nextrec 0.4.17__py3-none-any.whl → 0.4.19__py3-none-any.whl

nextrec/models/ranking/deepfm.py

@@ -1,6 +1,6 @@
 """
 Date: create on 27/10/2025
-Checkpoint: edit on 24/11/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou,zyaztec@gmail.com
 Reference:
 [1] Guo H, Tang R, Ye Y, et al. DeepFM: A factorization-machine based neural network
@@ -134,4 +134,4 @@ class DeepFM(BaseModel):
         y_deep = self.mlp(input_deep)  # [B, 1]
 
         y = y_linear + y_fm + y_deep
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/eulernet.py

@@ -1,6 +1,6 @@
 """
 Date: create on 09/11/2025
-Checkpoint: edit on 09/12/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Zhao Z, Zhang H, Tang H, et al. EulerNet: Efficient and Effective Feature
@@ -332,4 +332,4 @@ class EulerNet(BaseModel):
             r, p = layer(r, p)
         r_flat = r.reshape(r.size(0), self.num_orders * self.embedding_dim)
         p_flat = p.reshape(p.size(0), self.num_orders * self.embedding_dim)
-        return self.w(r_flat) + self.w_im(p_flat)
+        return self.w(r_flat) + self.w_im(p_flat)

nextrec/models/ranking/ffm.py

@@ -1,6 +1,6 @@
 """
 Date: create on 19/12/2025
-Checkpoint: edit on 19/12/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Juan Y, Zhuang Y, Chin W-S, et al. Field-aware Factorization Machines for CTR
@@ -273,4 +273,4 @@ class FFM(BaseModel):
                 )
 
         y = y_linear + y_interaction
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/fm.py

@@ -1,6 +1,6 @@
 """
 Date: create on 09/11/2025
-Checkpoint: edit on 09/12/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Rendle S. Factorization machines[C]//ICDM. 2010: 995-1000.
@@ -125,4 +125,4 @@ class FM(BaseModel):
         y_linear = self.linear(input_fm.flatten(start_dim=1))
         y_fm = self.fm(input_fm)
         y = y_linear + y_fm
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/lr.py

@@ -1,6 +1,6 @@
 """
 Date: create on 09/11/2025
-Checkpoint: edit on 09/12/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Hosmer D W, Lemeshow S, Sturdivant R X. Applied Logistic Regression.
@@ -116,4 +116,4 @@ class LR(BaseModel):
     def forward(self, x):
         input_linear = self.embedding(x=x, features=self.all_features, squeeze_dim=True)
         y = self.linear(input_linear)
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/masknet.py

@@ -1,6 +1,6 @@
 """
 Date: create on 09/11/2025
-Checkpoint: edit on 29/11/2025
+Checkpoint: edit on 23/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Wang Z, She Q, Zhang J. MaskNet: Introducing Feature-Wise
@@ -290,7 +290,6 @@ class MaskNet(BaseModel):
                 embedding_attr="embedding",
                 include_modules=["mask_blocks", "output_layer"],
             )
-        # serial
         else:
             self.register_regularization_weights(
                 embedding_attr="embedding", include_modules=["mask_blocks", "final_mlp"]
@@ -315,7 +314,6 @@ class MaskNet(BaseModel):
                 block_outputs.append(h)
             concat_hidden = torch.cat(block_outputs, dim=-1)
             logit = self.final_mlp(concat_hidden)  # [B, 1]
-        # serial
         else:
             hidden = self.first_block(field_emb, v_emb_flat)
             hidden = self.block_dropout(hidden)
@@ -324,4 +322,4 @@ class MaskNet(BaseModel):
                 hidden = self.block_dropout(hidden)
             logit = self.output_layer(hidden)  # [B, 1]
         y = self.prediction_layer(logit)
-        return y
+        return y

nextrec/models/ranking/pnn.py

@@ -1,7 +1,7 @@
 """
 Date: create on 09/11/2025
-Author:
-    Yang Zhou,zyaztec@gmail.com
+Checkpoint: edit on 23/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Qu Y, Cai H, Ren K, et al. Product-based neural networks for user response
 prediction[C]//ICDM. 2016: 1149-1154. (https://arxiv.org/abs/1611.00144)
@@ -198,4 +198,4 @@ class PNN(BaseModel):
 
         deep_input = torch.cat([linear_signal, product_signal], dim=1)
         y = self.mlp(deep_input)
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/widedeep.py

