nextrec 0.5.1__py3-none-any.whl → 0.5.2__py3-none-any.whl

nextrec/models/tree_base/base.py

@@ -28,7 +28,6 @@ from nextrec.basic.session import create_session, get_save_path
 from nextrec.data.dataloader import RecDataLoader
 from nextrec.data.data_processing import get_column_data
 from nextrec.utils.console import display_metrics_table
-from nextrec.utils.data import FILE_FORMAT_CONFIG, check_streaming_support
 from nextrec.utils.torch_utils import to_list
 from nextrec.utils.torch_utils import to_numpy
 
@@ -454,7 +453,7 @@ class TreeBaseModel(FeatureSet):
         stream_chunk_size: int = 10000,
         num_workers: int = 0,
     ) -> pd.DataFrame | np.ndarray | Path | None:
-        del batch_size, num_workers  # not used for tree models
+        del batch_size  # not used for tree models
 
         if self.model is None:
             raise ValueError(f"[{self.model_name}-predict Error] Model is not loaded.")
@@ -472,6 +471,7 @@ class TreeBaseModel(FeatureSet):
                 include_ids=include_ids,
                 stream_chunk_size=stream_chunk_size,
                 id_columns=predict_id_columns,
+                num_workers=num_workers,
             )
 
         if isinstance(data, (str, os.PathLike)):
@@ -508,12 +508,13 @@ class TreeBaseModel(FeatureSet):
             output = pred_df if return_dataframe else y_pred
 
         if save_path is not None:
-            suffix = FILE_FORMAT_CONFIG[save_format]["extension"][0]
+            if save_format not in {"csv", "parquet"}:
+                raise ValueError(f"Unsupported save format: {save_format}")
             target_path = get_save_path(
                 path=save_path,
                 default_dir=self.session.predictions_dir,
                 default_name="predictions",
-                suffix=suffix,
+                suffix=f".{save_format}",
                 add_timestamp=True if save_path is None else False,
             )
             if isinstance(output, pd.DataFrame):
@@ -527,12 +528,6 @@ class TreeBaseModel(FeatureSet):
                 df_to_save.to_csv(target_path, index=False)
             elif save_format == "parquet":
                 df_to_save.to_parquet(target_path, index=False)
-            elif save_format == "feather":
-                df_to_save.to_feather(target_path)
-            elif save_format == "excel":
-                df_to_save.to_excel(target_path, index=False)
-            elif save_format == "hdf5":
-                df_to_save.to_hdf(target_path, key="predictions", mode="w")
             else:
                 raise ValueError(f"Unsupported save format: {save_format}")
             logging.info(f"Predictions saved to: {target_path}")
@@ -546,6 +541,7 @@ class TreeBaseModel(FeatureSet):
         include_ids: bool,
         stream_chunk_size: int,
         id_columns: list[str] | None,
+        num_workers: int = 0,
     ) -> Path:
         if isinstance(data, (str, os.PathLike)):
             rec_loader = RecDataLoader(
@@ -561,25 +557,27 @@ class TreeBaseModel(FeatureSet):
                 shuffle=False,
                 streaming=True,
                 chunk_size=stream_chunk_size,
+                num_workers=num_workers,
             )
         else:
             data_loader = data
 
-        if not check_streaming_support(save_format):
+        if save_format.lower() not in {"csv", "parquet"}:
             logging.warning(
                 f"[{self.model_name}-predict Warning] Format '{save_format}' does not support streaming writes."
             )
 
-        suffix = FILE_FORMAT_CONFIG[save_format]["extension"][0]
+        if save_format not in {"csv", "parquet"}:
+            raise ValueError(f"Unsupported save format: {save_format}")
         target_path = get_save_path(
             path=save_path,
             default_dir=self.session.predictions_dir,
             default_name="predictions",
-            suffix=suffix,
+            suffix=f".{save_format}",
             add_timestamp=True if save_path is None else False,
         )
 
