format code && add dependabot && update CI/CD && update test files

.github/workflows/ci.yml

@@ -57,12 +57,12 @@ jobs:
         run: |
           pip install --upgrade pip
           # 安装特定版本的格式化工具以确保一致性
-          pip install yapf==0.32.0 isort==5.10.1 flake8>=3.8.0 mypy>=0.800
+          pip install yapf==0.32.0 isort==5.10.1 flake8>=3.8.0 mypy>=0.800 toml>=0.10.2
 
       - name: Format & Lint
         run: |
           # 步骤1: isort
-          isort torch_rechub/ examples/ tests/
+          isort --profile black torch_rechub/ examples/ tests/
           # 步骤2: yapf
           yapf_style="{based_on_style: google, column_limit: 248, join_multiple_lines: false, split_all_comma_separated_values: true, split_before_logical_operator: true, dedent_closing_brackets: true, align_closing_bracket_with_visual_indent: true, indent_width: 4}"
           yapf --in-place --recursive --style="$yapf_style" torch_rechub/ examples/ tests/

.pre-commit-config.yaml

@@ -26,7 +26,7 @@ repos:
     hooks:
       - id: yapf
         name: yapf (Python代码格式化)
-        args: [--style=config/.style.yapf, --in-place]
+        args: [--style=pyproject.toml, --in-place]
         additional_dependencies: []
 
   # isort - 导入语句排序

config/.flake8

@@ -1,36 +1,73 @@
 [flake8]
+# 基本配置
 max-line-length = 248
-extend-ignore =
+max-complexity = 30
+exclude = 
+    .git,
+    __pycache__,
+    docs/,
+    build/,
+    dist/,
+    .eggs/,
+    *.egg-info/,
+    htmlcov/,
+    .pytest_cache/,
+    .mypy_cache/,
+    .tox/,
+    .venv/,
+    venv/,
+    env/
+
+# 忽略的错误代码
+ignore = 
+    # E203: whitespace before ':' (与Black格式化工具冲突)
     E203,
+    # W503: line break before binary operator (已过时的规则)
     W503,
+    # E501: line too long (我们用248字符限制)
     E501,
+    # E722: do not use bare except (有时确实需要)
     E722,
+    # E402: module level import not at top of file
     E402,
+    # F821: undefined name (有时是动态导入)
     F821,
+    # F523: '...'.format(...) has unused arguments
     F523,
+    # E711: comparison to None should be 'if cond is None:'
     E711,
+    # E741: ambiguous variable name
     E741,
+    # F401: imported but unused (在__init__.py中常见)
     F401,
+    # E265: block comment should start with '# '
     E265,
+    # C901: too complex (已通过max-complexity设置)
     C901,
+    # E301: expected 1 blank line, found 0
     E301,
+    # E305: expected 2 blank lines after class or function definition
     E305,
+    # W293: blank line contains whitespace
     W293,
+    # E261: at least two spaces before inline comment
     E261,
+    # W291: trailing whitespace
     W291,
+    # W292: no newline at end of file
     W292,
+    # E111: indentation is not a multiple of four
     E111,
+    # E117: over-indented
     E117,
+    # F841: local variable is assigned to but never used
     F841,
+    # E302: expected 2 blank lines, found 1
     E302
-exclude =
-    .git,
-    __pycache__,
-    build,
-    dist,
-    .venv,
-    venv,
-    .eggs,
-    *.egg
-max-complexity = 30
-docstring-convention = google
+
+# 每个文件的最大导入数
+max-imports = 30
+
+# 统计信息
+statistics = True
+count = True

config/.pep8

@@ -1,3 +1,4 @@
 [pep8]
 max-line-length = 248
 ignore = E402
+

config/format_code.py

@@ -28,7 +28,7 @@ def main():
 
     # 阶段一: isort
     print("\n--- 阶段一: 使用 isort 排序导入 ---")
-    isort_command = [sys.executable, '-m', 'isort'] + source_dirs
+    isort_command = [sys.executable, '-m', 'isort', '--profile', 'black'] + source_dirs
     run_command(isort_command, "isort")
 
     # 阶段二: yapf

config/pytest.ini

@@ -5,39 +5,72 @@
 # pytest是Python最流行的测试框架，支持单元测试、集成测试等
 # 更多配置说明请参考: config/CONFIG_GUIDE.md
 
-[tool:pytest]
-# 测试目录 - pytest会在这些目录中查找测试文件
+[pytest]
+# pytest配置文件
+# 用于测试运行的配置
+
+# 最小版本要求
+minversion = 6.0
+
+# 命令行选项
+addopts = 
+    -ra
+    -q
+    --strict-markers
+    --tb=short
+    --maxfail=3
+    -v
+
+# 测试路径
 testpaths = tests
 
-# 测试文件模式 - 匹配以test_开头的Python文件
-python_files = test_*.py
+# Python文件模式
+python_files = 
+    test_*.py
+    *_test.py
 