@@ -1,12 +1,11 @@
 """
 Date: create on 09/11/2025
-Checkpoint: edit on 24/11/2025
-Author:
-    Yang Zhou,zyaztec@gmail.com
+Checkpoint: edit on 23/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
 Reference:
-    [1] Cheng H T, Koc L, Harmsen J, et al. Wide & Deep learning for recommender systems[C]
-        //Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. 2016: 7-10.
-        (https://arxiv.org/abs/1606.07792)
+[1] Cheng H T, Koc L, Harmsen J, et al. Wide & Deep learning for recommender systems[C]
+//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. 2016: 7-10.
+(https://arxiv.org/abs/1606.07792)
 
 Wide & Deep blends a linear wide component (memorization of cross features) with a
 deep neural network (generalization) sharing the same feature space. The wide part
@@ -138,4 +137,4 @@ class WideDeep(BaseModel):
 
         # Combine wide and deep
         y = y_wide + y_deep
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/models/ranking/xdeepfm.py

@@ -1,7 +1,7 @@
 """
 Date: create on 09/11/2025
-Author:
-Yang Zhou,zyaztec@gmail.com
+Checkpoint: edit on 23/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
 Reference:
 [1] Lian J, Zhou X, Zhang F, et al. xdeepfm: Combining explicit and implicit feature interactions
 for recommender systems[C]//Proceedings of the 24th ACM SIGKDD international conference on
@@ -219,4 +219,4 @@ class xDeepFM(BaseModel):
 
         # Combine all parts
         y = y_linear + y_cin + y_deep
-        return self.prediction_layer(y)
+        return self.prediction_layer(y)

nextrec/utils/console.py

@@ -228,7 +228,7 @@ def group_metrics_by_task(
     metrics: Mapping[str, Any] | None,
     target_names: list[str] | str | None,
     default_task_name: str = "overall",
-) -> tuple[list[str], dict[str, dict[str, float]]]:
+):
     if not metrics:
         return [], {}
 

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 19/12/2025
+Checkpoint: edit on 24/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
@@ -19,6 +19,46 @@ 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]:
     """
@@ -30,29 +70,39 @@ def resolve_file_paths(path: str) -> tuple[list[str], str]:
     path_obj = Path(path)
 
     if path_obj.is_file():
-        file_type = path_obj.suffix.lower().lstrip(".")
-        assert file_type in [
-            "csv",
-            "parquet",
-        ], f"Unsupported file extension: {file_type}"
-        return [str(path_obj)], file_type
+        file_format = get_file_format_from_extension(path_obj.suffix)
+        if file_format is None:
+            raise ValueError(
+                f"Unsupported file extension: {path_obj.suffix}. "
+                f"Supported formats: {', '.join(FILE_FORMAT_CONFIG.keys())}"
+            )
+        return [str(path_obj)], file_format
 
     if path_obj.is_dir():
         collected_files = [p for p in path_obj.iterdir() if p.is_file()]
-        csv_files = [str(p) for p in collected_files if p.suffix.lower() == ".csv"]
-        parquet_files = [
-            str(p) for p in collected_files if p.suffix.lower() == ".parquet"
-        ]
+        # Group files by format
+        format_groups: Dict[str, List[str]] = {}
+        for file in collected_files:
+            file_format = get_file_format_from_extension(file.suffix)
+            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."
+            )
 