-        header_written = False
+        header_written = target_path.exists()
         parquet_writer = None
         collected_frames: list[pd.DataFrame] = []
         id_column = id_columns[0] if id_columns else None
@@ -595,6 +593,7 @@ class TreeBaseModel(FeatureSet):
                 pred_df.to_csv(
                     target_path, mode="a", header=not header_written, index=False
                 )
+                header_written = True
             elif save_format == "parquet":
                 try:
                     import pyarrow as pa
@@ -609,19 +608,11 @@ class TreeBaseModel(FeatureSet):
                 parquet_writer.write_table(table)
             else:
                 collected_frames.append(pred_df)
-            header_written = True
         if parquet_writer is not None:
             parquet_writer.close()
         if collected_frames:
             combined_df = pd.concat(collected_frames, ignore_index=True)
-            if save_format == "feather":
-                combined_df.to_feather(target_path)
-            elif save_format == "excel":
-                combined_df.to_excel(target_path, index=False)
-            elif save_format == "hdf5":
-                combined_df.to_hdf(target_path, key="predictions", mode="w")
-            else:
-                raise ValueError(f"Unsupported save format: {save_format}")
+            raise ValueError(f"Unsupported save format: {save_format}")
         return target_path
 
     def save_model(self, save_path: str | os.PathLike | None = None) -> Path:

nextrec/utils/__init__.py

@@ -1,119 +0,0 @@
-"""
-Utilities package for NextRec
-
-Date: create on 13/11/2025
-Last update: 19/12/2025
-Author: Yang Zhou, zyaztec@gmail.com
-"""
-
-from . import console, data, embedding, loss, torch_utils
-from .config import (
-    build_feature_objects,
-    build_model_instance,
-    extract_feature_groups,
-    load_model_class,
-    register_processor_features,
-    resolve_path,
-    safe_value,
-    select_features,
-)
-from .console import (
-    display_metrics_table,
-    get_nextrec_version,
-    log_startup_info,
-    progress,
-)
-from .data import (
-    default_output_dir,
-    generate_distributed_ranking_data,
-    generate_match_data,
-    generate_multitask_data,
-    generate_ranking_data,
-    iter_file_chunks,
-    load_dataframes,
-    read_table,
-    read_yaml,
-    resolve_file_paths,
-)
-from .embedding import get_auto_embedding_dim
-from .torch_utils import as_float, to_list
-from .model import (
-    compute_pair_scores,
-    get_mlp_output_dim,
-    merge_features,
-)
-from .loss import normalize_task_loss
-from .torch_utils import (
-    add_distributed_sampler,
-    get_device,
-    gather_numpy,
-    get_initializer,
-    get_optimizer,
-    get_scheduler,
-    init_process_group,
-    to_tensor,
-)
-from .types import LossName, OptimizerName, SchedulerName, ActivationName
-
-__all__ = [
-    # Console utilities
-    "get_nextrec_version",
-    "log_startup_info",
-    "progress",
-    "display_metrics_table",
-    # Optimizer & Scheduler (torch utils)
-    "get_optimizer",
-    "get_scheduler",
-    # Initializer (torch utils)
-    "get_initializer",
-    # Embedding utilities
-    "get_auto_embedding_dim",
-    # Device utilities (torch utils)
-    "get_device",
-    "init_process_group",
-    "gather_numpy",
-    "add_distributed_sampler",
-    # Tensor utilities
-    "to_tensor",
-    # Data utilities
-    "resolve_file_paths",
-    "read_table",
-    "read_yaml",
-    "load_dataframes",
-    "iter_file_chunks",
-    "default_output_dir",
-    # Model utilities
-    "merge_features",
-    "get_mlp_output_dim",
-    "compute_pair_scores",
-    # Loss utilities
-    "normalize_task_loss",
-    # Feature utilities
-    "to_list",
-    "as_float",
-    # Config utilities
-    "resolve_path",
-    "safe_value",
-    "register_processor_features",
-    "build_feature_objects",
-    "extract_feature_groups",
-    "select_features",
-    "load_model_class",
-    "build_model_instance",
-    # Synthetic data utilities
-    "generate_ranking_data",
-    "generate_match_data",
-    "generate_multitask_data",
-    "generate_distributed_ranking_data",
-    # Module exports
-    "console",
-    "data",
-    "embedding",
-    "loss",
-    "torch_utils",
-    # Type aliases
-    "OptimizerName",
-    "SchedulerName",
-    "LossName",
-    "ActivationName",
-]

nextrec/utils/data.py

@@ -4,7 +4,7 @@ Data utilities for NextRec.
 This module provides file I/O helpers and synthetic data generation.
 
