths,
 )
-from nextrec.basic.loggers import setup_logger
+from nextrec.utils.feature import normalize_to_list
 
 logger = logging.getLogger(__name__)
 
@@ -71,6 +74,9 @@ def train_model(train_config_path: str) -> None:
     artifact_root = Path(session_cfg.get("artifact_root", "nextrec_logs"))
     session_dir = artifact_root / session_id
     setup_logger(session_id=session_id)
+    logger.info(
+        f"[NextRec CLI] Training start | version={get_nextrec_version()} | session_id={session_id} | artifacts={session_dir.resolve()}"
+    )
 
     processor_path = session_dir / "processor.pkl"
     processor_path = Path(processor_path)
@@ -324,6 +330,9 @@ def predict_model(predict_config_path: str) -> None:
     artifact_root = Path(session_cfg.get("artifact_root", "nextrec_logs"))
     session_dir = Path(cfg.get("checkpoint_path") or (artifact_root / session_id))
     setup_logger(session_id=session_id)
+    logger.info(
+        f"[NextRec CLI] Predict start | version={get_nextrec_version()} | session_id={session_id} | checkpoint={session_dir.resolve()}"
+    )
 
     processor_path = Path(session_dir / "processor.pkl")
     if not processor_path.exists():
@@ -454,6 +463,13 @@ def predict_model(predict_config_path: str) -> None:
 
 def main() -> None:
     """Parse CLI arguments and dispatch to train or predict mode."""
+
+    root = logging.getLogger()
+    if not root.handlers:
+        handler = logging.StreamHandler(sys.stdout)
+        handler.setFormatter(logging.Formatter("%(message)s"))
+        root.addHandler(handler)
+
     parser = argparse.ArgumentParser(
         description="NextRec: Training and Prediction Pipeline",
         formatter_class=argparse.RawDescriptionHelpFormatter,
@@ -466,16 +482,21 @@ Examples:
   nextrec --mode=predict --predict_config=configs/predict_config.yaml
         """,
     )
+
     parser.add_argument(
         "--mode",
         choices=["train", "predict"],
-        required=True,
         help="Running mode: train or predict",
     )
     parser.add_argument("--train_config", help="Training configuration file path")
     parser.add_argument("--predict_config", help="Prediction configuration file path")
     args = parser.parse_args()
 
+    logger.info(get_nextrec_version())
+
+    if not args.mode:
+        parser.error("[NextRec CLI Error] --mode is required (train|predict)")
+
     if args.mode == "train":
         config_path = args.train_config
         if not config_path:

nextrec/data/__init__.py

@@ -1,29 +1,26 @@
-from nextrec.data.batch_utils import collate_fn, batch_to_dict, stack_section
+from nextrec.basic.features import FeatureSet
+from nextrec.data import data_utils
+from nextrec.data.batch_utils import batch_to_dict, collate_fn, stack_section
 from nextrec.data.data_processing import (
-    get_column_data,
-    split_dict_random,
     build_eval_candidates,
+    get_column_data,
     get_user_ids,
+    split_dict_random,
 )
-
-from nextrec.utils.file import (
-    resolve_file_paths,
-    iter_file_chunks,
-    read_table,
-    load_dataframes,
-    default_output_dir,
-)
-
 from nextrec.data.dataloader import (
-    TensorDictDataset,
     FileDataset,
     RecDataLoader,
+    TensorDictDataset,
     build_tensors_from_data,
 )
-
 from nextrec.data.preprocessor import DataProcessor
-from nextrec.basic.features import FeatureSet
-from nextrec.data import data_utils
+from nextrec.utils.data import (
+    default_output_dir,
+    iter_file_chunks,
+    load_dataframes,
+    read_table,
+    resolve_file_paths,
+)
 
 __all__ = [
     # Batch utilities

nextrec/data/batch_utils.py

@@ -5,10 +5,11 @@ Date: create on 03/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
-import torch
-import numpy as np
 from typing import Any, Mapping
 
+import numpy as np
+import torch
+
 
 def stack_section(batch: list[dict], section: str):
     entries = [item.get(section) for item in batch if item.get(section) is not None]

nextrec/data/data_processing.py

@@ -2,13 +2,16 @@
 Data processing utilities for NextRec
 
 Date: create on 03/12/2025
+Checkpoint: edit on 19/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
-import torch
+import hashlib
+from typing import Any
+
 import numpy as np
 import pandas as pd
-from typing import Any
+import torch
 
 
 def get_column_data(data: dict | pd.DataFrame, name: str):
@@ -166,3 +169,8 @@ def get_user_ids(
             return arr.reshape(arr.shape[0])
 
     return None
+
+
+def hash_md5_mod(value: str, hash_size: int) -> int:
+    digest = hashlib.md5(value.encode("utf-8")).digest()
+    return int.from_bytes(digest, byteorder="big", signed=False) % hash_size

nextrec/data/data_utils.py

@@ -1,30 +1,25 @@
 """
-Data processing utilities for NextRec (Refactored)
-
-This module now re-exports functions from specialized submodules:
-- batch_utils: collate_fn, batch_to_dict
-- data_processing: get_column_data, split_dict_random, build_eval_candidates, get_user_ids
-- nextrec.utils.file_utils: resolve_file_paths, iter_file_chunks, read_table, load_dataframes, default_output_dir
+Data processing utilities for NextRec
 
 Date: create on 27/10/2025
-Last update: 03/12/2025 (refactored)
+Last update: 19/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
 # Import from new organized modules
-from nextrec.data.batch_utils import collate_fn, batch_to_dict, stack_section
+from nextrec.data.batch_utils import batch_to_dict, collate_fn, stack_section
 from nextrec.data.data_processing import (
-    get_column_data,
-    split_dict_random,
     build_eval_candidates,
+    get_column_data,
     get_user_ids,
+    split_dict_random,
 )
-from nextrec.utils.file import (
-    resolve_file_paths,
+from nextrec.utils.data import (
+    default_output_dir,
     iter_file_chunks,
-    read_table,
     load_dataframes,
-    default_output_dir,
+    read_table,
+    resolve_file_paths,
 )
 
 __all__ = [

nextrec/data/dataloader.py

@@ -2,33 +2,32 @@
 Dataloader definitions
 
 Date: create on 27/10/2025
-Checkpoint: edit on 02/12/2025
+Checkpoint: edit on 19/12/2025
 Author: Yang Zhou,zyaztec@gmail.com
 """
 
-import os
-import torch
 import logging
+import os
+from pathlib import Path
+from typing import cast
+
 import numpy as np
 import pandas as pd
 import pyarrow.parquet as pq
-
-from pathlib import Path
-from typing import cast
+import torch
+from torch.utils.data import DataLoader, Dataset, IterableDataset
 
 from nextrec.basic.features import (
     DenseFeature,
-    SparseFeature,
-    SequenceFeature,
     FeatureSet,
+    SequenceFeature,
+    SparseFeature,
 )
-from nextrec.data.preprocessor import DataProcessor
-from torch.utils.data import DataLoader, Dataset, IterableDataset
-
-from nextrec.utils.tensor import to_tensor
-from nextrec.utils.file import resolve_file_paths, read_table
 from nextrec.data.batch_utils import collate_fn
 from nextrec.data.data_processing import get_column_data
+from nextrec.data.preprocessor import DataProcessor
+from nextrec.utils.data import read_table, resolve_file_paths
+from nextrec.utils.torch_utils import to_tensor
 
 
 class TensorDictDataset(Dataset):