-        if csv_files and parquet_files:
+        if not format_groups:
             raise ValueError(
-                "Directory contains both CSV and Parquet files. Please keep a single format."
+                f"No supported data files found in directory: {path}. "
+                f"Supported formats: {', '.join(FILE_FORMAT_CONFIG.keys())}"
             )
-        file_paths = csv_files if csv_files else parquet_files
-        if not file_paths:
-            raise ValueError(f"No CSV or Parquet files found in directory: {path}")
+
+        file_type = list(format_groups.keys())[0]
+        file_paths = format_groups[file_type]
         file_paths.sort()
-        file_type = "csv" if csv_files else "parquet"
         return file_paths, file_type
 
     raise ValueError(f"Invalid path: {path}")
@@ -60,15 +110,55 @@ 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)
-    fmt = data_format.lower() if data_format else data_path.suffix.lower().lstrip(".")
-    if data_path.is_dir() and not fmt:
-        fmt = "parquet"
-    if fmt in {"parquet", ""}:
-        return pd.read_parquet(data_path)
-    if fmt in {"csv", "txt"}:
-        # Use low_memory=False to avoid mixed-type DtypeWarning on wide CSVs
-        return pd.read_csv(data_path, low_memory=False)
-    raise ValueError(f"Unsupported data format: {data_path}")
+
+    # Determine format
+    if data_format:
+        fmt = data_format.lower()
+    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."
+            )
+
+    if data_path.is_dir():
+        file_paths, _ = resolve_file_paths(str(data_path))
+        dataframes = [read_table(fp, fmt) for fp in file_paths]
+        if not dataframes:
+            raise ValueError(f"No supported data files found in directory: {data_path}")
+        if len(dataframes) == 1:
+            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]:
@@ -78,12 +168,44 @@ def load_dataframes(file_paths: list[str], file_type: str) -> list[pd.DataFrame]
 def iter_file_chunks(
     file_path: str, file_type: str, chunk_size: int
 ) -> Generator[pd.DataFrame, None, None]:
-    if file_type == "csv":
-        yield from pd.read_csv(file_path, chunksize=chunk_size)
-        return
-    parquet_file = pq.ParquetFile(file_path)
-    for batch in parquet_file.iter_batches(batch_size=chunk_size):
-        yield batch.to_pandas()
+    """Iterate over file in chunks for streaming reading.
+
+    Args:
+        file_path: Path to the file
+        file_type: Format type (csv, parquet)
+        chunk_size: Number of rows per chunk
+
+    Yields:
+        DataFrame chunks
+
+    Raises:
+        ValueError: If format doesn't support streaming
+    """
+    file_type = file_type.lower()
+    if not check_streaming_support(file_type):
+        raise ValueError(
+            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:

nextrec/utils/model.py

@@ -2,6 +2,7 @@
 Model-related utilities for NextRec
 
 Date: create on 03/12/2025
+Checkpoint: edit on 24/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
@@ -9,6 +10,16 @@ from collections import OrderedDict
 
 import torch
 
+from nextrec.loss import (
+    ApproxNDCGLoss,
+    BPRLoss,
+    HingeLoss,
+    ListMLELoss,
+    ListNetLoss,
+    SampledSoftmaxLoss,
+    TripletLoss,
+)
+
 
