Merge pull request #70 from alxndrkalinin/code-formatting

add black and flake8 to pre-commit and github actions

.flake8

@@ -0,0 +1,12 @@
+[flake8]
+ignore = E203, E501, W503
+exclude =
+    .git,
+    __pycache__,
+    docs/conf.py,
+    old,
+    build,
+    dist
+max-line-length = 88
+max-complexity = 12
+select = B,C,E,F,W,T4,B9

.github/workflows/format.yml

@@ -0,0 +1,41 @@
+name: Code formatting
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  format:
+    name: Black formatting
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@master
+    - name: Setup Python
+      uses: actions/setup-python@master
+      with:
+        python-version: 3.7
+    - name: Update pip
+      run: python -m pip install --upgrade pip
+    - name: Install Black
+      run: pip install black[jupyter]==22.3
+    - name: Run Black
+      run: black --config=black.toml --check .
+
+  lint:
+    name: Flake8 linting
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.7
+    - name: Update pip
+      run: python -m pip install --upgrade pip
+    - name: Install linters
+      run: pip install flake8==4.0.1 flake8-docstrings==1.6.0
+    - name: Run Flake8
+      run: flake8

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.2.0
+    hooks:
+    - id: trailing-whitespace
+    - id: end-of-file-fixer
+    - id: requirements-txt-fixer
+-   repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+    -   id: black
+        args: [--config=black.toml]
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 4.0.1
+    hooks:
+    -   id: flake8
+        additional_dependencies: [flake8-docstrings==1.6.0]

black.toml

@@ -0,0 +1,25 @@
+# Example configuration for Black.
+
+# NOTE: you have to use single-quoted strings in TOML for regular expressions.
+# It's the equivalent of r-strings in Python.  Multiline strings are treated as
+# verbose regular expressions by Black.  Use [ ] to denote a significant space
+# character.
+
+[tool.black]
+target-version = ['py35', 'py36', 'py37', 'py38']
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.eggs
+  | \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+  | .ipynb_checkpoints
+)/
+'''

cytominer_eval/__about__.py

@@ -1,3 +1,4 @@
+"""Information about cytominer_eval."""
 __project__ = "cytominer_eval"
 __author__ = "Gregory Way"
 __version__ = "0.1"

cytominer_eval/__init__.py

@@ -1,3 +1,6 @@
+"""Calculation of quality metrics for perturbation profiling experiments."""
 from .evaluate import evaluate
 from cytominer_eval import __about__
 from cytominer_eval.__about__ import __version__
+
+__all__ = [evaluate, __about__, __version__]

cytominer_eval/evaluate.py

@@ -2,8 +2,6 @@
 
 The primary entrypoint into quickly evaluating profile quality.
 """
-import warnings
-import numpy as np
 import pandas as pd
 from typing import List, Union
 

cytominer_eval/operations/__init__.py

@@ -4,3 +4,12 @@
 from .mp_value import mp_value
 from .enrichment import enrichment
 from .hitk import hitk
+
+__all__ = [
+    replicate_reproducibility,
+    precision_recall,
+    grit,
+    mp_value,
+    enrichment,
+    hitk,
+]

cytominer_eval/operations/enrichment.py

@@ -1,12 +1,10 @@
-"""Function to calculate the enrichment score for a given similarity matrix.
-"""
+"""Function to calculate the enrichment score for a given similarity matrix."""
 import numpy as np
 import pandas as pd
 from typing import List, Union
 import scipy
 
 from cytominer_eval.utils.operation_utils import assign_replicates
-from cytominer_eval.utils.transform_utils import set_pair_ids, assert_melt
 
 
 def enrichment(

cytominer_eval/operations/grit.py

@@ -4,7 +4,6 @@
   with respect to:
 - Similarity to control perturbations
 """
-import numpy as np
 import pandas as pd
 from typing import List
 

cytominer_eval/operations/hitk.py

@@ -1,5 +1,4 @@
-"""Function to calculate the hits at k list and scores for a given similarity matrix.
-"""
+"""Function to calculate the hits at k list and scores for a given similarity matrix."""
 import pandas as pd
 from typing import List, Union
 
@@ -82,7 +81,7 @@ def hitk(
 
     # make a list of the ranks of correct connection (hits), ie where the group_replicate is true
     hits_list = similarity_melted_with_rank[
-        similarity_melted_with_rank["group_replicate"] == True
+        similarity_melted_with_rank["group_replicate"]
     ]["rank"].tolist()
 
     # calculate the scores at each percentage

cytominer_eval/operations/mp_value.py

@@ -12,7 +12,6 @@
    doi: 10.1177/1087057112469257
 """
 
-import numpy as np
 import pandas as pd
 from typing import List
 

cytominer_eval/operations/precision_recall.py

@@ -1,8 +1,5 @@
-"""
-Functions to calculate precision and recall at a given k
-"""
+"""Functions to calculate precision and recall at a given k."""
 
-import numpy as np
 import pandas as pd
 from typing import List, Union
 

cytominer_eval/operations/replicate_reproducibility.py

@@ -1,7 +1,5 @@
-"""Functions to calculate replicate reproducibility
-"""
+"""Functions to calculate replicate reproducibility."""
 
-import numpy as np
 import pandas as pd
 from typing import List
 

cytominer_eval/tests/__init__.py

@@ -0,0 +1 @@
+"""Test cytominer-eval."""

cytominer_eval/tests/test_evaluate.py

@@ -1,7 +1,7 @@
+"""Test evaluate method of cytominer-eval."""
 import os
 import pytest
 import pathlib
-import tempfile
 import numpy as np
 import pandas as pd
 from math import isclose
@@ -115,7 +115,11 @@ def test_evaluate_replicate_reprod_return_cor_true():
 
     assert np.round(med_cor_df.similarity_metric.max(), 3) == 0.949
     assert sorted(med_cor_df.columns.tolist()) == sorted(
-        ["Metadata_gene_name", "Metadata_pert_name", "similarity_metric",]
+        [
+            "Metadata_gene_name",
+            "Metadata_pert_name",
+            "similarity_metric",
+        ]
     )
 
 
@@ -211,7 +215,9 @@ def test_evaluate_grit():
     top_result = (
         grit_results_df.sort_values(by="grit", ascending=False)
         .reset_index(drop=True)
-        .iloc[0,]
+        .iloc[
+            0,
+        ]
     )
     assert np.round(top_result.grit, 4) == 2.3352
     assert top_result.group == "PTK2"
@@ -237,7 +243,9 @@ def test_evaluate_grit():
     top_result = (
         grit_results_df.sort_values(by="grit", ascending=False)
         .reset_index(drop=True)
-        .iloc[0,]
+        .iloc[
+            0,
+        ]
     )
 
     assert np.round(top_result.grit, 4) == 0.9990

cytominer_eval/tests/test_operations/test_enrichment.py

@@ -1,6 +1,5 @@
 import os
 import random
-import pytest
 import pathlib
 import tempfile
 import numpy as np

cytominer_eval/tests/test_operations/test_grit.py

@@ -1,14 +1,10 @@
 import os
-import random
 import pytest
 import pathlib
-import tempfile
 import numpy as np
 import pandas as pd
 from pandas.testing import assert_frame_equal
 
-from sklearn.preprocessing import StandardScaler
-
 from cytominer_eval.operations import grit
 from cytominer_eval.transform import metric_melt
 
@@ -186,7 +182,7 @@ def test_grit_summary_metric():
     )
 
     with pytest.raises(ValueError) as ve:
-        output = grit(
+        grit(
             similarity_melted_df=similarity_melted_df,
             control_perts=control_perts,
             profile_col=profile_col,

cytominer_eval/tests/test_operations/test_hitk.py

@@ -106,8 +106,7 @@ def test_hitk_list():
 
 
 def test_number_of_hits():
-    """Calculates the number of indexes based off the MOA value count in the original df
-    """
+    """Calculates the number of indexes based off the MOA value count in the original df"""
     s = sum([n * (n - 1) for n in df["Metadata_moa"].value_counts()])
     assert s == len(index_list)
 

cytominer_eval/tests/test_operations/test_mp_value.py

@@ -1,7 +1,6 @@
 import os
 import pytest
 import pathlib
-import tempfile
 import numpy as np
 import pandas as pd
 from math import isclose

cytominer_eval/tests/test_operations/test_replicate_reproducibility.py

@@ -5,7 +5,6 @@
 import tempfile
 import numpy as np
 import pandas as pd
-import pandas.api.types as ptypes
 
 from cytominer_eval.transform import metric_melt
 from cytominer_eval.operations import replicate_reproducibility
@@ -58,7 +57,7 @@ def test_replicate_reproducibility():
 def test_replicate_reproducibility_uniquerows():
     with pytest.raises(AssertionError) as err:
         replicate_groups = ["Metadata_pert_well"]
-        output = replicate_reproducibility(
+        replicate_reproducibility(
             similarity_melted_df=similarity_melted_df,
             replicate_groups=replicate_groups,
             quantile_over_null=0.95,

cytominer_eval/tests/test_transform/test_transform.py

@@ -2,16 +2,13 @@
 import random
 import pytest
 import pathlib
-import tempfile
 import numpy as np
 import pandas as pd
-import pandas.api.types as ptypes
 
 from cytominer_eval.transform.transform import get_pairwise_metric, process_melt
 from cytominer_eval.transform import metric_melt
 
 random.seed(123)
-tmpdir = tempfile.gettempdir()
 
 example_file = "SQ00015054_normalized_feature_select.csv.gz"
 example_file = pathlib.Path(
@@ -40,11 +37,11 @@
 
 def test_get_pairwise_metric():
     with pytest.raises(ValueError) as ve:
-        output = get_pairwise_metric(df, similarity_metric="pearson")
+        get_pairwise_metric(df, similarity_metric="pearson")
     assert "check input features" in str(ve.value)
 
     with pytest.raises(AssertionError) as ve:
-        output = get_pairwise_metric(feature_df, similarity_metric="not supported")
+        get_pairwise_metric(feature_df, similarity_metric="not supported")
     assert "not supported not supported" in str(ve.value)
 
     result_df = get_pairwise_metric(feature_df, similarity_metric="pearson")
@@ -56,7 +53,7 @@ def test_get_pairwise_metric():
 
 def test_process_melt():
     with pytest.raises(AssertionError) as ve:
-        output = process_melt(df=feature_df, meta_df=meta_df)
+        process_melt(df=feature_df, meta_df=meta_df)
     assert "Matrix must be symmetrical" in str(ve.value)
 
     melted_df = process_melt(df=pairwise_metric_df, meta_df=meta_df)
@@ -82,7 +79,7 @@ def test_metric_melt():
     assert result_df.shape[0] == 73536
 
     with pytest.raises(AssertionError) as ve:
-        output = metric_melt(
+        metric_melt(
             df,
             features,
             meta_features,
@@ -92,13 +89,13 @@ def test_metric_melt():
     assert "MISSING not supported. Select one of" in str(ve.value)
 
     with pytest.raises(AssertionError) as ve:
-        output = metric_melt(
+        metric_melt(
             df, features + ["NOT SUPPORTED"], meta_features, similarity_metric="pearson"
         )
     assert "Profile feature not found" in str(ve.value)
 
     with pytest.raises(AssertionError) as ve:
-        output = metric_melt(
+        metric_melt(
             df, features, meta_features + ["NOT SUPPORTED"], similarity_metric="pearson"
         )
     assert "Metadata feature not found" in str(ve.value)

cytominer_eval/tests/test_utils/test_assert_melt.py

@@ -1,11 +1,7 @@
 import os
-import random
 import pytest
 import pathlib
-import tempfile
-import numpy as np
 import pandas as pd
-import pandas.api.types as ptypes
 
 from cytominer_eval.transform import metric_melt
 from cytominer_eval.utils.operation_utils import assign_replicates
@@ -55,7 +51,7 @@ def test_assert_melt():
 
         for dummy_metric in dummy_metrics:
             with pytest.raises(AssertionError) as ve:
-                output = assert_melt(result, eval_metric=dummy_metric)
+                assert_melt(result, eval_metric=dummy_metric)
             assert (
                 "Stop! The eval_metric provided in 'metric_melt()' is incorrect!"
                 in str(ve.value)