 Date: create on 19/12/2025
-Checkpoint: edit on 24/12/2025
+Checkpoint: edit on 29/01/2026
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
@@ -19,46 +19,6 @@ import pyarrow.parquet as pq
 import torch
 import yaml
 
-FILE_FORMAT_CONFIG = {
-    "csv": {
-        "extension": [".csv", ".txt"],
-        "streaming": True,
-    },
-    "parquet": {
-        "extension": [".parquet"],
-        "streaming": True,
-    },
-    "feather": {
-        "extension": [".feather", ".ftr"],
-        "streaming": False,
-    },
-    "excel": {
-        "extension": [".xlsx", ".xls"],
-        "streaming": False,
-    },
-    "hdf5": {
-        "extension": [".h5", ".hdf5"],
-        "streaming": False,
-    },
-}
-
-
-def get_file_format_from_extension(ext: str) -> str | None:
-    """Get file format from extension."""
-    return {
-        ext.lstrip("."): fmt
-        for fmt, config in FILE_FORMAT_CONFIG.items()
-        for ext in config["extension"]
-    }.get(ext.lower().lstrip("."))
-
-
-def check_streaming_support(file_format: str) -> bool:
-    """Check if a format supports streaming."""
-    file_format = file_format.lower()
-    if file_format not in FILE_FORMAT_CONFIG:
-        return False
-    return FILE_FORMAT_CONFIG[file_format].get("streaming", False)
-
 
 def resolve_file_paths(path: str) -> tuple[list[str], str]:
     """
@@ -70,34 +30,45 @@ def resolve_file_paths(path: str) -> tuple[list[str], str]:
     path_obj = Path(path)
 
     if path_obj.is_file():
-        file_format = get_file_format_from_extension(path_obj.suffix)
+        name = path_obj.name
+        ext = name.rsplit(".", 1)[-1].lower() if "." in name else ""
+        if ext in {"csv", "txt"}:
+            file_format = "csv"
+        elif ext == "parquet":
+            file_format = "parquet"
+        else:
+            file_format = None
         if file_format is None:
             raise ValueError(
-                f"Unsupported file extension: {path_obj.suffix}. "
-                f"Supported formats: {', '.join(FILE_FORMAT_CONFIG.keys())}"
+                f"Unsupported file extension: {path_obj.suffix}. Supported formats: csv, parquet."
             )
         return [str(path_obj)], file_format
 
     if path_obj.is_dir():
         collected_files = [p for p in path_obj.iterdir() if p.is_file()]
-        # Group files by format
-        format_groups: Dict[str, List[str]] = {}
+
+        format_groups = {}
         for file in collected_files:
-            file_format = get_file_format_from_extension(file.suffix)
+            name = file.name
+            ext = name.rsplit(".", 1)[-1].lower() if "." in name else ""
+            if ext in {"csv", "txt"}:
+                file_format = "csv"
+            elif ext == "parquet":
+                file_format = "parquet"
+            else:
+                file_format = None
             if file_format:
                 format_groups.setdefault(file_format, []).append(str(file))
 
         if len(format_groups) > 1:
             formats = ", ".join(format_groups.keys())
             raise ValueError(
-                f"Directory contains mixed file formats: {formats}. "
-                "Please keep a single format per directory."
+                f"Directory contains mixed file formats: {formats}. Please keep a single format per directory."
             )
 
         if not format_groups:
             raise ValueError(
-                f"No supported data files found in directory: {path}. "
-                f"Supported formats: {', '.join(FILE_FORMAT_CONFIG.keys())}"
+                f"No supported data files found in directory: {path}. Supported formats: csv, parquet."
             )
 
         file_type = list(format_groups.keys())[0]
@@ -111,18 +82,14 @@ def resolve_file_paths(path: str) -> tuple[list[str], str]:
 def read_table(path: str | Path, data_format: str | None = None) -> pd.DataFrame:
     data_path = Path(path)
 
