Add black, isort and pre-commit

Toloka · Oct 3, 2023 · 2e36dae · 2e36dae
1 parent e9b83b5
commit 2e36dae
Show file tree

Hide file tree

Showing 89 changed files with 3,753 additions and 2,309 deletions.
diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml
@@ -2,4 +2,4 @@ blank_issues_enabled: false
 contact_links:
   - name: Toloka Global Community
     url: https://toloka.ai/community/
-    about: Any other issue, including usage questions and technical assistance
+    about: Any other issue, including usage questions and technical assistance
diff --git a/.github/ISSUE_TEMPLATE/feature_request_template.yml b/.github/ISSUE_TEMPLATE/feature_request_template.yml
@@ -57,4 +57,4 @@ body:
         Add any additional information you think will be helpful to better
         understand the feature you are proposing.
     validations:
-      required: false
+      required: false
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -22,8 +22,8 @@ jobs:
           pipenv install --python "${{ matrix.python-version }}" --dev --system --skip-lock
       - name: Lint with Mypy
         run: mypy crowdkit tests
-      - name: Lint with flake8
-        run: flake8
+      - name: Pre-Commit Check
+        uses: pre-commit/[email protected]
       - name: Test with pytest
         run: coverage run --source crowdkit -m pytest
       - name: Codecov

diff --git a/.isort.cfg b/.isort.cfg
@@ -0,0 +1,3 @@
+[settings]
+profile=black
+src_paths=crowdkit,tests
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,20 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v3.2.0
+  hooks:
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+  - id: check-yaml
+  - id: check-added-large-files
+- repo: https://github.com/psf/black
+  rev: 23.3.0
+  hooks:
+  - id: black
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+  - id: isort
+- repo: https://github.com/pycqa/flake8
+  rev: 6.0.0
+  hooks:
+  - id: flake8
diff --git a/crowdkit/__init__.py b/crowdkit/__init__.py
@@ -1,5 +1,5 @@
 from typing import List
 
-__version__ = '1.2.1'
+__version__ = "1.2.1"
 
 __all__: List[str] = []
diff --git a/crowdkit/aggregation/__init__.py b/crowdkit/aggregation/__init__.py
@@ -2,69 +2,58 @@
 
 from . import base
 from .classification import (
-    DawidSkene,
     GLAD,
-    GoldMajorityVote,
     KOS,
     MACE,
-    MajorityVote,
     MMSR,
+    DawidSkene,
+    GoldMajorityVote,
+    MajorityVote,
     OneCoinDawidSkene,
     Wawa,
-    ZeroBasedSkill
-)
-from .multilabel import BinaryRelevance
-from .embeddings import (
-    ClosestToAverage,
-    HRRASA,
-    RASA,
+    ZeroBasedSkill,
 )
+from .embeddings import HRRASA, RASA, ClosestToAverage
 from .image_segmentation import (
     SegmentationEM,
+    SegmentationMajorityVote,
     SegmentationRASA,
-    SegmentationMajorityVote
-)
-from .pairwise import (
-    BradleyTerry,
-    NoisyBradleyTerry
-)
-from .texts import (
-    TextRASA,
-    TextHRRASA,
-    ROVER
 )
+from .multilabel import BinaryRelevance
+from .pairwise import BradleyTerry, NoisyBradleyTerry
+from .texts import ROVER, TextHRRASA, TextRASA
 
 __all__ = [
-    'base',
-
-    'BradleyTerry',
-    'ClosestToAverage',
-    'DawidSkene',
-    'OneCoinDawidSkene',
-    'GLAD',
-    'GoldMajorityVote',
-    'HRRASA',
-    'KOS',
-    'MACE',
-    'MMSR',
-    'MajorityVote',
-    'NoisyBradleyTerry',
-    'RASA',
-    'ROVER',
-    'SegmentationEM',
-    'SegmentationMajorityVote',
-    'SegmentationRASA',
-    'TextHRRASA',
-    'TextRASA',
-    'Wawa',
-    'ZeroBasedSkill',
-    'BinaryRelevance'
+    "base",
+    "BradleyTerry",
+    "ClosestToAverage",
+    "DawidSkene",
+    "OneCoinDawidSkene",
+    "GLAD",
+    "GoldMajorityVote",
+    "HRRASA",
+    "KOS",
+    "MACE",
+    "MMSR",
+    "MajorityVote",
+    "NoisyBradleyTerry",
+    "RASA",
+    "ROVER",
+    "SegmentationEM",
+    "SegmentationMajorityVote",
+    "SegmentationRASA",
+    "TextHRRASA",
+    "TextRASA",
+    "Wawa",
+    "ZeroBasedSkill",
+    "BinaryRelevance",
 ]
 
 
 def is_arcadia() -> bool:
     try:
         import __res
+
         return cast(bool, __res == __res)
     except ImportError:
         return False
diff --git a/crowdkit/aggregation/base/__init__.py b/crowdkit/aggregation/base/__init__.py
@@ -1,9 +1,9 @@
 __all__ = [
-    'BaseClassificationAggregator',
-    'BaseImageSegmentationAggregator',
-    'BaseEmbeddingsAggregator',
-    'BaseTextsAggregator',
-    'BasePairwiseAggregator',
+    "BaseClassificationAggregator",
+    "BaseImageSegmentationAggregator",
+    "BaseEmbeddingsAggregator",
+    "BaseTextsAggregator",
+    "BasePairwiseAggregator",
 ]
 
 from typing import Optional
@@ -24,9 +24,9 @@ class BaseClassificationAggregator:
             is the tasks's most likely true label.
     """
 