 def merge_features(primary, secondary) -> list:
     merged: OrderedDict[str, object] = OrderedDict()
@@ -53,6 +64,80 @@ def compute_pair_scores(model, data, batch_size: int = 512):
         user_tensor = torch.as_tensor(user_emb, device=model.device)
         item_tensor = torch.as_tensor(item_emb, device=model.device)
         scores = model.compute_similarity(user_tensor, item_tensor)
-        if model.training_mode == "pointwise":
+        mode = model.training_mode
+        if isinstance(mode, list):
+            mode = mode[0] if mode else "pointwise"
+        if mode == "pointwise":
             scores = torch.sigmoid(scores)
     return scores.detach().cpu().numpy()
+
+
+def prepare_ranking_targets(
+    y_pred: torch.Tensor, y_true: torch.Tensor
+) -> tuple[torch.Tensor, torch.Tensor]:
+    if y_pred.dim() == 1:
+        y_pred = y_pred.view(-1, 1)
+    if y_true.dim() == 1:
+        y_true = y_true.view(-1, 1)
+    if y_pred.shape != y_true.shape:
+        raise ValueError(f"Shape mismatch: {y_pred.shape} vs {y_true.shape}")
+    return y_pred, y_true
+
+
+def split_pos_neg_scores(
+    scores: torch.Tensor, labels: torch.Tensor
+) -> tuple[torch.Tensor, torch.Tensor]:
+    if scores.dim() != 2 or labels.dim() != 2:
+        raise ValueError(
+            "[Ranking Error] pairwise/listwise training requires 2D scores and labels."
+        )
+    list_size = scores.size(1)
+    if list_size < 2:
+        raise ValueError(
+            "[Ranking Error] pairwise/listwise training requires list_size >= 2."
+        )
+    pos_mask = labels > 0
+    pos_counts = pos_mask.sum(dim=1)
+    neg_counts = list_size - pos_counts
+    if not torch.all(pos_counts == 1).item():
+        raise ValueError(
+            "[Ranking Error] pairwise/listwise with pos/neg split requires exactly one positive per row."
+        )
+    if not torch.all(neg_counts == list_size - 1).item():
+        raise ValueError(
+            "[Ranking Error] pairwise/listwise with pos/neg split requires at least one negative per row."
+        )
+    pos_scores = scores[pos_mask].view(-1)
+    neg_scores = scores[~pos_mask].view(scores.size(0), list_size - 1)
+    return pos_scores, neg_scores
+
+
+def compute_ranking_loss(
+    training_mode: str,
+    loss_fn: torch.nn.Module,
+    y_pred: torch.Tensor,
+    y_true: torch.Tensor,
+) -> torch.Tensor:
+    y_pred, y_true = prepare_ranking_targets(y_pred, y_true)
+    if training_mode == "pairwise":
+        pos_scores, neg_scores = split_pos_neg_scores(y_pred, y_true)
+        if isinstance(loss_fn, (BPRLoss, HingeLoss, SampledSoftmaxLoss)):
+            loss = loss_fn(pos_scores, neg_scores)
+        elif isinstance(loss_fn, TripletLoss):
+            raise ValueError(
+                "[Ranking Error] TripletLoss expects embeddings, not scalar scores."
+            )
+        else:
+            loss = loss_fn(pos_scores, neg_scores)
+    elif training_mode == "listwise":
+        if isinstance(loss_fn, (ListNetLoss, ListMLELoss, ApproxNDCGLoss)):
+            loss = loss_fn(y_pred, y_true)
+        elif isinstance(loss_fn, SampledSoftmaxLoss):
+            pos_scores, neg_scores = split_pos_neg_scores(y_pred, y_true)
+            loss = loss_fn(pos_scores, neg_scores)
+        else:
+            loss = loss_fn(y_pred, y_true)
+    else:
+        raise ValueError(f"[Ranking Error] Unknown training mode: {training_mode}")
+
+    return loss

{nextrec-0.4.17.dist-info → nextrec-0.4.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextrec
-Version: 0.4.17
+Version: 0.4.19
 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
@@ -63,13 +63,12 @@ Description-Content-Type: text/markdown
 
 <div align="center">
 
-[![PyPI Downloads](https://static.pepy.tech/personalized-badge/nextrec?period=total&units=NONE&left_color=BLACK&right_color=GREEN&left_text=PyPI-downloads)](https://pepy.tech/projects/nextrec)
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/nextrec?period=total&units=NONE&left_color=BLACK&right_color=GREEN&left_text=PyPI-downloads)](https://pypistats.org/packages/nextrec)
 ![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-0.4.17-orange.svg)
-
+![Version](https://img.shields.io/badge/Version-0.4.19-orange.svg)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/zerolovesea/NextRec)
 
