nextrec 0.4.14__py3-none-any.whl → 0.4.16__py3-none-any.whl

nextrec/__version__.py

@@ -1 +1 @@
-__version__ = "0.4.14"
+__version__ = "0.4.16"

nextrec/basic/metrics.py

@@ -77,6 +77,8 @@ def check_user_id(*metric_sources: Any) -> bool:
 
 def compute_ks(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     """Compute Kolmogorov-Smirnov statistic."""
+    y_true = np.asarray(y_true).reshape(-1)
+    y_pred = np.asarray(y_pred).reshape(-1)
     sorted_indices = np.argsort(y_pred)[::-1]
     y_true_sorted = y_true[sorted_indices]
 

nextrec/basic/model.py

@@ -481,7 +481,7 @@ class BaseModel(FeatureSet, nn.Module):
                         "[BaseModel-compile Error] loss_weights list must have exactly one element for single-task setup."
                     )
                 loss_weights = loss_weights[0]
-            self.loss_weights = [float(loss_weights)] # type: ignore
+            self.loss_weights = [float(loss_weights)]  # type: ignore
         else:
             if isinstance(loss_weights, (int, float)):
                 weights = [float(loss_weights)] * self.nums_task
@@ -591,8 +591,8 @@ class BaseModel(FeatureSet, nn.Module):
 
     def fit(
         self,
-        train_data = None,
-        valid_data = None,
+        train_data=None,
+        valid_data=None,
         metrics: (
             list[str] | dict[str, list[str]] | None
         ) = None,  # ['auc', 'logloss'] or {'target1': ['auc', 'logloss'], 'target2': ['mse']}
@@ -1420,6 +1420,11 @@ class BaseModel(FeatureSet, nn.Module):
         # Create DataLoader based on data type
         if isinstance(data, DataLoader):
             data_loader = data
+            if num_workers != 0:
+                logging.warning(
+                    "[Predict Warning] num_workers parameter is ignored when data is already a DataLoader. "
+                    "The DataLoader's existing num_workers configuration will be used."
+                )
         elif isinstance(data, (str, os.PathLike)):
             rec_loader = RecDataLoader(
                 dense_features=self.dense_features,
@@ -1578,6 +1583,17 @@ class BaseModel(FeatureSet, nn.Module):
         else:
             data_loader = data
 
+            if hasattr(data_loader, "num_workers") and data_loader.num_workers > 0:
+                if (
+                    hasattr(data_loader.dataset, "__class__")
+                    and "Streaming" in data_loader.dataset.__class__.__name__
+                ):
+                    logging.warning(
+                        f"[Predict Streaming Warning] Detected DataLoader with num_workers={data_loader.num_workers} "
+                        "and streaming dataset. This may cause data duplication! "
+                        "When using streaming mode, set num_workers=0 to avoid reading data multiple times."
+                    )
+
         suffix = ".csv" if save_format == "csv" else ".parquet"
         target_path = resolve_save_path(
             path=save_path,

nextrec/cli.py

@@ -21,6 +21,7 @@ Author: Yang Zhou, zyaztec@gmail.com
 import argparse
 import logging
 import pickle
+import resource
 import sys
 import time
 from pathlib import Path
@@ -625,6 +626,17 @@ def predict_model(predict_config_path: str) -> None:
 def main() -> None:
     """Parse CLI arguments and dispatch to train or predict mode."""
 
+    # Increase file descriptor limit to avoid "Too many open files" error
+    # when using DataLoader with multiple workers
+    try:
+        soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
+        target_limit = 65535
+        if soft < target_limit:
+            resource.setrlimit(resource.RLIMIT_NOFILE, (min(target_limit, hard), hard))
+    except (ValueError, OSError):
+        # If we can't set the limit, continue anyway
+        pass
+
     root = logging.getLogger()
     if not root.handlers:
         handler = logging.StreamHandler(sys.stdout)

nextrec/data/dataloader.py

@@ -210,6 +210,15 @@ class RecDataLoader(FeatureSet):
             DataLoader instance.
         """
 
+        # Enforce num_workers=0 for streaming mode to prevent data duplication
+        if streaming and num_workers > 0:
+            logging.warning(
+                f"[RecDataLoader Warning] num_workers={num_workers} is not compatible with streaming=True. "
+                "Each worker would create its own data stream, causing data duplication. "
+                "Forcing num_workers=0."
+            )
+            num_workers = 0
+
         if isinstance(data, DataLoader):
             return data
         elif isinstance(data, (str, os.PathLike)):
@@ -363,6 +372,13 @@ class RecDataLoader(FeatureSet):
             logging.info(
                 "[RecDataLoader Info] Streaming mode enforces batch_size=1; tune chunk_size to control memory/throughput."
             )
+        if num_workers > 0:
+            logging.warning(
+                f"[RecDataLoader Warning] num_workers={num_workers} is not compatible with streaming mode. "
+                "Each worker would create its own data stream, causing data duplication. "
+                "Forcing num_workers=0."
+            )
+            num_workers = 0
         dataset = FileDataset(
             file_paths=file_paths,
             dense_features=self.dense_features,

nextrec/utils/config.py

@@ -28,7 +28,9 @@ if TYPE_CHECKING:
     from nextrec.data.preprocessor import DataProcessor
 
