nextrec 0.4.24__py3-none-any.whl → 0.4.25__py3-none-any.whl

nextrec/utils/model.py

@@ -2,14 +2,13 @@
 Model-related utilities for NextRec
 
 Date: create on 03/12/2025
-Checkpoint: edit on 29/12/2025
+Checkpoint: edit on 31/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
 from collections import OrderedDict
 
 import torch
-from torch import nn
 
 from nextrec.loss import (
     ApproxNDCGLoss,
@@ -20,14 +19,6 @@ from nextrec.loss import (
     SampledSoftmaxLoss,
     TripletLoss,
 )
-from nextrec.utils.types import (
-    LossName,
-    OptimizerName,
-    SchedulerName,
-    TrainingModeName,
-    TaskTypeName,
-    MetricsName,
-)
 
 
 def merge_features(primary, secondary) -> list:
@@ -81,47 +72,26 @@ def compute_pair_scores(model, data, batch_size: int = 512):
     return scores.detach().cpu().numpy()
 
 
-def get_training_modes(
-    training_mode,
-    nums_task: int,
-    valid_modes: set[str] | None = None,
-) -> list:
-    valid_modes = valid_modes or {"pointwise", "pairwise", "listwise"}
-    if isinstance(training_mode, list):
-        training_modes = list(training_mode)
-        if len(training_modes) != nums_task:
-            raise ValueError(
-                "[BaseModel-init Error] training_mode list length must match number of tasks."
-            )
-    else:
-        training_modes = [training_mode] * nums_task
-    if any(mode not in valid_modes for mode in training_modes):
-        raise ValueError(
-            "[BaseModel-init Error] training_mode must be one of {'pointwise', 'pairwise', 'listwise'}."
-        )
-    return training_modes
-
-
 def get_loss_list(
     loss,
     training_modes: list[str],
     nums_task: int,
-    default_losses: dict[str, str],
 ):
-    effective_loss = loss
-    if effective_loss is None:
+    default_losses = {
+        "pointwise": "bce",
+        "pairwise": "bpr",
+        "listwise": "listnet",
+    }
+    if loss is None:
         loss_list = [default_losses[mode] for mode in training_modes]
-    elif isinstance(effective_loss, list):
-        if not effective_loss:
-            loss_list = [default_losses[mode] for mode in training_modes]
-        else:
-            if len(effective_loss) != nums_task:
-                raise ValueError(
-                    f"[BaseModel-compile Error] Number of loss functions ({len(effective_loss)}) must match number of tasks ({nums_task})."
-                )
-            loss_list = list(effective_loss)
+    elif isinstance(loss, list):
+        if len(loss) != nums_task:
+            raise ValueError(
+                f"[BaseModel-compile Error] Number of loss functions ({len(loss)}) must match number of tasks ({nums_task})."
+            )
+        loss_list = loss
     else:
-        loss_list = [effective_loss] * nums_task
+        loss_list = [loss] * nums_task
 
     for idx, mode in enumerate(training_modes):
         if isinstance(loss_list[idx], str) and loss_list[idx] in {
@@ -133,32 +103,6 @@ def get_loss_list(
     return loss_list
 
 
-def resolve_loss_weights(loss_weights, nums_task: int):
-    if loss_weights is None:
-        return None
-    if nums_task == 1:
-        if isinstance(loss_weights, (list, tuple)):
-            if len(loss_weights) != 1:
-                raise ValueError(
-                    "[BaseModel-compile Error] loss_weights list must have exactly one element for single-task setup."
-                )
-            loss_weights = loss_weights[0]
-        return [float(loss_weights)]
-    if isinstance(loss_weights, (int, float)):
-        weights = [float(loss_weights)] * nums_task
-    elif isinstance(loss_weights, (list, tuple)):
-        weights = [float(w) for w in loss_weights]
-        if len(weights) != nums_task:
-            raise ValueError(
-                f"[BaseModel-compile Error] Number of loss_weights ({len(weights)}) must match number of tasks ({nums_task})."
-            )
-    else:
-        raise TypeError(
-            f"[BaseModel-compile Error] loss_weights must be int, float, list or tuple, got {type(loss_weights)}"
-        )
-    return weights
-
-
 def prepare_ranking_targets(
     y_pred: torch.Tensor, y_true: torch.Tensor
 ) -> tuple[torch.Tensor, torch.Tensor]:

nextrec/utils/torch_utils.py

@@ -204,6 +204,11 @@ def get_scheduler(
             )
         else:
             raise NotImplementedError(f"Unsupported scheduler: {scheduler}")
+    elif isinstance(scheduler, type) and issubclass(
+        scheduler,
+        (torch.optim.lr_scheduler._LRScheduler, torch.optim.lr_scheduler.LRScheduler),
+    ):
+        scheduler_fn = scheduler(optimizer, **scheduler_params)
     elif isinstance(
         scheduler,
         (torch.optim.lr_scheduler._LRScheduler, torch.optim.lr_scheduler.LRScheduler),
@@ -215,6 +220,12 @@ def get_scheduler(
     return scheduler_fn
 
