nextrec 0.3.4__tar.gz → 0.3.5__tar.gz

{nextrec-0.3.4 → nextrec-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextrec
-Version: 0.3.4
+Version: 0.3.5
 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
@@ -63,7 +63,7 @@ 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-0.3.4-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.3.5-orange.svg)
 
 English | [中文文档](README_zh.md)
 
@@ -110,7 +110,7 @@ To dive deeper, Jupyter notebooks are available:
 - [Hands on the NextRec framework](/tutorials/notebooks/en/Hands%20on%20nextrec.ipynb)
 - [Using the data processor for preprocessing](/tutorials/notebooks/en/Hands%20on%20dataprocessor.ipynb)
 
-> Current version [0.3.4]: the matching module is not fully polished yet and may have compatibility issues or unexpected errors. Please raise an issue if you run into problems.
+> Current version [0.3.5]: the matching module is not fully polished yet and may have compatibility issues or unexpected errors. Please raise an issue if you run into problems.
 
 ## 5-Minute Quick Start
 

{nextrec-0.3.4 → nextrec-0.3.5}/README.md

@@ -7,7 +7,7 @@
 ![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-0.3.4-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.3.5-orange.svg)
 
 English | [中文文档](README_zh.md)
 
@@ -54,7 +54,7 @@ To dive deeper, Jupyter notebooks are available:
 - [Hands on the NextRec framework](/tutorials/notebooks/en/Hands%20on%20nextrec.ipynb)
 - [Using the data processor for preprocessing](/tutorials/notebooks/en/Hands%20on%20dataprocessor.ipynb)
 
-> Current version [0.3.4]: the matching module is not fully polished yet and may have compatibility issues or unexpected errors. Please raise an issue if you run into problems.
+> Current version [0.3.5]: the matching module is not fully polished yet and may have compatibility issues or unexpected errors. Please raise an issue if you run into problems.
 
 ## 5-Minute Quick Start
 

{nextrec-0.3.4 → nextrec-0.3.5}/README_zh.md

@@ -7,7 +7,7 @@
 ![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-0.3.4-orange.svg)
+![Version](https://img.shields.io/badge/Version-0.3.5-orange.svg)
 
 [English Version](README.md) | 中文文档
 
@@ -54,7 +54,7 @@ NextRec采用模块化、低耦合的工程设计，使得推荐系统从数据
 - [如何上手NextRec框架](/tutorials/notebooks/zh/Hands%20on%20nextrec.ipynb)
 - [如何使用数据处理器进行数据预处理](/tutorials/notebooks/zh/Hands%20on%20dataprocessor.ipynb)
 
-> 当前版本[0.3.4]，召回模型模块尚不完善，可能存在一些兼容性问题或意外报错，如果遇到问题，欢迎开发者在Issue区提出问题。
+> 当前版本[0.3.5]，召回模型模块尚不完善，可能存在一些兼容性问题或意外报错，如果遇到问题，欢迎开发者在Issue区提出问题。
 
 ## 5分钟快速上手
 

{nextrec-0.3.4 → nextrec-0.3.5}/docs/rtd/conf.py

@@ -11,7 +11,7 @@ sys.path.insert(0, str(PROJECT_ROOT / "nextrec"))
 project = "NextRec"
 copyright = "2025, Yang Zhou"
 author = "Yang Zhou"
-release = "0.3.4"
+release = "0.3.5"
 
 extensions = [
     "myst_parser",

nextrec-0.3.5/nextrec/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.3.5"

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/basic/features.py

@@ -7,7 +7,7 @@ Author: Yang Zhou, zyaztec@gmail.com
 """
 import torch
 from nextrec.utils.embedding import get_auto_embedding_dim
-from nextrec.utils.common import normalize_to_list
+from nextrec.utils.feature import normalize_to_list
 
 class BaseFeature(object):
     def __repr__(self):

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/basic/model.py

@@ -31,10 +31,12 @@ from nextrec.basic.session import resolve_save_path, create_session
 from nextrec.basic.metrics import configure_metrics, evaluate_metrics, check_user_id
 
 from nextrec.data.dataloader import build_tensors_from_data
-from nextrec.data.data_utils import get_column_data, collate_fn, batch_to_dict, get_user_ids
+from nextrec.data.data_processing import get_column_data, get_user_ids
+from nextrec.data.batch_utils import collate_fn, batch_to_dict
 
 from nextrec.loss import get_loss_fn, get_loss_kwargs
-from nextrec.utils import get_optimizer, get_scheduler, to_tensor
+from nextrec.utils import get_optimizer, get_scheduler
+from nextrec.utils.tensor import to_tensor
 
 from nextrec import __version__
 

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/basic/session.py

@@ -1,14 +1,5 @@
 """Session and experiment utilities.
 