 中文文档 | [English Version](README_en.md)
 
@@ -244,11 +243,13 @@ nextrec --mode=train --train_config=path/to/train_config.yaml
 nextrec --mode=predict --predict_config=path/to/predict_config.yaml
 ```
 
-> 截止当前版本0.4.17，NextRec CLI支持单机训练，分布式训练相关功能尚在开发中。
+预测结果固定保存到 `{checkpoint_path}/predictions/{name}.{save_data_format}`。
+
+> 截止当前版本0.4.19，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0.4.17，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0.4.19，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-0.4.17.dist-info → nextrec-0.4.19.dist-info}/RECORD

@@ -1,24 +1,24 @@
 nextrec/__init__.py,sha256=_M3oUqyuvQ5k8Th_3wId6hQ_caclh7M5ad51XN09m98,235
-nextrec/__version__.py,sha256=rJbmNVFVceaHhRo-pizixUQW0k5sqoDVdU1TfXfG8CA,23
-nextrec/cli.py,sha256=JUprwpoVbT4tXsGgMpj9Y_5yYByQXYMliMdWd38ReKo,24441
+nextrec/__version__.py,sha256=mfToEOXd_f_mFG0ts1iWNTvKhsjPQqwRFaAmcx61xJo,23
+nextrec/cli.py,sha256=aJnv8A_K9xbzVRo0BPIUGg8vk__C4kniXweKanlh2G8,24326
 nextrec/basic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/basic/activation.py,sha256=uzTWfCOtBSkbu_Gk9XBNTj8__s241CaYLJk6l8nGX9I,2885
 nextrec/basic/callback.py,sha256=nn1f8FG9c52vJ-gvwteqPbk3-1QuNS1vmhBlkENdb0I,14636
 nextrec/basic/features.py,sha256=GyCUzGPuizUofrZSSOdqHK84YhnX4MGTdu7Cx2OGhUA,4654
-nextrec/basic/heads.py,sha256=0TqttvqkaUFkGg2bkMbFhOK63AuHs8sZVzvtbgpo1CE,3318
+nextrec/basic/heads.py,sha256=UcAfD6Tw3o-HVBHSqutvJSa56xX7ZIY_Fx2SNBCkb9E,3280
 nextrec/basic/layers.py,sha256=ZM3Nka3e2cit3e3peL0ukJCMgKZK1ovNFfAWvVOwlos,28556
-nextrec/basic/loggers.py,sha256=Zh1A5DVAFqlGglyaQ4_IMgvFbWAcXX5H3aHbCWA82nE,6524
+nextrec/basic/loggers.py,sha256=kZsvWnKl45bIcGid59M6m-khTxb_2P6gvWAg4wohaO4,6509
 nextrec/basic/metrics.py,sha256=1r6efTc9TpARNBt5X9ISoppTZflej6EdFkjPYHV-YZI,23162
-nextrec/basic/model.py,sha256=MFJr6_FAT8-niEwZrqmo8oWzkjuspdjXRsizt1R056Q,103814
+nextrec/basic/model.py,sha256=xueGxwl0A7XwdzgIqMuHavWon4glEsFKfu4e4QbGBWc,109348
 nextrec/basic/session.py,sha256=UOG_-EgCOxvqZwCkiEd8sgNV2G1sm_HbzKYVQw8yYDI,4483
 nextrec/data/__init__.py,sha256=YZQjpty1pDCM7q_YNmiA2sa5kbujUw26ObLHWjMPjKY,1194
 nextrec/data/batch_utils.py,sha256=0bYGVX7RlhnHv_ZBaUngjDIpBNw-igCk98DgOsF7T6o,2879
 nextrec/data/data_processing.py,sha256=lKXDBszrO5fJMAQetgSPr2mSQuzOluuz1eHV4jp0TDU,5538