 
+def to_numpy(values: Any) -> np.ndarray:
+    if isinstance(values, torch.Tensor):
+        return values.detach().cpu().numpy()
+    return np.asarray(values)
+
+
 def to_tensor(
     value: Any, dtype: torch.dtype, device: torch.device | str | None = None
 ) -> torch.Tensor:

{nextrec-0.4.24.dist-info → nextrec-0.4.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextrec
-Version: 0.4.24
+Version: 0.4.25
 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
@@ -69,7 +69,7 @@ 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-0.4.24-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.4.25-orange.svg)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/zerolovesea/NextRec)
 
 中文文档 | [English Version](README_en.md)
@@ -249,11 +249,11 @@ 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0.4.24，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0.4.25，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0.4.24，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0.4.25，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-0.4.24.dist-info → nextrec-0.4.25.dist-info}/RECORD

@@ -1,6 +1,6 @@
 nextrec/__init__.py,sha256=_M3oUqyuvQ5k8Th_3wId6hQ_caclh7M5ad51XN09m98,235
-nextrec/__version__.py,sha256=WWrTOK_Nz_e97GQCElAGK_CtxVsM2uOWZphO5msHKOs,23
-nextrec/cli.py,sha256=Vm1XCFVw1vFh9NFw3PYZ_fYbh07tf45fl3RtPycooUI,24317
+nextrec/__version__.py,sha256=2KhS4HNlDzv_pmrC0ssutBbIG8FVsE-4OUVNs-FKmXw,23
+nextrec/cli.py,sha256=uOaXnlAM-ARrbxKOVWWkTE_rv-54px168kBhFUHtIAg,25073
 nextrec/basic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/basic/activation.py,sha256=uekcJsOy8SiT0_NaDO2VNSStyYFzVikDFVLDk-VrjwQ,2949
 nextrec/basic/callback.py,sha256=7geza5iMMlMojlrIKH5A7nzvCe4IYwgUaMRh_xpblWk,12585
@@ -9,15 +9,15 @@ nextrec/basic/heads.py,sha256=BshykLxD41KxKuZaBxf4Fmy1Mc52b3ioJliN1BVaGlk,3374
 nextrec/basic/layers.py,sha256=tr8XFOcTvUHEZ6T3zJwmtKMA-u_xfzHloIkItGs821U,40084
 nextrec/basic/loggers.py,sha256=KxTPVHtkebAbpxZIYZ4aqncZCu-dccpKtIxmi2bVs6o,13160
 nextrec/basic/metrics.py,sha256=CPzENDcpO6QTDZLBtQlfAGKUYYQc0FT-eaMKJ4MURFo,23396
-nextrec/basic/model.py,sha256=2dXMpYC8KV-prpUW7ex5hLq_NvKbPFbCNB9ncmCmBAE,104416
+nextrec/basic/model.py,sha256=FFJIrMW0dqh89Jq1poXpNN-8XvPfcqIlKdChQpGH6x0,110083
 nextrec/basic/session.py,sha256=mrIsjRJhmvcAfoO1pXX-KB3SK5CCgz89wH8XDoAiGEI,4475
-nextrec/basic/summary.py,sha256=9xDtDbtMCPSQuEVLx23-SLL6qDRl1MfM19YMBG3Wtow,15372
+nextrec/basic/summary.py,sha256=b6jLo70gqZj_bQ4eb5yb8SXmr2ilZlKNN293EyVnkyc,17759
 nextrec/data/__init__.py,sha256=YZQjpty1pDCM7q_YNmiA2sa5kbujUw26ObLHWjMPjKY,1194
 nextrec/data/batch_utils.py,sha256=0bYGVX7RlhnHv_ZBaUngjDIpBNw-igCk98DgOsF7T6o,2879
-nextrec/data/data_processing.py,sha256=ZDZMSTBvxjPppl872is4M49o4WAkZXw2vUFOsNr0q3w,6658