-This module centralizes session/experiment management so the rest of the
-framework writes all artifacts to a consistent location:: <pwd>/log/<experiment_id>/
-
-Within that folder we keep model parameters, checkpoints, training metrics,
-evaluation metrics, and consolidated log output. When users do not provide an
-``experiment_id`` a timestamp-based identifier is generated once per process to
-avoid scattering files across multiple directories. Test runs are redirected to
-temporary folders so local trees are not polluted.
-
 Date: create on 23/11/2025
 Author: Yang Zhou,zyaztec@gmail.com
 """
@@ -16,7 +7,7 @@ Author: Yang Zhou,zyaztec@gmail.com
 import os
 import tempfile
 from dataclasses import dataclass
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 
 __all__ = [
@@ -74,6 +65,7 @@ def create_session(experiment_id: str | Path | None = None) -> Session:
     if experiment_id is not None and str(experiment_id).strip():
         exp_id = str(experiment_id).strip()
     else:
+        # Use local time for session naming
         exp_id = "nextrec_session_" + datetime.now().strftime("%Y%m%d")
 
     if (
@@ -111,6 +103,7 @@ def resolve_save_path(
       timestamp.
     - Parent directories are created.
     """
+    # Use local time for file timestamps
     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") if add_timestamp else None
 
     normalized_suffix = suffix if suffix.startswith(".") else f".{suffix}"

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/data/__init__.py

@@ -1,48 +1,86 @@
 """
 Data utilities package for NextRec
 
-This package provides data processing and manipulation utilities.
+This package provides data processing and manipulation utilities organized by category:
+- batch_utils: Batch collation and processing
+- data_processing: Data manipulation and user ID extraction
+- data_utils: Legacy module (re-exports from specialized modules)
+- dataloader: Dataset and DataLoader implementations
+- preprocessor: Data preprocessing pipeline
 
 Date: create on 13/11/2025
+Last update: 03/12/2025 (refactored)
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
-from nextrec.data.data_utils import (
-    collate_fn,
+# Batch utilities
+from nextrec.data.batch_utils import collate_fn, batch_to_dict, stack_section
+
+# Data processing utilities
+from nextrec.data.data_processing import (
     get_column_data,
-    default_output_dir,
     split_dict_random,
     build_eval_candidates,
+    get_user_ids,
+)
+
+# File utilities (from utils package)
+from nextrec.utils.file import (
     resolve_file_paths,
     iter_file_chunks,
     read_table,
     load_dataframes,
+    default_output_dir,
 )
-from nextrec.basic.features import FeatureSet
-from nextrec.data import data_utils
+
+# DataLoader components
 from nextrec.data.dataloader import (
     TensorDictDataset,
     FileDataset,
     RecDataLoader,
     build_tensors_from_data,
 )
+
+# Preprocessor
 from nextrec.data.preprocessor import DataProcessor
 
+# Feature definitions
+from nextrec.basic.features import FeatureSet
+
+# Legacy module (for backward compatibility)
+from nextrec.data import data_utils
+
 __all__ = [
+    # Batch utilities
     'collate_fn',
+    'batch_to_dict',
+    'stack_section',
+    
+    # Data processing
     'get_column_data',
-    'default_output_dir',
     'split_dict_random',
     'build_eval_candidates',
+    'get_user_ids',
+    
+    # File utilities
     'resolve_file_paths',
     'iter_file_chunks',
     'read_table',
     'load_dataframes',
-    'FeatureSet',
-    'data_utils',
+    'default_output_dir',
+    
+    # DataLoader
     'TensorDictDataset',
     'FileDataset',
     'RecDataLoader',
     'build_tensors_from_data',
+    
+    # Preprocessor
     'DataProcessor',
+    
+    # Features
+    'FeatureSet',
+    
+    # Legacy module
+    'data_utils',
 ]