-    # Determine format
     if data_format:
-        fmt = data_format.lower()
+        fmt = data_format
     elif data_path.is_dir():
         _, fmt = resolve_file_paths(str(data_path))
     else:
-        fmt = get_file_format_from_extension(data_path.suffix)
-        if fmt is None:
-            raise ValueError(
-                f"Cannot determine format for {data_path}. "
-                f"Please specify data_format parameter."
-            )
+        raise ValueError(
+            f"Cannot determine format for {data_path}. Please specify data_format parameter."
+        )
 
     if data_path.is_dir():
         file_paths, _ = resolve_file_paths(str(data_path))
@@ -133,36 +100,11 @@ def read_table(path: str | Path, data_format: str | None = None) -> pd.DataFrame
             return dataframes[0]
         return pd.concat(dataframes, ignore_index=True)
 
-    # Read based on format
-    try:
-        if fmt == "hdf5":
-            # HDF5 requires a key; use the first available key
-            with pd.HDFStore(data_path, mode="r") as store:
-                if len(store.keys()) == 0:
-                    raise ValueError(f"HDF5 file {data_path} contains no datasets")
-                return pd.read_hdf(data_path, key=store.keys()[0])
-        reader = {
-            "parquet": pd.read_parquet,
-            "csv": lambda p: pd.read_csv(p, low_memory=False),
-            "feather": pd.read_feather,
-            "excel": pd.read_excel,
-        }.get(fmt)
-        if reader:
-            return reader(data_path)
-        raise ValueError(
-            f"Unsupported format: {fmt}. "
-            f"Supported: {', '.join(FILE_FORMAT_CONFIG.keys())}"
-        )
-    except ImportError as e:
-        raise ImportError(
-            f"Format '{fmt}' requires additional dependencies. "
-            f"Install with: pip install pandas[{fmt}] or check documentation. "
-            f"Original error: {e}"
-        ) from e
-
-
-def load_dataframes(file_paths: list[str], file_type: str) -> list[pd.DataFrame]:
-    return [read_table(fp, file_type) for fp in file_paths]
+    if fmt == "parquet":
+        return pd.read_parquet(data_path)
+    if fmt == "csv":
+        return pd.read_csv(data_path, low_memory=False)
+    raise ValueError(f"Unsupported format: {fmt}.")
 
 
 def iter_file_chunks(
@@ -182,37 +124,17 @@ def iter_file_chunks(
         ValueError: If format doesn't support streaming
     """
     file_type = file_type.lower()
-    if not check_streaming_support(file_type):
+    if file_type not in {"csv", "parquet"}:
         raise ValueError(
-            f"Format '{file_type}' does not support streaming reads. "
-            "Formats with streaming support: csv, parquet"
+            f"Format '{file_type}' does not support streaming reads. Formats with streaming support: csv, parquet"
         )
 
-    try:
-        if file_type == "csv":
-            yield from pd.read_csv(file_path, chunksize=chunk_size)
-        elif file_type == "parquet":
-            parquet_file = pq.ParquetFile(file_path)
-            for batch in parquet_file.iter_batches(batch_size=chunk_size):
-                yield batch.to_pandas()
-        else:
-            raise ValueError(
-                f"Format '{file_type}' does not support streaming. "
-                f"Use read_table() to load the entire file into memory."
-            )
-    except ImportError as e:
-        raise ImportError(
-            f"Streaming format '{file_type}' requires additional dependencies. "
-            f"Install with: pip install pandas[{file_type}] pyarrow. "
-            f"Original error: {e}"
-        ) from e
-
-
-def default_output_dir(path: str) -> Path:
-    path_obj = Path(path)
-    if path_obj.is_file():
-        return path_obj.parent / f"{path_obj.stem}_preprocessed"
-    return path_obj.with_name(f"{path_obj.name}_preprocessed")
+    if file_type == "csv":
+        yield from pd.read_csv(file_path, chunksize=chunk_size)
+    elif file_type == "parquet":
+        parquet_file = pq.ParquetFile(file_path)
+        for batch in parquet_file.iter_batches(batch_size=chunk_size):
+            yield batch.to_pandas()
 