+nextrec/data/data_processing.py,sha256=lhuwYxWp4Ts2bbuLGDt2LmuPrOy7pNcKczd2uVcQ4ss,6476
 nextrec/data/data_utils.py,sha256=0Ls1cnG9lBz0ovtyedw5vwp7WegGK_iF-F8e_3DEddo,880
-nextrec/data/dataloader.py,sha256=hjp9gf9tgREozZE0tBVBhtNDb2Ss1bpOVo6Bw0WWsrk,19091
-nextrec/data/preprocessor.py,sha256=4mVhQ6W2M9nmTeQjArx_cndWwnk2i29U2iXSNgg5gXM,52917
+nextrec/data/dataloader.py,sha256=gTs4YC5tHHwTq0A9481KYK1XyloeN2dMVOjPAFehF_E,19972
+nextrec/data/preprocessor.py,sha256=AD5bHNbkAZAnI_SbDfJJaAh57CRtRjoOQJ6aIBkgoQs,65251
 nextrec/loss/__init__.py,sha256=rualGsY-IBvmM52q9eOBk0MyKcMkpkazcscOeDXi_SM,774
 nextrec/loss/grad_norm.py,sha256=YoE_XSIN1HOUcNq1dpfkIlWtMaB5Pu-SEWDaNgtRw1M,8316
 nextrec/loss/listwise.py,sha256=mluxXQt9XiuWGvXA1nk4I0miqaKB6_GPVQqxLhAiJKs,5999
@@ -70,17 +70,17 @@ nextrec/models/retrieval/youtube_dnn.py,sha256=ciD9RyBy19mfQcEoqw1UfydmVBsJvffDw
 nextrec/models/sequential/hstu.py,sha256=4-EUOQ4HTRG5MAhTA2b9FOOXXw8oyPxDBaaDFunkT6o,18979
 nextrec/models/sequential/sasrec.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nextrec/utils/__init__.py,sha256=jD73RLigxcHFP-rXBoPi2VUTKH7kE5vNMQkr4lW8UUY,2655
-nextrec/utils/config.py,sha256=UIi4zntP2g4IJaeMQYoa6kMQlU_23Hq4N1ZugMgnB5A,20331
+nextrec/utils/config.py,sha256=WeGHjoQYA5SoC9B_uS3D6ChzKr9Z5n2fwE-8l6nsuLE,20425
 nextrec/utils/console.py,sha256=RA3ZTjtUQXvueouSmXJNLkRjeUGQZesphwWjFMTbV4I,13577
 nextrec/utils/data.py,sha256=pSL96mWjWfW_RKE-qlUSs9vfiYnFZAaRirzA6r7DB6s,24994
 nextrec/utils/embedding.py,sha256=akAEc062MG2cD7VIOllHaqtwzAirQR2gq5iW7oKpGAU,1449
 nextrec/utils/feature.py,sha256=E3NOFIW8gAoRXVrDhCSonzg8k7nMUZyZzMfCq9k73_A,623
 nextrec/utils/loss.py,sha256=GBWQGpDaYkMJySpdG078XbeUNXUC34PVqFy0AqNS9N0,4578
-nextrec/utils/model.py,sha256=M9ToX2sOw5t07a6lG2DagSjPJtUULopANOZ1EW_Wcds,7752
-nextrec/utils/torch_utils.py,sha256=1lvZ7BG-rGLIAlumQIoeq5T9dO9hx2p8sa2_DC_bTZU,11564
+nextrec/utils/model.py,sha256=dcAL2lXNXRzFfCHMfOM_gIDLH68IAezMosSmmOD3FiQ,5624
+nextrec/utils/torch_utils.py,sha256=UQpWS7F3nITYqvx2KRBaQJc9oTowRkIvowhuQLt6NFM,11953
 nextrec/utils/types.py,sha256=VhtLXUVvu0zAZVAUgRUML4FExRC-GH-ZmC1UiVSr3HE,1523
-nextrec-0.4.24.dist-info/METADATA,sha256=hH313iUy8qYMnSD05xW4m_E6LYh7x_NblMrxu6f34U4,21859
-nextrec-0.4.24.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-nextrec-0.4.24.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
-nextrec-0.4.24.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
-nextrec-0.4.24.dist-info/RECORD,,
+nextrec-0.4.25.dist-info/METADATA,sha256=AY7ejbF1WA7Z4EHCbZVKB-Flom6diV50LGwiUVt-auA,21859
+nextrec-0.4.25.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+nextrec-0.4.25.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
+nextrec-0.4.25.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
+nextrec-0.4.25.dist-info/RECORD,,