nextrec-0.3.5/nextrec/data/batch_utils.py

@@ -0,0 +1,80 @@
+"""
+Batch collation utilities for NextRec
+
+Date: create on 03/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
+"""
+
+import torch
+import numpy as np
+from typing import Any, Mapping
+
+def stack_section(batch: list[dict], section: str):
+    entries = [item.get(section) for item in batch if item.get(section) is not None]
+    if not entries:
+        return None
+    merged: dict = {}
+    for name in entries[0]:  # type: ignore
+        tensors = [item[section][name] for item in batch if item.get(section) is not None and name in item[section]]
+        merged[name] = torch.stack(tensors, dim=0)
+    return merged
+
+def collate_fn(batch):
+    """
+    Collate a list of sample dicts into the unified batch format:
+    {
+        "features": {name: Tensor(B, ...)},
+        "labels": {target: Tensor(B, ...)} or None,
+        "ids": {id_name: Tensor(B, ...)} or None,
+    }
+    Args: batch: List of samples from DataLoader
+        
+    Returns: dict: Batched data in unified format
+    """
+    if not batch:
+        return {"features": {}, "labels": None, "ids": None}
+
+    first = batch[0]
+    if isinstance(first, dict) and "features" in first:
+        # Streaming dataset yields already-batched chunks; avoid adding an extra dim.
+        if first.get("_already_batched") and len(batch) == 1:
+            return {
+                "features": first.get("features", {}),
+                "labels": first.get("labels"),
+                "ids": first.get("ids"),
+            }
+        return {
+            "features": stack_section(batch, "features") or {},
+            "labels": stack_section(batch, "labels"),
+            "ids": stack_section(batch, "ids"),
+        }
+
+    # Fallback: stack tuples/lists of tensors
+    num_tensors = len(first)
+    result = []
+    for i in range(num_tensors):
+        tensor_list = [item[i] for item in batch]
+        first_item = tensor_list[0]
+        if isinstance(first_item, torch.Tensor):
+            stacked = torch.cat(tensor_list, dim=0)
+        elif isinstance(first_item, np.ndarray):
+            stacked = np.concatenate(tensor_list, axis=0)
+        elif isinstance(first_item, list):
+            combined = []
+            for entry in tensor_list:
+                combined.extend(entry)
+            stacked = combined
+        else:
+            stacked = tensor_list
+        result.append(stacked)
+    return tuple(result)
+
+
+def batch_to_dict(batch_data: Any, include_ids: bool = True) -> dict:
+    if not (isinstance(batch_data, Mapping) and "features" in batch_data):
+        raise TypeError("[BaseModel-batch_to_dict Error] Batch data must be a dict with 'features' produced by the current DataLoader.")
+    return {
+        "features": batch_data.get("features", {}),
+        "labels": batch_data.get("labels"),
+        "ids": batch_data.get("ids") if include_ids else None,
+    }