 
-def resolve_path(path_str: str | Path | None = None, base_dir: Path | None = None) -> Path:
+def resolve_path(
+    path_str: str | Path | None = None, base_dir: Path | None = None
+) -> Path:
     if path_str is None:
         return Path.cwd()
     path = Path(path_str).expanduser()
@@ -36,9 +38,16 @@ def resolve_path(path_str: str | Path | None = None, base_dir: Path | None = Non
         return path
     # Prefer resolving relative to current working directory when the path (or its parent)
     # already exists there; otherwise fall back to the config file's directory.
-    candidates = ((Path.cwd() / path).resolve(), ((base_dir or Path.cwd()) / path).resolve())
+    candidates = (
+        (Path.cwd() / path).resolve(),
+        ((base_dir or Path.cwd()) / path).resolve(),
+    )
     return next(
-        (candidate for candidate in candidates if candidate.exists() or candidate.parent.exists()),
+        (
+            candidate
+            for candidate in candidates
+            if candidate.exists() or candidate.parent.exists()
+        ),
         candidates[0],
     )
 

nextrec/utils/console.py

@@ -16,8 +16,9 @@ import numbers
 import os
 import platform
 import sys
+import time
 from datetime import datetime, timedelta
-from typing import Any, Callable, Iterable, Mapping, TypeVar
+from typing import Any, Callable, Mapping, TypeVar
 
 import numpy as np
 from rich import box
@@ -128,45 +129,85 @@ class BlackMofNCompleteColumn(MofNCompleteColumn):
         )
 
 
-def progress(
-    iterable: Iterable[T],
-    *,
-    description: str | None = None,
-    total: int | None = None,
-    disable: bool = False,
-) -> Iterable[T]:
+def progress(iterable, *, description=None, total=None, disable=False):
     if disable:
-        for item in iterable:
-            yield item
+        yield from iterable
         return
+
     resolved_total = total
     if resolved_total is None:
         try:
-            resolved_total = len(iterable)  # type: ignore[arg-type]
+            resolved_total = len(iterable)
         except TypeError:
             resolved_total = None
 
+    stream = sys.stderr
+
+    if not stream.isatty():
+        start_time = time.monotonic()
+        last_tick = start_time
+        min_interval_seconds = 10.0
+        max_interval_seconds = 300.0
+        target_steps = (
+            max(1, resolved_total // 20) if resolved_total is not None else 500
+        )
+        interval_seconds = min_interval_seconds
+        completed = 0
+
+        def emit(now: float):
+            elapsed = max(0.0, now - start_time)
+            speed = completed / elapsed if elapsed > 0 else 0.0
+            if resolved_total is not None and speed > 0:
+                remaining = max(0.0, resolved_total - completed)
+                eta_seconds = remaining / speed
+                eta_text = str(timedelta(seconds=int(eta_seconds)))
+            else:
+                eta_text = "--:--:--"
+            total_text = str(resolved_total) if resolved_total is not None else "?"
+            stream.write(
+                f"{description or 'Working'}: {completed}/{total_text} "
+                f"elapsed={timedelta(seconds=int(elapsed))} "
+                f"speed={speed:.2f}/s ETA={eta_text}\n"
+            )
+            stream.flush()
+            return speed
+
+        for item in iterable:
+            yield item
+            completed += 1
+            now = time.monotonic()
+            if now - last_tick >= interval_seconds:
+                speed = emit(now)
+                last_tick = now
+                if speed > 0:
+                    interval_seconds = min(
+                        max_interval_seconds,
+                        max(min_interval_seconds, target_steps / speed),
+                    )
+        end_now = time.monotonic()
+        if end_now - last_tick >= 1e-6:
+            emit(end_now)
+        return
+
+    # TTY: rich
+    console = Console(file=stream, force_terminal=True)
     progress_bar = Progress(
-        SpinnerColumn(style="black"),
-        TextColumn("{task.description}", style="black"),
-        BarColumn(
-            bar_width=36, style="black", complete_style="black", finished_style="black"
-        ),
-        TaskProgressColumn(style="black"),
-        BlackMofNCompleteColumn(),
-        BlackTimeElapsedColumn(),
-        BlackTimeRemainingColumn(),
+        SpinnerColumn(),
+        TextColumn("{task.description}"),
+        BarColumn(bar_width=36),
+        TaskProgressColumn(),
+        MofNCompleteColumn(),
+        TimeElapsedColumn(),
+        TimeRemainingColumn(),
         refresh_per_second=12,
+        console=console,
     )
 
-    task_id = progress_bar.add_task(description or "Working", total=resolved_total)
-    progress_bar.start()
-    try:
+    with progress_bar:
+        task_id = progress_bar.add_task(description or "Working", total=resolved_total)
         for item in iterable:
             yield item
             progress_bar.advance(task_id, 1)
-    finally:
-        progress_bar.stop()
 
 
 def group_metrics_by_task(

{nextrec-0.4.14.dist-info → nextrec-0.4.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextrec
-Version: 0.4.14
+Version: 0.4.16
 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
@@ -63,10 +63,13 @@ 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)
 ![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-0.4.14-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.4.16-orange.svg)
+
 