 
 def read_yaml(path: str | Path):
@@ -232,7 +154,6 @@ def generate_ranking_data(
     embedding_dim: int = 16,
     seed: int = 42,
     custom_sparse_features: Optional[Dict[str, int]] = None,
-    use_simple_names: bool = True,
 ) -> Tuple[pd.DataFrame, List, List, List]:
     """
     Generate synthetic data for ranking tasks (CTR prediction)
@@ -737,7 +658,6 @@ def generate_distributed_ranking_data(
             "category": num_categories,
             "city": num_cities,
         },
-        use_simple_names=False,
     )
 
 

nextrec/utils/model.py

@@ -2,24 +2,20 @@
 Model-related utilities for NextRec
 
 Date: create on 03/12/2025
-Checkpoint: edit on 31/12/2025
+Checkpoint: edit on 31/01/2026
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
-from collections import OrderedDict
-
 import torch
 import torch.nn as nn
 
-from nextrec.loss import (
+from nextrec.loss.listwise import (
     ApproxNDCGLoss,
-    BPRLoss,
-    HingeLoss,
     ListMLELoss,
     ListNetLoss,
     SampledSoftmaxLoss,
-    TripletLoss,
 )
+from nextrec.loss.pairwise import BPRLoss, HingeLoss, TripletLoss
 
 from nextrec.utils.types import (
     LossName,
@@ -27,13 +23,6 @@ from nextrec.utils.types import (
 )
 
 
-def merge_features(primary, secondary) -> list:
-    merged: OrderedDict[str, object] = OrderedDict()
-    for feat in list(primary or []) + list(secondary or []):
-        merged.setdefault(feat.name, feat)
-    return list(merged.values())
-
-
 def get_mlp_output_dim(params: dict, fallback: int) -> int:
     hidden_dims = params.get("hidden_dims")
     if hidden_dims:
@@ -46,6 +35,8 @@ def select_features(
     names: list[str],
     param_name: str,
 ) -> list:
+    """select features by names from available features."""
+
     if not names:
         return []
 

{nextrec-0.5.1.dist-info → nextrec-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextrec
-Version: 0.5.1
+Version: 0.5.2
 Summary: A comprehensive recommendation library with match, ranking, and multi-task learning models
 Project-URL: Homepage, https://github.com/zerolovesea/NextRec
 Project-URL: Repository, https://github.com/zerolovesea/NextRec
@@ -73,7 +73,7 @@ Description-Content-Type: text/markdown
 ![Python](https://img.shields.io/badge/Python-3.10+-blue.svg)
 ![PyTorch](https://img.shields.io/badge/PyTorch-1.10+-ee4c2c.svg)
 ![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)
-![Version](https://img.shields.io/badge/Version-0.5.1-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.5.2-orange.svg)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/zerolovesea/NextRec)
 
