MAINT use isort for imports (#948)

Author: glemaitre

.pre-commit-config.yaml

@@ -20,3 +20,7 @@ repos:
      -  id: mypy
         files: sklearn/
         additional_dependencies: [pytest==6.2.4]
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.10.1
+    hooks:
+    -   id: isort

azure-pipelines.yml

@@ -45,11 +45,14 @@ jobs:
         versionSpec: '3.9'
     - bash: |
         # Include pytest compatibility with mypy
-        pip install pytest flake8 mypy==0.782 black==22.3
+        pip install pytest flake8 mypy==0.782 black==22.3 isort
       displayName: Install linters
     - bash: |
         black --check --diff .
       displayName: Run black
+    - bash: |
+        isort --check --diff .
+      displayName: Run isort
     - bash: |
         ./build_tools/azure/linting.sh
       displayName: Run linting

conftest.py

@@ -6,6 +6,7 @@
 # rather than the one from site-packages.
 
 import os
+
 import pytest
 
 

doc/conf.py

@@ -15,8 +15,8 @@
 import os
 import sys
 from datetime import datetime
-from pathlib import Path
 from io import StringIO
+from pathlib import Path
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the

doc/sphinxext/github_link.py

@@ -1,9 +1,9 @@
-from operator import attrgetter
 import inspect
-import subprocess
 import os
+import subprocess
 import sys
 from functools import partial
+from operator import attrgetter
 
 REVISION_CMD = "git rev-parse --short HEAD"
 

examples/api/plot_sampling_strategy_usage.py

@@ -26,6 +26,7 @@
 
 # %%
 from sklearn.datasets import load_iris
+
 from imblearn.datasets import make_imbalance
 
 iris = load_iris(as_frame=True)

examples/applications/plot_impact_imbalanced_classes.py

@@ -60,9 +60,10 @@
 # As a baseline, we could use a classifier which will always predict the
 # majority class independently of the features provided.
 
+from sklearn.dummy import DummyClassifier
+
 # %%
 from sklearn.model_selection import cross_validate
-from sklearn.dummy import DummyClassifier
 
 dummy_clf = DummyClassifier(strategy="most_frequent")
 scoring = ["accuracy", "balanced_accuracy"]
@@ -121,9 +122,8 @@
 
 # %%
 from sklearn.impute import SimpleImputer
-from sklearn.preprocessing import StandardScaler
-from sklearn.preprocessing import OneHotEncoder
 from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
 
 num_pipe = make_pipeline(
     StandardScaler(), SimpleImputer(strategy="mean", add_indicator=True)
@@ -139,8 +139,8 @@
 # numerical pipeline
 
 # %%
-from sklearn.compose import make_column_transformer
 from sklearn.compose import make_column_selector as selector
+from sklearn.compose import make_column_transformer
 
 preprocessor_linear = make_column_transformer(
     (num_pipe, selector(dtype_include="number")),
@@ -176,9 +176,10 @@
 # classifier, we will not need to scale the numerical data, and we will only
 # need to ordinal encode the categorical data.
 
+from sklearn.ensemble import RandomForestClassifier
+
 # %%
 from sklearn.preprocessing import OrdinalEncoder
-from sklearn.ensemble import RandomForestClassifier
 
 num_pipe = SimpleImputer(strategy="mean", add_indicator=True)
 cat_pipe = make_pipeline(
@@ -336,8 +337,9 @@
 # applying a single random under-sampling. We will use a gradient-boosting
 # classifier within a :class:`~imblearn.ensemble.BalancedBaggingClassifier`.
 
-from sklearn.experimental import enable_hist_gradient_boosting  # noqa
 from sklearn.ensemble import HistGradientBoostingClassifier
+from sklearn.experimental import enable_hist_gradient_boosting  # noqa
+
 from imblearn.ensemble import BalancedBaggingClassifier
 
 bag_clf = make_pipeline(

examples/applications/plot_multi_class_under_sampling.py

@@ -20,9 +20,9 @@
 from sklearn.preprocessing import StandardScaler
 
 from imblearn.datasets import make_imbalance
-from imblearn.under_sampling import NearMiss
-from imblearn.pipeline import make_pipeline
 from imblearn.metrics import classification_report_imbalanced
+from imblearn.pipeline import make_pipeline
+from imblearn.under_sampling import NearMiss
 
 print(__doc__)
 

examples/applications/plot_outlier_rejections.py

@@ -13,10 +13,9 @@
 # Authors: Guillaume Lemaitre <[email protected]>
 # License: MIT
 
-import numpy as np
 import matplotlib.pyplot as plt
-
-from sklearn.datasets import make_moons, make_blobs
+import numpy as np
+from sklearn.datasets import make_blobs, make_moons
 from sklearn.ensemble import IsolationForest
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import classification_report

examples/applications/plot_over_sampling_benchmark_lfw.py

@@ -72,11 +72,12 @@
 #
 # We will create different pipelines and evaluate them.
 
+from sklearn.neighbors import KNeighborsClassifier
+
 # %%
 from imblearn import FunctionSampler
-from imblearn.over_sampling import ADASYN, RandomOverSampler, SMOTE
+from imblearn.over_sampling import ADASYN, SMOTE, RandomOverSampler
 from imblearn.pipeline import make_pipeline
-from sklearn.neighbors import KNeighborsClassifier
 
 classifier = KNeighborsClassifier(n_neighbors=3)
 
@@ -98,7 +99,7 @@
 # cross-validation.
 
 # %%
-from sklearn.metrics import RocCurveDisplay, roc_curve, auc
+from sklearn.metrics import RocCurveDisplay, auc, roc_curve
 
 disp = []
 for model in pipeline: