Merge pull request #44 from felixriese/dev-updates

Dev updates

.github/workflows/tests_and_linting.yml

@@ -31,27 +31,32 @@ jobs:
     - name: List of installed packages
       run: |
         pip list
+    - name: Lint with flake8 (with stopping)
+      if: ${{ matrix.python-version == '3.10' }}
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+    - name: Lint with flake8 (without stopping)
+      if: ${{ matrix.python-version == '3.10' }}
+      run: |
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Check formatting (black, isort)
+      if: ${{ matrix.python-version == '3.10' }}
+      run: |
+        black --check .
+        isort --check .
     - name: Test with pytest
-      if: ${{ matrix.python-version != '3.9' }}
+      if: ${{ matrix.python-version != '3.10' }}
       run: |
         pytest --nbval
     - name: Test with pytest and Codecov
-      if: ${{ matrix.python-version == '3.9' }}
+      if: ${{ matrix.python-version == '3.10' }}
       run: |
         pip install pytest-cov
         pytest --nbval  --cov=susi --cov-report=xml --cov-config .coveragerc
     - name: Upload coverage to Codecov
-      if: ${{ matrix.python-version == '3.9' }}
+      if: ${{ matrix.python-version == '3.10' }}
       uses: codecov/codecov-action@v1
       with:
         verbose: true
-    - name: Lint with flake8 (with stopping)
-      if: ${{ matrix.python-version == '3.9' }}
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-    - name: Lint with flake8 (without stopping)
-      if: ${{ matrix.python-version == '3.9' }}
-      run: |
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics

.pre-commit-config.yaml

@@ -5,29 +5,31 @@ default_language_version:
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.3.0
+  rev: v4.4.0
   hooks:
     - id: no-commit-to-branch
       args: ['--branch', 'main']
     - id: check-added-large-files
       args: ["--maxkb=1000"]
     - id: detect-private-key
     - id: check-merge-conflict
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.10
+      args: [--config=pyproject.toml]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
 - repo: https://github.com/pycqa/flake8
-  rev: 5.0.4
+  rev: 6.0.0
   hooks:
   - id: flake8
     args: ["--ignore=E501,W503"]
 - repo: https://github.com/pycqa/pydocstyle
-  rev: 6.1.1
+  rev: 6.3.0
   hooks:
   - id: pydocstyle
     additional_dependencies: [toml]
-- repo: local
-  hooks:
-  - id: pytest
-    name: Run tests
-    entry: pytest --nbval
-    language: system
-    types: [python]
-    pass_filenames: false

dev-requirements.txt

@@ -1,16 +1,12 @@
 -r requirements.txt
 -r test-requirements.txt
 
-# for formatting
-black==22.10.0
-isort==5.12.0
-
 # for the documentation
 sphinx==7.0.1
 sphinx-autobuild>=0.7.1
 numpydoc==1.5.0
 sphinx_rtd_theme==1.2.2
 
 # for linting
-mypy==0.991
-pre-commit==2.20.0
+mypy==1.4.1
+pre-commit==3.3.3

pyproject.toml

@@ -4,7 +4,7 @@ license_file = "LICENSE"
 
 [tool.black]
 line-length = 79
-target-version = ['py37', 'py38', 'py39', 'py310']
+target-version = ['py38', 'py39', 'py310', 'py311']
 include = '\.pyi?$'
 exclude = '''
 /(
@@ -24,6 +24,11 @@ exclude = '''
 
 [tool.isort]
 profile = "black"
+line_length = 79
+
+[tool.mypy]
+python_version = "3.11"
+ignore_missing_imports = true
 
 [tool.pydocstyle]
 convention = "numpy"

susi/SOMClassifier.py

@@ -5,8 +5,8 @@
 from scipy.special import softmax
 from sklearn.base import ClassifierMixin
 from sklearn.preprocessing import LabelBinarizer
-from sklearn.utils.validation import check_array, check_is_fitted
 from sklearn.utils import class_weight
+from sklearn.utils.validation import check_array, check_is_fitted
 from tqdm import tqdm
 
 from .SOMEstimator import SOMEstimator
@@ -224,7 +224,6 @@ def _init_super_som(self) -> None:
 
         # initialize classification SOM
         if self.init_mode_supervised == "majority":
-
             # define dtype
             if self.class_dtype_ in [str, np.str_]:
                 init_dtype = "U" + str(
@@ -376,7 +375,6 @@ def _modify_weight_matrix_supervised(
 