nextrec-0.3.5/nextrec/data/data_processing.py

@@ -0,0 +1,152 @@
+"""
+Data processing utilities for NextRec
+
+Date: create on 03/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
+"""
+
+import torch
+import numpy as np
+import pandas as pd
+from typing import Any, Mapping
+
+
+def get_column_data(data: dict | pd.DataFrame, name: str):
+    if isinstance(data, dict):
+        return data[name] if name in data else None
+    elif isinstance(data, pd.DataFrame):
+        if name not in data.columns:
+            return None
+        return data[name].values
+    else:
+        if hasattr(data, name):
+            return getattr(data, name)
+        raise KeyError(f"Unsupported data type for extracting column {name}")
+
+def split_dict_random(
+    data_dict: dict,
+    test_size: float = 0.2,
+    random_state: int | None = None
+):
+    lengths = [len(v) for v in data_dict.values()]
+    if len(set(lengths)) != 1:
+        raise ValueError(f"Length mismatch: {lengths}")
+    
+    n = lengths[0]
+    rng = np.random.default_rng(random_state)
+    perm = rng.permutation(n)
+    cut = int(round(n * (1 - test_size)))
+    train_idx, test_idx = perm[:cut], perm[cut:]
+    
+    def take(v, idx):
+        if isinstance(v, np.ndarray):
+            return v[idx]
+        elif isinstance(v, pd.Series):
+            return v.iloc[idx].to_numpy()
+        else:
+            v_arr = np.asarray(v, dtype=object)
+            return v_arr[idx]
+    
+    train_dict = {k: take(v, train_idx) for k, v in data_dict.items()}
+    test_dict = {k: take(v, test_idx) for k, v in data_dict.items()}
+    return train_dict, test_dict
+
+
+def build_eval_candidates(
+    df_all: pd.DataFrame,
+    user_col: str,
+    item_col: str,
+    label_col: str,
+    user_features: pd.DataFrame,
+    item_features: pd.DataFrame,
+    num_pos_per_user: int = 5,
+    num_neg_per_pos: int = 50,
+    random_seed: int = 2025,
+) -> pd.DataFrame:
+    """
+    Build evaluation candidates with positive and negative samples for each user.
+    
+    Args:
+        df_all: Full interaction DataFrame
+        user_col: Name of the user ID column
+        item_col: Name of the item ID column
+        label_col: Name of the label column
+        user_features: DataFrame containing user features
+        item_features: DataFrame containing item features
+        num_pos_per_user: Number of positive samples per user (default: 5)
+        num_neg_per_pos: Number of negative samples per positive (default: 50)
+        random_seed: Random seed for reproducibility (default: 2025)
+        
+    Returns:
+        pd.DataFrame: Evaluation candidates with features
+    """
+    rng = np.random.default_rng(random_seed)
+
+    users = df_all[user_col].unique()
+    all_items = item_features[item_col].unique()
+    rows = []
+    user_hist_items = {u: df_all[df_all[user_col] == u][item_col].unique() for u in users}
+    
+    for u in users:
+        df_user = df_all[df_all[user_col] == u]
+        pos_items = df_user[df_user[label_col] == 1][item_col].unique()
+        if len(pos_items) == 0:
+            continue
+        pos_items = pos_items[:num_pos_per_user]
+        seen_items = set(user_hist_items[u])
+        neg_pool = np.setdiff1d(all_items, np.fromiter(seen_items, dtype=all_items.dtype))
+        if len(neg_pool) == 0:
+            continue
+        for pos in pos_items:
+            if len(neg_pool) <= num_neg_per_pos:
+                neg_items = neg_pool
+            else:
+                neg_items = rng.choice(neg_pool, size=num_neg_per_pos, replace=False)
+            rows.append((u, pos, 1))
+            for ni in neg_items:
+                rows.append((u, ni, 0))
+    
+    eval_df = pd.DataFrame(rows, columns=[user_col, item_col, label_col])
+    eval_df = eval_df.merge(user_features, on=user_col, how='left')
+    eval_df = eval_df.merge(item_features, on=item_col, how='left')
+    return eval_df
+
+
+def get_user_ids(
+    data: Any,
+    id_columns: list[str] | str | None = None
+) -> np.ndarray | None:
+    """
+    Extract user IDs from various data structures.
+    
+    Args:
+        data: Data source (DataFrame, dict, or batch dict)
+        id_columns: List or single ID column name(s) (default: None)
+        
+    Returns:
+        np.ndarray | None: User IDs as numpy array, or None if not found
+    """
+    id_columns = (
+        id_columns if isinstance(id_columns, list)
+        else [id_columns] if isinstance(id_columns, str)
+        else []
+    )
+    if not id_columns:
+        return None
+
+    main_id = id_columns[0]
+    if isinstance(data, pd.DataFrame) and main_id in data.columns:
+        arr = np.asarray(data[main_id].values)
+        return arr.reshape(arr.shape[0])
+    
+    if isinstance(data, dict):
+        ids_container = data.get("ids")
+        if isinstance(ids_container, dict) and main_id in ids_container:
+            val = ids_container[main_id]
+            val = val.detach().cpu().numpy() if isinstance(val, torch.Tensor) else np.asarray(val)
+            return val.reshape(val.shape[0])
+        if main_id in data:
+            arr = np.asarray(data[main_id])
+            return arr.reshape(arr.shape[0])
+
+    return None

nextrec-0.3.5/nextrec/data/data_utils.py

@@ -0,0 +1,35 @@
+"""
+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
+
+Date: create on 27/10/2025
+Last update: 03/12/2025 (refactored)
+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.data_processing import get_column_data, split_dict_random, build_eval_candidates, get_user_ids
+from nextrec.utils.file import resolve_file_paths, iter_file_chunks, read_table, load_dataframes, default_output_dir
+
+__all__ = [
+    # Batch utilities
+    'collate_fn',
+    'batch_to_dict',
+    'stack_section',
+    # Data processing
+    'get_column_data',
+    'split_dict_random',
+    'build_eval_candidates',
+    'get_user_ids',
+    # File utilities
+    'resolve_file_paths',
+    'iter_file_chunks',
+    'read_table',
+    'load_dataframes',
+    'default_output_dir',
+]

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/data/dataloader.py

@@ -20,8 +20,10 @@ from nextrec.data.preprocessor import DataProcessor
 from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature, FeatureSet
 
 from nextrec.basic.loggers import colorize
-from nextrec.data import get_column_data, collate_fn, resolve_file_paths, read_table
-from nextrec.utils import to_tensor
+from nextrec.data.data_processing import get_column_data
+from nextrec.data.batch_utils import collate_fn
+from nextrec.utils.file import resolve_file_paths, read_table
+from nextrec.utils.tensor import to_tensor
 
 class TensorDictDataset(Dataset):
     """Dataset returning sample-level dicts matching the unified batch schema."""