 nextrec/data/data_utils.py,sha256=0Ls1cnG9lBz0ovtyedw5vwp7WegGK_iF-F8e_3DEddo,880
-nextrec/data/dataloader.py,sha256=0JYoQk5MXCwtbj-h8X38SOsb4YPJQawASCatuPNgTw4,19561
-nextrec/data/preprocessor.py,sha256=K-cUP-YdlQx1VJ2m1CXuprncpjDJe2ERVO5xCSoxHKI,44470
+nextrec/data/dataloader.py,sha256=8kGZIrt88UnGFDOCNiMpCW5tn2H9D38GzfSaWHk-oqI,18943
+nextrec/data/preprocessor.py,sha256=sIkuGNOpDTjtGy6gIlxxro3ktcUWOjIEqeWd2FN9s2g,47253
 nextrec/loss/__init__.py,sha256=ZCgsfyR5YAecv6MdOsnUjkfacvZg2coQVjuKAfPvmRo,923
-nextrec/loss/grad_norm.py,sha256=91Grspx95Xu_639TkL_WZRX1xt5QOTZCzBeJWbUGPiE,8385
+nextrec/loss/grad_norm.py,sha256=1BU1uHh6CuNRc_M_bPP2mrVKOnUGQWv_tR_8-ETOJlg,8385
 nextrec/loss/listwise.py,sha256=UT9vJCOTOQLogVwaeTV7Z5uxIYnngGdxk-p9e97MGkU,5744
 nextrec/loss/loss_utils.py,sha256=xMmT_tWcKah_xcU3FzVMmSEzyZfxiMKZWUbwkAspcDg,4579
 nextrec/loss/pairwise.py,sha256=X9yg-8pcPt2IWU0AiUhWAt3_4W_3wIF0uSdDYTdoPFY,3398
@@ -26,28 +26,28 @@ nextrec/loss/pointwise.py,sha256=o9J3OznY0hlbDsUXqn3k-BBzYiuUH5dopz8QBFqS_kQ,734
 nextrec/models/generative/__init__.py,sha256=0MV3P-_ainPaTxmRBGWKUVCEt14KJvuvEHmRB3OQ1Fs,176
 nextrec/models/generative/tiger.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/models/multi_task/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nextrec/models/multi_task/esmm.py,sha256=zVHuDwVP0HNx1tgjJOc9iz_uFXfUwoy5pVPn-XX0zBs,6561
-nextrec/models/multi_task/mmoe.py,sha256=lXK_kSw9TFTY6437yDA90_jerZi02lKdVM8zTCH3QMU,8673
-nextrec/models/multi_task/ple.py,sha256=9X0eSMIFGj4Dj9yy2tpKEI7vp9TL5XvgKehMLm4wpJs,13100
-nextrec/models/multi_task/poso.py,sha256=BomMkRx-tNtFiZ0mFBrRYms6PnffMvRlPkO9c5QZaiQ,19209
-nextrec/models/multi_task/share_bottom.py,sha256=i1vt3z6Ycj4SjucHrzmJeuIfo2_VDwSF9ubJeNzKy6c,6599
+nextrec/models/multi_task/esmm.py,sha256=WoqRtXZnAQaWHkPMGrV1PCY-BOn6tcx_B8okung84Ec,6540
+nextrec/models/multi_task/mmoe.py,sha256=e6i1wG42LOrOWO602zEH7NJCXUiICcEK1xa_u5ZCQlI,8674
+nextrec/models/multi_task/ple.py,sha256=KjhYR4hT91Q8XGesOp1hHw-2933sIZmJLBkI5QlrZ0s,13101
+nextrec/models/multi_task/poso.py,sha256=cwLZeoFnC2Kiq7K9hxTuhVOlCTCN5RmK-7KKd9JIO_s,19241
+nextrec/models/multi_task/share_bottom.py,sha256=QJrKvhq21dhV41m4MtbhCUTLUBf1uUFhDA8d4dacu9k,6600
 nextrec/models/ranking/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nextrec/models/ranking/afm.py,sha256=p3rNc957TaEc2tkhpbQyTup8a1oH34UJ2YKLqCuUD-4,10141