         """
         if self.train_mode_supervised == "online":
-
             # require valid values for true_vector and learning_rate
             if not isinstance(true_vector, np.ndarray) or not isinstance(
                 learning_rate, float

susi/SOMClustering.py

@@ -167,7 +167,6 @@ def _init_unsuper_som(self) -> None:
             )
 
         elif self.init_mode_unsupervised == "pca":
-
             # fixed number of components
             pca = PCA(n_components=2, random_state=self.random_state)
 
@@ -237,7 +236,6 @@ def _train_unsupervised_som(self) -> None:
                 desc="unsuper",
                 **self.tqdm_params_,
             ):
-
                 # select one input vector & calculate best matching unit (BMU)
                 dp = np.random.randint(low=0, high=len(self.X_))
                 bmu_pos = self.get_bmu(self.X_[dp], self.unsuper_som_)
@@ -267,7 +265,6 @@ def _train_unsupervised_som(self) -> None:
                 desc="unsuper",
                 **self.tqdm_params_,
             ):
-
                 # calculate BMUs
                 bmus = self.get_bmus(self.X_)
 
@@ -813,7 +810,6 @@ def _calc_u_matrix_distances(self) -> None:
         for u_node in itertools.product(
             range(self.n_rows * 2 - 1), range(self.n_columns * 2 - 1)
         ):
-
             # neighbor vector
             nb = (0, 0)
 
@@ -845,7 +841,6 @@ def _calc_u_matrix_means(self) -> None:
         for u_node in itertools.product(
             range(self.n_rows * 2 - 1), range(self.n_columns * 2 - 1)
         ):
-
             if not (u_node[0] % 2) and not (u_node[1] % 2):
                 # SOM nodes -> mean over 2-4 values
 

susi/SOMEstimator.py

@@ -361,7 +361,6 @@ def _modify_weight_matrix_supervised(
 
         """
         if self.train_mode_supervised == "online":
-
             # require valid values for true_vector and learning_rate
             if not isinstance(true_vector, np.ndarray) or not isinstance(
                 learning_rate, float
@@ -397,7 +396,6 @@ def _train_supervised_som(self):
                 desc="super",
                 **self.tqdm_params_,
             ):
-
                 # select one input vector & calculate best matching unit (BMU)
                 dp_index = self._get_random_datapoint_index()
                 bmu_pos = self.bmus_[dp_index]
@@ -426,7 +424,6 @@ def _train_supervised_som(self):
                 desc="super",
                 **self.tqdm_params_,
             ):
-
                 # calculate BMUs with the unsupervised (!) SOM
                 bmus = self.get_bmus(self.X_)
 

test-requirements.txt

@@ -1,6 +1,8 @@
+black==23.7.0
 codecov>=2.1.10
 coverage>=5.3
-flake8==5.0.4
+flake8==6.0.0
+isort==5.12.0
 nbval>=0.9.5
 pytest>=7.2.0
 pytest-cov>=2.10.1

tests/test_MultiOutput.py

@@ -14,8 +14,7 @@
 sys.path.insert(
     0, os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 )
-import susi
-
+import susi  # noqa
 
 # define test dataset
 cali = fetch_california_housing()

tests/test_SOMClassifier.py

@@ -4,11 +4,12 @@
 python -m pytest tests/test_SOMClassifier.py
 
 """
-import pytest
+import itertools
 import os
 import sys
+
 import numpy as np
-import itertools
+import pytest
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
@@ -17,7 +18,7 @@
 sys.path.insert(
     0, os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 )
-import susi
+import susi  # noqa
 
 # define test dataset
 iris = load_iris()

tests/test_SOMEstimator.py

@@ -4,15 +4,16 @@
 python -m pytest tests/test_SOMEstimator.py
 
 """
-import pytest
 import os
 import sys
+
 import numpy as np
+import pytest
 
 sys.path.insert(
     0, os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 )
-import susi
+import susi  # noqa
 
 
 @pytest.mark.parametrize(

tests/test_SOMRegressor.py

@@ -4,11 +4,12 @@
 python -m pytest tests/test_SOMRegressor.py
 
 """
-import pytest
+import itertools
 import os
 import sys
-import itertools
+
 import numpy as np
+import pytest
 from sklearn.datasets import fetch_california_housing
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
@@ -17,7 +18,7 @@
 sys.path.insert(
     0, os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 )
-import susi
+import susi  # noqa
 
 
 @pytest.fixture
@@ -124,7 +125,6 @@ def test_init_super_som_regressor(X, y, init_mode):
 def test_predict(
     training_data, train_mode_unsupervised, train_mode_supervised
 ):
-
     X_train, X_test, y_train, y_test = training_data
 
     som_reg = susi.SOMRegressor(