-# 测试类模式 - 匹配以Test开头的类
+# Python类模式
 python_classes = Test*
 
-# 测试函数模式 - 匹配以test_开头的函数
+# Python函数模式
 python_functions = test_*
 
-# 附加选项 - 控制pytest的行为
-addopts = 
-    --strict-markers        # 严格标记模式，未定义的标记会报错
-    --strict-config         # 严格配置模式，配置错误会报错
-    --verbose               # 详细输出模式
-    --tb=short             # 简短的回溯信息
-    --cov=torch_rechub     # 代码覆盖率分析 - 分析torch_rechub包
-    --cov-report=term-missing:skip-covered  # 终端报告，显示未覆盖的行
-    --cov-report=html      # HTML格式的覆盖率报告
-    --cov-report=xml       # XML格式的覆盖率报告 (CI/CD使用)
-    --cov-branch           # 分支覆盖率分析
-
-# 自定义标记 - 用于分类和选择测试
+# 标记定义
 markers =
-    slow: marks tests as slow (deselect with '-m "not slow"')
-        # 标记慢速测试，可用 pytest -m "not slow" 跳过
-    integration: marks tests as integration tests
-        # 标记集成测试
-    unit: marks tests as unit tests
-        # 标记单元测试
+    slow: 标记为慢速测试 (使用 '-m "not slow"' 排除)
+    integration: 标记为集成测试
+    unit: 标记为单元测试
+    e2e: 标记为端到端测试
+
+# 覆盖率设置
+[coverage:run]
+source = torch_rechub
+omit = 
+    */tests/*
+    */examples/*
+    */docs/*
+    */__pycache__/*
+    */htmlcov/*
+
+[coverage:report]
+# 排除的行
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    if self\.debug:
+    if __name__ == .__main__.:
+    raise AssertionError
+    raise NotImplementedError
+    pass
+
+# 精度设置
+precision = 2
+
+# 显示缺失的行
+show_missing = True
+
+# 跳过覆盖的文件
+skip_covered = False
 
 # 过滤警告 - 忽略特定类型的警告
 filterwarnings =

examples/matching/run_ml_comirec.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import ComirecDR, ComirecSA
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_dssm.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import DSSM
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_facebook_dssm.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import FaceBookDSSM
 from torch_rechub.trainers import MatchTrainer
-from torch_rechub.utils.data import (MatchDataGenerator, array_replace_with_dict, df_to_dict)
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.data import MatchDataGenerator, array_replace_with_dict, df_to_dict
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_gru4rec.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import GRU4Rec
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_mind.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import MIND
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_sine.py

@@ -10,7 +10,7 @@
 from torch_rechub.models.matching import SINE
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_youtube_dnn.py

@@ -7,11 +7,11 @@
 from movielens_utils import match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import YoutubeDNN
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_ml_youtube_sbc.py

@@ -8,11 +8,11 @@
 from movielens_utils import get_item_sample_weight, match_evaluation
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.matching import YoutubeSBC
 from torch_rechub.trainers import MatchTrainer
 from torch_rechub.utils.data import MatchDataGenerator, df_to_dict
-from torch_rechub.utils.match import (gen_model_input, generate_seq_feature_match)
+from torch_rechub.utils.match import gen_model_input, generate_seq_feature_match
 
 sys.path.append("../..")
 

examples/matching/run_sbr.py

@@ -7,7 +7,7 @@
 import pandas as pd
 import torch
 import torch.nn.utils.rnn as rnn_utils
-from data.session_based.preprocess_session_based import (INTERNAL_ITEM_ID_FIELD, TEST_DATA_PREFIX, TRAIN_DATA_PREFIX)
+from data.session_based.preprocess_session_based import INTERNAL_ITEM_ID_FIELD, TEST_DATA_PREFIX, TRAIN_DATA_PREFIX
 from torch.utils.data import DataLoader
 
 from torch_rechub.basic.features import SequenceFeature

examples/ranking/run_amazon_electronics.py

@@ -4,10 +4,10 @@
 import pandas as pd
 import torch
 
-from torch_rechub.basic.features import (DenseFeature, SequenceFeature, SparseFeature)
+from torch_rechub.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from torch_rechub.models.ranking import DIN
 from torch_rechub.trainers import CTRTrainer
-from torch_rechub.utils.data import (DataGenerator, df_to_dict, generate_seq_feature, pad_sequences)
+from torch_rechub.utils.data import DataGenerator, df_to_dict, generate_seq_feature, pad_sequences
 
 sys.path.append("../..")
 

examples/ranking/run_avazu.py

@@ -7,7 +7,7 @@
 from tqdm import tqdm
 
 from torch_rechub.basic.features import DenseFeature, SparseFeature
-from torch_rechub.models.ranking import (DCN, DeepFFM, DeepFM, FatDeepFFM, WideDeep)
+from torch_rechub.models.ranking import DCN, DeepFFM, DeepFM, FatDeepFFM, WideDeep
 from torch_rechub.trainers import CTRTrainer
 from torch_rechub.utils.data import DataGenerator
 

examples/ranking/run_criteo.py

@@ -7,7 +7,7 @@
 from tqdm import tqdm
 
 from torch_rechub.basic.features import DenseFeature, SparseFeature
-from torch_rechub.models.ranking import (DCN, EDCN, DCNv2, DeepFFM, DeepFM, FatDeepFFM, FiBiNet, WideDeep)
+from torch_rechub.models.ranking import DCN, EDCN, DCNv2, DeepFFM, DeepFM, FatDeepFFM, FiBiNet, WideDeep
 from torch_rechub.trainers import CTRTrainer
 from torch_rechub.utils.data import DataGenerator