 中文文档 | [English Version](README_en.md)
@@ -112,7 +112,6 @@ NextRec是一个基于PyTorch的现代推荐系统框架，旨在为研究工程
 - **21/12/2025** 在v0.4.16中加入了对[GradNorm](/nextrec/loss/grad_norm.py)的支持，通过compile的`loss_weight='grad_norm'`进行配置
 - **12/12/2025** 在v0.4.9中加入了[RQ-VAE](/nextrec/models/representation/rqvae.py)模块。配套的[数据集](/dataset/ecommerce_task.csv)和[代码](tutorials/notebooks/zh/使用RQ-VAE构建语义ID.ipynb)已经同步在仓库中
 - **07/12/2025** 发布了NextRec CLI命令行工具，它允许用户根据配置文件进行一键训练和推理，我们提供了相关的[教程](/nextrec_cli_preset/NextRec-CLI_zh.md)和[教学代码](/nextrec_cli_preset)
-- **03/12/2025** NextRec获得了100颗🌟！感谢大家的支持
 - **06/12/2025** 在v0.4.1中支持了单机多卡的分布式DDP训练，并且提供了配套的[代码](tutorials/distributed)
 - **11/11/2025** NextRec v0.1.0发布，我们提供了10余种Ranking模型，11种多任务模型和4种召回模型，以及统一的训练/日志/指标管理系统
 
@@ -260,11 +259,11 @@ nextrec --mode=predict --predict_config=path/to/predict_config.yaml
 
 预测结果固定保存到 `{checkpoint_path}/predictions/{name}.{save_data_format}`。
 
-> 截止当前版本0.5.1，NextRec CLI支持单机训练，分布式训练相关功能尚在开发中。
+> 截止当前版本0.5.2，NextRec CLI支持单机训练，分布式训练相关功能尚在开发中。
 
 ## 兼容平台
 
-当前最新版本为0.5.1，所有模型和测试代码均已在以下平台通过验证，如果开发者在使用中遇到兼容问题，请在issue区提出错误报告及系统版本：
+当前最新版本为0.5.2，所有模型和测试代码均已在以下平台通过验证，如果开发者在使用中遇到兼容问题，请在issue区提出错误报告及系统版本：
 