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/data/preprocessor.py

@@ -16,24 +16,14 @@ import pandas as pd
 import tqdm
 from pathlib import Path
 from typing import Dict, Union, Optional, Literal, Any
-from sklearn.preprocessing import (
-    StandardScaler, 
-    MinMaxScaler, 
-    RobustScaler, 
-    MaxAbsScaler,
-    LabelEncoder
-)
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler, MaxAbsScaler, LabelEncoder
+
 
-from nextrec.basic.loggers import setup_logger, colorize
-from nextrec.data.data_utils import (
-    resolve_file_paths,
-    iter_file_chunks,
-    read_table,
-    load_dataframes,
-    default_output_dir,
-)
-from nextrec.basic.session import resolve_save_path
 from nextrec.basic.features import FeatureSet
+from nextrec.basic.loggers import colorize
+from nextrec.basic.session import resolve_save_path
+from nextrec.utils.file import resolve_file_paths, iter_file_chunks, read_table, load_dataframes, default_output_dir
+
 from nextrec.__version__ import __version__
 
 

{nextrec-0.3.4 → nextrec-0.3.5}/nextrec/models/multi_task/poso.py

@@ -46,7 +46,7 @@ from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
 from nextrec.basic.activation import activation_layer
 from nextrec.basic.model import BaseModel
-from nextrec.utils.common import merge_features
+from nextrec.utils.model import merge_features
 
 
 class POSOGate(nn.Module):

nextrec-0.3.5/nextrec/utils/__init__.py

@@ -0,0 +1,68 @@
+"""
+Utilities package for NextRec
+
+This package provides various utility functions organized by category:
+- optimizer: Optimizer and scheduler utilities
+- initializer: Weight initialization utilities
+- embedding: Embedding dimension calculation
+- device_utils: Device management and selection
+- tensor_utils: Tensor operations and conversions
+- file_utils: File I/O operations
+- model_utils: Model-related utilities
+- feature_utils: Feature processing utilities
+
+Date: create on 13/11/2025
+Last update: 03/12/2025 (refactored)
+Author: Yang Zhou, zyaztec@gmail.com
+"""
+
+from .optimizer import get_optimizer, get_scheduler
+from .initializer import get_initializer
+from .embedding import get_auto_embedding_dim
+from .device import resolve_device, get_device_info
+from .tensor import to_tensor, stack_tensors, concat_tensors, pad_sequence_tensors
+from .file import resolve_file_paths, read_table, load_dataframes, iter_file_chunks, default_output_dir
+from .model import merge_features, get_mlp_output_dim
+from .feature import normalize_to_list
+from . import optimizer, initializer, embedding
+
+__all__ = [
+    # Optimizer & Scheduler
+    'get_optimizer',
+    'get_scheduler',
+    
+    # Initializer
+    'get_initializer',
+    
+    # Embedding
+    'get_auto_embedding_dim',
+    
+    # Device utilities
+    'resolve_device',
+    'get_device_info',
+    
+    # Tensor utilities
+    'to_tensor',
+    'stack_tensors',
+    'concat_tensors',
+    'pad_sequence_tensors',
+    
+    # File utilities
+    'resolve_file_paths',
+    'read_table',
+    'load_dataframes',
+    'iter_file_chunks',
+    'default_output_dir',
+    
+    # Model utilities
+    'merge_features',
+    'get_mlp_output_dim',
+    
+    # Feature utilities
+    'normalize_to_list',
+    
+    # Module exports
+    'optimizer',
+    'initializer',
+    'embedding',
+]

nextrec-0.3.5/nextrec/utils/device.py

@@ -0,0 +1,37 @@
+"""
+Device management utilities for NextRec
+
+Date: create on 03/12/2025
+Author: Yang Zhou, zyaztec@gmail.com
+"""
+
+import torch
+import platform
+
+
+def resolve_device() -> str:
+    if torch.cuda.is_available():
+        return "cuda"
+    if torch.backends.mps.is_available():
+        mac_ver = platform.mac_ver()[0]
+        try:
+            major, minor = (int(x) for x in mac_ver.split(".")[:2])
+        except Exception:
+            major, minor = 0, 0
+        if major >= 14:
+            return "mps"
+    return "cpu"
+
+def get_device_info() -> dict:
+    info = {
+        'cuda_available': torch.cuda.is_available(),
+        'cuda_device_count': torch.cuda.device_count() if torch.cuda.is_available() else 0,
+        'mps_available': torch.backends.mps.is_available(),
+        'current_device': resolve_device(),
+    }
+    
+    if torch.cuda.is_available():
+        info['cuda_device_name'] = torch.cuda.get_device_name(0)
+        info['cuda_capability'] = torch.cuda.get_device_capability(0)
+    
+    return info