-nextrec/models/ranking/autoint.py,sha256=OgNh-NpC9ragHbIJfMCnQJRS6mh0wINkw961rGp32_Q,8125
-nextrec/models/ranking/dcn.py,sha256=c22ZBbBw3aEAISgtnsKZqhCvcYhM68AmEPZFS6MYO44,7315
-nextrec/models/ranking/dcn_v2.py,sha256=PqhkSPhGUx52hZMd2JPBqYQr1o5twCg6M6hCaaTl3aY,11179
-nextrec/models/ranking/deepfm.py,sha256=9K_TEptWwIr_SNC4yqN8PA2SzUKafZL94PVT2qH5Bag,5216
+nextrec/models/ranking/afm.py,sha256=lhHTyDh51yIEhEbNyxlRaJKSPleIrhcgeE2H6tvy5UA,10142
+nextrec/models/ranking/autoint.py,sha256=FbKfhXq31mUpv9pQYv7b34d_HPxDrzAiiIgcUbi-Qow,8126
+nextrec/models/ranking/dcn.py,sha256=u9Wvfjom7Aqy3TyyNJevJawrI7h-MB2DOgfj2j7keZE,7316
+nextrec/models/ranking/dcn_v2.py,sha256=sx0W6JaU3ZTR2DNMz2vaqVeRhwwzzCFxmyGWBkas5P0,11180
+nextrec/models/ranking/deepfm.py,sha256=RN9Kjgzl0ZZwlu3gHJQtyNs5-Qv7s2eNjsO1VZMf2hk,5217
 nextrec/models/ranking/dien.py,sha256=URKWeOPeRD5OIWNsAxgVvbetOSrBHoq2eO5rR5UJ0jU,18971
 nextrec/models/ranking/din.py,sha256=Y8v0gONRt1OZORmn0hqMuzMfkvX0Nz1gByJ94jo3MUw,9435
-nextrec/models/ranking/eulernet.py,sha256=Mz2TObgYmYR7jIzwkafaySIxSn7P0ZVVFJTHZ0QEPFs,12217
-nextrec/models/ranking/ffm.py,sha256=0NB-ygR486lAJgarhOsdbaE8E0rbc1o8h5d8spWs5io,11278
+nextrec/models/ranking/eulernet.py,sha256=UPTTbuog9d4kjrOPSwBiLhiBUMlXvkJm75qNzkbYG3U,12218
+nextrec/models/ranking/ffm.py,sha256=8jgaCD2DLdxJ2qdm5DEOJ6ACKjopjIuOQvKYWWwgqOg,11279
 nextrec/models/ranking/fibinet.py,sha256=VP0gNoQwoLKxniv2HmHzxlnR3YlrnQJt6--CwmAgsW4,7932
-nextrec/models/ranking/fm.py,sha256=wX0VBvme41mFxSaT4Y1w4JfROL8EYT5KEe-hwRNr3zc,4552
-nextrec/models/ranking/lr.py,sha256=hc7XKa1GJhRa2CJY8-sYR0AB_fvmVLYCFoDRNCg04rU,4024
-nextrec/models/ranking/masknet.py,sha256=NNtIyAd-UHT78TvLcGbMvzR_aJRPzG3HBri1adNBrc4,12389
-nextrec/models/ranking/pnn.py,sha256=6a78M6n6B9aMBSvm0qICyBKjccoZ9TWVkDo9enc5d08,8190
-nextrec/models/ranking/widedeep.py,sha256=LNhLBmFP7M_z6ldxp99uMMK9s07EkP_9pjCAl6Hqp_Q,5093
-nextrec/models/ranking/xdeepfm.py,sha256=q4ITrgFfLe7NABxJQuchs8yqW_-jKwgXIwmpB2Lvoio,8172
+nextrec/models/ranking/fm.py,sha256=rNLF6Rs3AUc2H9elMsjQjHgvEsOe69Apb_T2j_CBmKg,4553
+nextrec/models/ranking/lr.py,sha256=rPqDyRrJNamWE44419fwCSX0ad7MNSy8_EUKCyTnHDg,4025
+nextrec/models/ranking/masknet.py,sha256=hvqe8FrU-IcPiXWFpvBzcRZc8Z8D6pMvpDola5uJGb0,12356