 中文文档 | [English Version](README_en.md)
 
@@ -99,7 +102,7 @@ NextRec是一个基于PyTorch的现代推荐系统框架，旨在为研究工程
 
 ## NextRec近期进展
 
-- **21/12/2025** 在v0.4.14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
+- **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
@@ -241,11 +244,11 @@ 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0.4.14，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0.4.16，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0.4.14，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0.4.16，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-0.4.14.dist-info → nextrec-0.4.16.dist-info}/RECORD

@@ -1,20 +1,20 @@
 nextrec/__init__.py,sha256=_M3oUqyuvQ5k8Th_3wId6hQ_caclh7M5ad51XN09m98,235
-nextrec/__version__.py,sha256=kBEbn8dkCFa3vKochkZqeCl78cbsUbutSFlOYZrn__w,23
-nextrec/cli.py,sha256=6nBY8O8-0931h428eQS8CALkKn1FmizovJme7Q1c_O0,23978
+nextrec/__version__.py,sha256=Qgm7I6hoEastyorRf_J_YW-gsesKcI737L731iY3jes,23
+nextrec/cli.py,sha256=JUprwpoVbT4tXsGgMpj9Y_5yYByQXYMliMdWd38ReKo,24441
 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/layers.py,sha256=ZM3Nka3e2cit3e3peL0ukJCMgKZK1ovNFfAWvVOwlos,28556
 nextrec/basic/loggers.py,sha256=Zh1A5DVAFqlGglyaQ4_IMgvFbWAcXX5H3aHbCWA82nE,6524
-nextrec/basic/metrics.py,sha256=saNgM7kuHk9xqDxZF6x33irTaxeXCU-hxYTUQauuGgg,23074
-nextrec/basic/model.py,sha256=wzz2yMnzls7zxJmCNt2z51k0ZNTKRJ1HQdk3HQ61ObU,102854
+nextrec/basic/metrics.py,sha256=1r6efTc9TpARNBt5X9ISoppTZflej6EdFkjPYHV-YZI,23162
+nextrec/basic/model.py,sha256=eC4qV6wLHsIiYr2HZ4dOpliiD4mjTJhr4XdiezMO690,103767
 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=As2AvO2IGc-ofVl98HM7CIwSuzIvQtxJrSfvpJ2gamA,18787
+nextrec/data/dataloader.py,sha256=0JYoQk5MXCwtbj-h8X38SOsb4YPJQawASCatuPNgTw4,19561
 nextrec/data/preprocessor.py,sha256=K-cUP-YdlQx1VJ2m1CXuprncpjDJe2ERVO5xCSoxHKI,44470
 nextrec/loss/__init__.py,sha256=ZCgsfyR5YAecv6MdOsnUjkfacvZg2coQVjuKAfPvmRo,923
 nextrec/loss/grad_norm.py,sha256=91Grspx95Xu_639TkL_WZRX1xt5QOTZCzBeJWbUGPiE,8385
@@ -64,15 +64,15 @@ nextrec/models/retrieval/youtube_dnn.py,sha256=xtGPV6_5LeSZBKkrTaU1CmtxlhgYLvZmj
 nextrec/models/sequential/hstu.py,sha256=P2Kl7HEL3afwiCApGKQ6UbUNO9eNXXrB10H7iiF8cI0,19735
 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=2zcjK4TeN8ow-JSXbWpqyh9C1vFeKnEsYHPg1x564KU,19969
-nextrec/utils/console.py,sha256=e94SiwA0gKn2pfpP94mY_jl-kFok3TCjxo298KdFuP4,11696
+nextrec/utils/config.py,sha256=VgCh5fto8HGodwXPJacenqjxre3Aw6tw-mntW9n3OYA,20044
+nextrec/utils/console.py,sha256=u-hq_VcA62B0HPok12pnLOf9aI8B3Hjyg0ysMrOBOxI,13220
 nextrec/utils/data.py,sha256=alruiWZFbmwy3kO12q42VXmtHmXFFjVULpHa43fx_mI,21098
 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/torch_utils.py,sha256=AKfYbSOJjEw874xsDB5IO3Ote4X7vnqzt_E0jJny0o8,13468
-nextrec-0.4.14.dist-info/METADATA,sha256=HDpc5CcuuuVeBhmTwZTCEJw1T_w0GgA7K5CaL-N1Kq8,21103
-nextrec-0.4.14.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-nextrec-0.4.14.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
-nextrec-0.4.14.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
-nextrec-0.4.14.dist-info/RECORD,,
+nextrec-0.4.16.dist-info/METADATA,sha256=21yLJcEh_Y70_gsTysLVt6X8l-YN15x9AX99x0wVB-o,21298
+nextrec-0.4.16.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+nextrec-0.4.16.dist-info/entry_points.txt,sha256=NN-dNSdfMRTv86bNXM7d3ZEPW2BQC6bRi7QP7i9cIps,45
+nextrec-0.4.16.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
+nextrec-0.4.16.dist-info/RECORD,,