-    labels_: Optional[pd.Series] = named_series_attrib(name='agg_label')
+    labels_: Optional[pd.Series] = named_series_attrib(name="agg_label")
 
-    def fit(self, data: pd.DataFrame) -> 'BaseClassificationAggregator':
+    def fit(self, data: pd.DataFrame) -> "BaseClassificationAggregator":
         """Args:
             data (DataFrame): Workers' labeling results.
                 A pandas.DataFrame containing `task`, `worker` and `label` columns.
@@ -58,9 +58,9 @@ class BaseImageSegmentationAggregator:
             is the tasks's aggregated segmentation.
     """
 
-    segmentations_: pd.Series = named_series_attrib(name='agg_segmentation')
+    segmentations_: pd.Series = named_series_attrib(name="agg_segmentation")
 
-    def fit(self, data: pd.DataFrame) -> 'BaseImageSegmentationAggregator':
+    def fit(self, data: pd.DataFrame) -> "BaseImageSegmentationAggregator":
         """Args:
             data (DataFrame): Workers' segmentations.
                 A pandas.DataFrame containing `worker`, `task` and `segmentation` columns'.
@@ -93,7 +93,7 @@ class BaseEmbeddingsAggregator:
 
     embeddings_and_outputs_: pd.DataFrame = attr.ib(init=False)
 
-    def fit(self, data: pd.DataFrame) -> 'BaseEmbeddingsAggregator':
+    def fit(self, data: pd.DataFrame) -> "BaseEmbeddingsAggregator":
         """Args:
             data (DataFrame): Workers' outputs with their embeddings.
                 A pandas.DataFrame containing `task`, `worker`, `output` and `embedding` columns.
@@ -122,9 +122,9 @@ class BaseTextsAggregator:
             is the task's text.
     """
 
-    texts_: pd.Series = named_series_attrib(name='agg_text')
+    texts_: pd.Series = named_series_attrib(name="agg_text")
 
-    def fit(self, data: pd.DataFrame) -> 'BaseTextsAggregator':
+    def fit(self, data: pd.DataFrame) -> "BaseTextsAggregator":
         """Args:
             data (DataFrame): Workers' text outputs.
                 A pandas.DataFrame containing `task`, `worker` and `text` columns.
@@ -153,9 +153,9 @@ class BasePairwiseAggregator:
             A pandas.Series index by labels and holding corresponding label's scores
     """
 
-    scores_: pd.Series = named_series_attrib(name='agg_score')
+    scores_: pd.Series = named_series_attrib(name="agg_score")
 
-    def fit(self, data: pd.DataFrame) -> 'BasePairwiseAggregator':
+    def fit(self, data: pd.DataFrame) -> "BasePairwiseAggregator":
         """Args:
             data (DataFrame): Workers' pairwise comparison results.
                 A pandas.DataFrame containing `worker`, `left`, `right`, and `label` columns'.
@@ -168,12 +168,12 @@ def fit(self, data: pd.DataFrame) -> 'BasePairwiseAggregator':
 
     def fit_predict(self, data: pd.DataFrame) -> pd.Series:
         """Args:
-                    data (DataFrame): Workers' pairwise comparison results.
-                        A pandas.DataFrame containing `worker`, `left`, `right`, and `label` columns'.
-                        For each row `label` must be equal to either `left` column or `right` column.
-
-                Returns:
-                    Series: 'Labels' scores.
-                        A pandas.Series index by labels and holding corresponding label's scores
-                """
+            data (DataFrame): Workers' pairwise comparison results.
+                A pandas.DataFrame containing `worker`, `left`, `right`, and `label` columns'.
+                For each row `label` must be equal to either `left` column or `right` column.
+
+        Returns:
+            Series: 'Labels' scores.
+                A pandas.Series index by labels and holding corresponding label's scores
+        """
         raise NotImplementedError()
diff --git a/crowdkit/aggregation/classification/__init__.py b/crowdkit/aggregation/classification/__init__.py
@@ -1,22 +1,22 @@
 __all__ = [
-    'DawidSkene',
-    'GLAD',
-    'GoldMajorityVote',
-    'KOS',
-    'MACE',
-    'MajorityVote',
-    'MMSR',
-    'OneCoinDawidSkene',
-    'Wawa',
-    'ZeroBasedSkill',
+    "DawidSkene",
+    "GLAD",
+    "GoldMajorityVote",
+    "KOS",
+    "MACE",
+    "MajorityVote",
+    "MMSR",
+    "OneCoinDawidSkene",
+    "Wawa",
+    "ZeroBasedSkill",
 ]
 
 from .dawid_skene import DawidSkene, OneCoinDawidSkene
 from .glad import GLAD
 from .gold_majority_vote import GoldMajorityVote
 from .kos import KOS
+from .m_msr import MMSR
 from .mace import MACE
 from .majority_vote import MajorityVote
-from .m_msr import MMSR
 from .wawa import Wawa
 from .zero_based_skill import ZeroBasedSkill