+nextrec/models/ranking/pnn.py,sha256=wtej_QcEifQk3WFNKUl5_YZAD5yTLQoPDwCEkf9G1pg,8219
+nextrec/models/ranking/widedeep.py,sha256=WAskeJbMA68_Qlxpl3vZc7KyrGVVyNQG_6LOH8VuxI4,5071
+nextrec/models/ranking/xdeepfm.py,sha256=_Ng4q18IGNuHf_M1RpoAk4ypm4zLNvx3tw9uBwpAnc8,8205
 nextrec/models/representation/__init__.py,sha256=O3QHMMXBszwM-mTl7bA3wawNZvDGet-QIv6Ys5GHGJ8,190
 nextrec/models/representation/autorec.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/models/representation/bpr.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -66,14 +66,14 @@ nextrec/models/sequential/hstu.py,sha256=P2Kl7HEL3afwiCApGKQ6UbUNO9eNXXrB10H7iiF
 nextrec/models/sequential/sasrec.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/utils/__init__.py,sha256=C-1l-suSsN_MlPlj_5LApyCRQLOao5l7bO0SccwKHw4,2598
 nextrec/utils/config.py,sha256=VgCh5fto8HGodwXPJacenqjxre3Aw6tw-mntW9n3OYA,20044
-nextrec/utils/console.py,sha256=wHAGQT0HmPumWlMlqQuBVXPVGCWubgYez-vuzkOMiMQ,13646
-nextrec/utils/data.py,sha256=alruiWZFbmwy3kO12q42VXmtHmXFFjVULpHa43fx_mI,21098
+nextrec/utils/console.py,sha256=jlZLCOopPHcspOx7ymWNcz3i77EgzP6v8bqZaiiBbuM,13597
+nextrec/utils/data.py,sha256=pSL96mWjWfW_RKE-qlUSs9vfiYnFZAaRirzA6r7DB6s,24994
 nextrec/utils/embedding.py,sha256=akAEc062MG2cD7VIOllHaqtwzAirQR2gq5iW7oKpGAU,1449
 nextrec/utils/feature.py,sha256=rsUAv3ELyDpehVw8nPEEsLCCIjuKGTJJZuFaWB_wrPk,633
-nextrec/utils/model.py,sha256=3B85a0IJCggI26dxv25IX8R_5yQPo7wXI0JIAns6bkQ,1727
+nextrec/utils/model.py,sha256=fHvFciUuMOVcM1oWiRva4LcArRdZ1R5Uzml-COSqqvM,4688
 nextrec/utils/torch_utils.py,sha256=AKfYbSOJjEw874xsDB5IO3Ote4X7vnqzt_E0jJny0o8,13468
-nextrec-0.4.17.dist-info/METADATA,sha256=X-ezN2q05f0SKvwE80Y8ThecPGQI1D7RJCl6FEDXyjA,21298
-nextrec-0.4.17.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-nextrec-0.4.17.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
-nextrec-0.4.17.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
-nextrec-0.4.17.dist-info/RECORD,,
+nextrec-0.4.19.dist-info/METADATA,sha256=alzuH4O4ACST72cQX6SEbwc8wWGODXX0BV87b2lPUF8,21482
+nextrec-0.4.19.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+nextrec-0.4.19.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
+nextrec-0.4.19.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
+nextrec-0.4.19.dist-info/RECORD,,