 | 平台 | 配置 | 
 |------|------|

{nextrec-0.5.1.dist-info → nextrec-0.5.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
 nextrec/__init__.py,sha256=_M3oUqyuvQ5k8Th_3wId6hQ_caclh7M5ad51XN09m98,235
-nextrec/__version__.py,sha256=eZ1bOun1DDVV0YLOBW4wj2FP1ajReLjbIrGmzN7ASBw,22
-nextrec/cli.py,sha256=lISpZYbdyQpKl6rWqm4ENXh4WqSfu-8jlC8jTDt1u1Y,29074
+nextrec/__version__.py,sha256=isJrmDBLRag7Zc2UK9ZovWGOv7ji1Oh-zJtJMNJFkXw,22
+nextrec/cli.py,sha256=ddYlk2zXF7iVFpONhG9Ofwb9dVgXfy112nk_JOHy1kI,29840
 nextrec/basic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/basic/activation.py,sha256=rU-W-DHgiD3AZnMGmD014ChxklfP9BpedDTiwtdgXhA,2762
 nextrec/basic/asserts.py,sha256=eaB4FZJ7Sbh9S8PLJZNiYd7Zi98ca2rDi4S7wSYCaEw,1473
@@ -10,21 +10,21 @@ nextrec/basic/heads.py,sha256=WqvavaH6Y8Au8dLaoUfH2AaOOWgYvjZI5US8avkQNsQ,4009
 nextrec/basic/layers.py,sha256=tawggQMMHlYTGpnubxUAvDPDJe_Lpq-HpLLCSjbJV54,37320
 nextrec/basic/loggers.py,sha256=jJUzUt_kMpjpV2Mqr7qBENWA1olEutTI7dFnpmndUUw,13845
 nextrec/basic/metrics.py,sha256=nVz3AkKwsxj_M97CoZWyQj8_Y9ZM_Icvw_QCM6c33Bc,26262
-nextrec/basic/model.py,sha256=x4QZc8lNXHzpOJLeN3qPs9G_kNC1KgKn_2K52v3-vLw,132691
+nextrec/basic/model.py,sha256=Fp1nRVd-8xq6wgjny02afGdIPUhJ-x1jD9bIPHserjQ,135037
 nextrec/basic/session.py,sha256=mrIsjRJhmvcAfoO1pXX-KB3SK5CCgz89wH8XDoAiGEI,4475
-nextrec/basic/summary.py,sha256=hCDVB8127GSGtlfFnfEFHWXuvW5qjCSTwowNoA1i1xE,19815
-nextrec/data/__init__.py,sha256=YZQjpty1pDCM7q_YNmiA2sa5kbujUw26ObLHWjMPjKY,1194
-nextrec/data/batch_utils.py,sha256=TbnXYqYlmK51dJthaL6dO7LTn4wyp8221I-kdgvpvDE,3542
-nextrec/data/data_processing.py,sha256=xD6afp4zc217ddKfDtHtToyDpxMDWvoqD_Vk4pIpvXU,6333
-nextrec/data/data_utils.py,sha256=0Ls1cnG9lBz0ovtyedw5vwp7WegGK_iF-F8e_3DEddo,880
-nextrec/data/dataloader.py,sha256=2sXwoiWxupKE-V1QYeZlXjK1yJyxhDtlOhknAnJF8Wk,19727
-nextrec/data/preprocessor.py,sha256=kOEfPy0t0M3jBA0kPIlwuSQYsuvn8yUNr_uE_NiulHU,49939
-nextrec/loss/__init__.py,sha256=rualGsY-IBvmM52q9eOBk0MyKcMkpkazcscOeDXi_SM,774
+nextrec/basic/summary.py,sha256=r5d8VtxJsgY6WRAVRa2-UcGb_sYA9VjMKDfQ31928qM,20494
+nextrec/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nextrec/data/batch_utils.py,sha256=Gbeo6XxP2ZsAAGP6f74MYQth-X_EDnXxkuMIGMr2bPk,3537
+nextrec/data/data_processing.py,sha256=TQdvqBOy8_h2TSjMFibCnWcoqtgyFV4TeLyFC621Xb8,5413
+nextrec/data/data_utils.py,sha256=RBpk2ymWJQHtNaa_yAnRk6bkck2UzazKfPSQsRTR1tU,786
+nextrec/data/dataloader.py,sha256=4fAqHZFSbnKOtXWrXLJ39zYfmTAa-dpySyFON1PlWfk,20503
+nextrec/data/preprocessor.py,sha256=92r7c3B_3BSpCmEqI9gXywTlS319kxf4qqzkxHjBfVk,51350
+nextrec/loss/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/loss/grad_norm.py,sha256=I4jAs0f84I7MWmYZOMC0JRUNvBHZzhgpuox0hOtYWDg,7435
 nextrec/loss/listwise.py,sha256=mluxXQt9XiuWGvXA1nk4I0miqaKB6_GPVQqxLhAiJKs,5999
 nextrec/loss/pairwise.py,sha256=9fyH9p2u-N0-jAnNTq3X5Dje0ipj1dob8wp-yQKRra4,3493
 nextrec/loss/pointwise.py,sha256=09nzI1L5eP9raXnj3Q49bD9Clp_JmsSWUvEj7bkTzSw,7474
-nextrec/models/generative/__init__.py,sha256=0MV3P-_ainPaTxmRBGWKUVCEt14KJvuvEHmRB3OQ1Fs,176
