dev: Add pre-commit hooks for code quality

.flake8

@@ -0,0 +1,2 @@
+[flake8]
+max-line-length = 127

.github/workflows/unit-test.yml

@@ -31,13 +31,11 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r requirements.txt
 
-      - name: Lint with flake8
+      - name: Run pre-commit hooks
         run: |
-          pip install flake8
-          # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # 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
+          pip install -r requirements-dev.txt
+          pre-commit install
+          pre-commit run --all-files
 
       - name: Run unit tests with pytest
         run: |

.gitignore

@@ -10,4 +10,3 @@ visualime.egg-info/
 .idea/
 **/__pycache__/**
 **/.ipynb_checkpoints/**
-

.pre-commit-config.yaml

@@ -0,0 +1,24 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.2.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: mixed-line-ending
+
+  - repo: https://github.com/pycqa/flake8
+    rev: 4.0.1
+    hooks:
+      - id: flake8
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        args: [ "--profile", "black" ]
+
+  - repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+      - id: black

README.md

@@ -30,12 +30,12 @@ from visualime.explain import explain_classification, render_explanation
 
 image = ...  # a numpy array of shape (width, height, 3) representing an RGB image
 
-def predict_fn(images: np.ndarray) -> np.ndarray: 
+def predict_fn(images: np.ndarray) -> np.ndarray:
     # a function that takes a numpy array of shape (num_of_samples, width, height, 3)
     # representing num_of_samples RGB images and returns a numpy array of
     # shape (num_of_samples, num_of_classes) where each entry corresponds to the
     # classifiers output for the respective image
-    predictions = ...  
+    predictions = ...
     return predictions
 
 segment_mask, segment_weights = explain_classification(image, predict_fn)

example.ipynb

@@ -305,4 +305,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

requirements-dev.txt

@@ -1 +1,2 @@
 notebook
+pre-commit

requirements-test.txt

@@ -1,4 +1,3 @@
 pytest
 pytest-coverage
 tensorflow-cpu
-

visualime/explain.py

@@ -1,18 +1,18 @@
-from typing import Dict, Optional, Union, Tuple, Callable, Any
+from typing import Any, Callable, Dict, Optional, Tuple, Union
 
 import numpy as np
 from PIL import Image
 
+from .feature_selection import forward_selection, select_by_weight
 from .lime import (
     create_segments,
-    generate_samples,
     generate_images,
-    predict_images,
+    generate_samples,
     image_distances,
+    predict_images,
     weigh_segments,
 )
-from .visualize import select_segments, generate_overlay, scale_opacity
-from .feature_selection import select_by_weight, forward_selection
+from .visualize import generate_overlay, scale_opacity, select_segments
 
 
 def explain_classification(
@@ -122,7 +122,7 @@ def explain_classification(
         )
     else:
         raise ValueError(
-            f"Segment selection method has to be either 'by_weight' or 'forward_selection'."
+            "Segment selection method has to be either 'by_weight' or 'forward_selection'."
         )
 
     segment_weights = weigh_segments(

visualime/feature_selection.py

@@ -1,15 +1,15 @@
-from typing import Optional, List
+from typing import List, Optional
 
 import numpy as np
 from sklearn.linear_model import lars_path
 
 from .lime import (
-    weigh_segments,
-    default_distance,
+    DISTANCES_DOC,
     LINEAR_MODELS,
-    SAMPLES_PREDICTIONS_LABEL_IDX_DOC,
     MODEL_TYPE_DOC,
-    DISTANCES_DOC,
+    SAMPLES_PREDICTIONS_LABEL_IDX_DOC,
+    default_distance,
+    weigh_segments,
 )
 
 
@@ -46,13 +46,13 @@ def select_by_weight(
     Parameters
     ----------
     {SAMPLES_PREDICTIONS_LABEL_IDX_DOC}
-    
+
     {MODEL_TYPE_DOC}
-    
+
         It is generally advisable to use the same model as for the final `weigh_segments()` function.
-    
+
     {DISTANCES_DOC}
-    
+
     num_segments_to_select : int, optional
         The number of segments to select. If not given, select all segments.
 
@@ -61,7 +61,7 @@ def select_by_weight(
     selected_segments : List[int]
         List of the indices of the selected segments.
         Segments are ordered by descending weight.
-    
+
     """
 
 
@@ -122,13 +122,13 @@ def score(current_features: List[int], next_feature_idx: int):
     Parameters
     ----------
     {SAMPLES_PREDICTIONS_LABEL_IDX_DOC}
-    
+
     {MODEL_TYPE_DOC}
-    
+
         It is generally advisable to use the same model as for the final `weigh_segments()` function.
-    
+
     {DISTANCES_DOC}
-      
+
     num_segments_to_select : int, optional
         The number of segments to select. If not given, select all segments.
 
@@ -192,7 +192,7 @@ def lars_selection(
     Parameters
     ----------
     {SAMPLES_PREDICTIONS_LABEL_IDX_DOC}
-    
+
     num_segments_to_select : int, optional
         The maximum number of segments to select.
         If not given, this value is set to the total number of segments.

visualime/lime.py

@@ -1,10 +1,10 @@
-from typing import Dict, Callable, Any, Optional, Union, List
+from typing import Any, Callable, Dict, List, Optional, Union
 
 import numpy as np
 from skimage.color import rgb2gray
 from skimage.filters import sobel
-from skimage.segmentation import felzenszwalb, slic, quickshift, watershed
-from sklearn.linear_model import Ridge, BayesianRidge, Lasso, LinearRegression
+from skimage.segmentation import felzenszwalb, quickshift, slic, watershed
+from sklearn.linear_model import BayesianRidge, Lasso, LinearRegression, Ridge
 
 SAMPLES_PREDICTIONS_LABEL_IDX_DOC = """
     samples : np.ndarray
@@ -30,7 +30,8 @@
         The type of linear model to fit.
         Available options are `"bayesian_ridge"`, `"lasso"`, and `"linear_regression"`.
 
-        See [the `scikit-learn` documentation](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.linear_model)
+        See the
+        [`scikit-learn` documentation](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.linear_model)
         for details on each of the methods.
 """
 
@@ -83,7 +84,8 @@ def create_segments(
     Which method and settings are appropriate is highly use-case specific.
 
     For an introduction into image segmentation and a comparison of the different methods, see
-    [this tutorial in the `scikit-learn` documentation](https://scikit-image.org/docs/stable/auto_examples/segmentation/plot_segmentations.html).
+    [this tutorial](https://scikit-image.org/docs/stable/auto_examples/segmentation/plot_segmentations.html)
+    in the `scikit-learn` documentation.
 
     Parameters
     ----------
@@ -349,5 +351,5 @@ def weigh_segments(
     segment_weights : np.ndarray
         Array of length `num_of_segments` where each entry corresponds to the segment's coefficient
         in the fitted linear model.
-        
+
     """

visualime/visualize.py

@@ -1,5 +1,6 @@
+from typing import List, Optional, Tuple, Union
+
 import numpy as np
-from typing import Union, Tuple, List, Optional
 
 
 def select_segments(