+nextrec/models/generative/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/models/generative/tiger.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/models/multi_task/[pre]aitm.py,sha256=A2n0T4JEui-uHgbqITU5lpsmtnP14fQXRZM1peTPvhQ,6661
 nextrec/models/multi_task/[pre]snr_trans.py,sha256=k08tC-TI--a_Tt4_BmX0ZubzntyqwsejutYzbB5F4S4,9077
@@ -65,23 +65,23 @@ nextrec/models/retrieval/mind.py,sha256=I0qVj39ApweRGW3qDNLca5vsNtJwRe7gBLh1peds
 nextrec/models/retrieval/sdm.py,sha256=h9TqVmSJ8YF7hgPci784nAlBg1LazB641c4iEeuiLDg,9956
 nextrec/models/retrieval/youtube_dnn.py,sha256=hLyR4liuusJIjRg4vuaSoSEecYgDICipXnNFiA3o3oY,6351
 nextrec/models/sequential/hstu.py,sha256=XFq-IERFg2ohqg03HkP6YinQaZUXljtYayUmvU-N_IY,18916
-nextrec/models/tree_base/__init__.py,sha256=ssGpU1viVidr1tgKCyvmkUXe32bUmwb5qPEkTh7ce70,342
-nextrec/models/tree_base/base.py,sha256=HcxUkctNgizY9LOBh2qXY6gUiYoy2JXA7j11NwUfWT4,26562
+nextrec/models/tree_base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nextrec/models/tree_base/base.py,sha256=czmIrlbGGMjiwwTcj_nVP5-Bnqrl_VNdh0YGHeRaejk,26101
 nextrec/models/tree_base/catboost.py,sha256=hXINyx7iianwDxOZx3SLm0i-YP1jiC3HcAeqP9A2i4A,3434
 nextrec/models/tree_base/lightgbm.py,sha256=VilMU7SgfHR5LAaaoQo-tY1vkzpSvWovIrgaSeuJ1-A,2263
 nextrec/models/tree_base/xgboost.py,sha256=thOmDIC_nitno_k2mcH2cj2VcS07f9veTG01FMOO-28,1957
-nextrec/utils/__init__.py,sha256=a29_8gjGzTj1A8r4oOi6LUyFhC97v4ePLOPKbNtCJ6M,2702
+nextrec/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/utils/config.py,sha256=Ngd_u8ZS5br4lIqrBJ_ecLquMF4KJi6TPAGqLZg8H4s,20485
 nextrec/utils/console.py,sha256=RnSUplJnyanSQ6TyMQkP7S1j2rGMver1DbFVqNH6_1k,13581
-nextrec/utils/data.py,sha256=pSL96mWjWfW_RKE-qlUSs9vfiYnFZAaRirzA6r7DB6s,24994
+nextrec/utils/data.py,sha256=JN30npycFMo_caBQJ5815tciRW3r7YDqSQxnJuXhlVA,22299
 nextrec/utils/embedding.py,sha256=akAEc062MG2cD7VIOllHaqtwzAirQR2gq5iW7oKpGAU,1449
 nextrec/utils/loss.py,sha256=GBWQGpDaYkMJySpdG078XbeUNXUC34PVqFy0AqNS9N0,4578
-nextrec/utils/model.py,sha256=PI9y8oWz1lhktgapZsiXb8rTr2NrFFlc80tr4yOFHik,5334
+nextrec/utils/model.py,sha256=K1-ZfS1umSTVo-lNHKNkBb3xvWnfiJJSTRicSVDpk4s,5148
 nextrec/utils/onnx_utils.py,sha256=KIVV_ELYzj3kCswfsSBZ1F2OnSwRJnXj7sxDBwBoBaA,8668
 nextrec/utils/torch_utils.py,sha256=_a9e6GXa3QKuu0E5RL44QRZ1iJSobbtNcPB3vtaCsu8,12313
 nextrec/utils/types.py,sha256=LFwYCBRo5WeYUh5LSCuyP1Lg9ez0Ih00Es3fUttGAFw,2273
-nextrec-0.5.1.dist-info/METADATA,sha256=DswmHjwCt-xuCenbNsKJgeSMw2LqVOAJFVFjgEn2CRc,23532
-nextrec-0.5.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-nextrec-0.5.1.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
-nextrec-0.5.1.dist-info/licenses/LICENSE,sha256=COP1BsqnEUwdx6GCkMjxOo5v3pUe4-Go_CdmQmSfYXM,1064
-nextrec-0.5.1.dist-info/RECORD,,
+nextrec-0.5.2.dist-info/METADATA,sha256=ibFYpr07uouyfvIqXngb9GcezGwZe3gIK-E3lbNtavY,23464
+nextrec-0.5.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+nextrec-0.5.2.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
+nextrec-0.5.2.dist-info/licenses/LICENSE,sha256=COP1BsqnEUwdx6GCkMjxOo5v3pUe4-Go_CdmQmSfYXM,1064
+nextrec-0.5.2.dist-info/RECORD,,