MNT adapt for scikit-learn 1.1 (#902)

Author: glemaitre

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ repos:
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 21.6b0
+    rev: 22.3.0
     hooks:
     -   id: black
 -   repo: https://gitlab.com/pycqa/flake8

README.rst

@@ -27,12 +27,12 @@
 .. |Black| image:: https://img.shields.io/badge/code%20style-black-000000.svg
 .. _Black: :target: https://github.com/psf/black
 
-.. |PythonMinVersion| replace:: 3.7
-.. |NumPyMinVersion| replace:: 1.14.6
-.. |SciPyMinVersion| replace:: 1.1.0
-.. |ScikitLearnMinVersion| replace:: 1.0.1
-.. |MatplotlibMinVersion| replace:: 2.2.3
-.. |PandasMinVersion| replace:: 0.25.0
+.. |PythonMinVersion| replace:: 3.8
+.. |NumPyMinVersion| replace:: 1.17.3
+.. |SciPyMinVersion| replace:: 1.3.2
+.. |ScikitLearnMinVersion| replace:: 1.1.0
+.. |MatplotlibMinVersion| replace:: 3.1.2
+.. |PandasMinVersion| replace:: 1.0.5
 .. |TensorflowMinVersion| replace:: 2.4.3
 .. |KerasMinVersion| replace:: 2.4.3
 .. |SeabornMinVersion| replace:: 0.9.0

azure-pipelines.yml

@@ -45,7 +45,7 @@ jobs:
         versionSpec: '3.9'
     - bash: |
         # Include pytest compatibility with mypy
-        pip install pytest flake8 mypy==0.782 black==21.6b0
+        pip install pytest flake8 mypy==0.782 black==22.3
       displayName: Install linters
     - bash: |
         black --check --diff .
@@ -115,7 +115,7 @@ jobs:
       py37_conda_forge_openblas_ubuntu_1804:
         DISTRIB: 'conda'
         CONDA_CHANNEL: 'conda-forge'
-        PYTHON_VERSION: '3.7'
+        PYTHON_VERSION: '3.8'
         BLAS: 'openblas'
         COVERAGE: 'false'
 
@@ -140,13 +140,13 @@ jobs:
         PANDAS_VERSION: 'none'
         THREADPOOLCTL_VERSION: 'min'
         COVERAGE: 'false'
-      # Linux + Python 3.7 build with OpenBLAS and without SITE_JOBLIB
+      # Linux + Python 3.8 build with OpenBLAS and without SITE_JOBLIB
       py37_conda_defaults_openblas:
         DISTRIB: 'conda'
-        CONDA_CHANNEL: 'defaults'  # Anaconda main channel
-        PYTHON_VERSION: '3.7'
+        CONDA_CHANNEL: 'conda-forge'
+        PYTHON_VERSION: '3.8'
         BLAS: 'openblas'
-        NUMPY_VERSION: '1.16.6'  # we cannot get an older version of the dependencies resolution
+        NUMPY_VERSION: '1.19.5'  # we cannot get an older version of the dependencies resolution
         SCIPY_VERSION: 'min'
         SKLEARN_VERSION: 'min'
         MATPLOTLIB_VERSION: 'none'
@@ -177,7 +177,7 @@ jobs:
       conda_tensorflow_minimum:
         DISTRIB: 'conda-minimum-tensorflow'
         CONDA_CHANNEL: 'conda-forge'
-        PYTHON_VERSION: '3.7'
+        PYTHON_VERSION: '3.8'
         SKLEARN_VERSION: 'min'
         TENSORFLOW_VERSION: 'min'
         TEST_DOCS: 'true'
@@ -201,33 +201,34 @@ jobs:
       conda_keras_minimum:
         DISTRIB: 'conda-minimum-keras'
         CONDA_CHANNEL: 'conda-forge'
-        PYTHON_VERSION: '3.7'
+        PYTHON_VERSION: '3.8'
         SKLEARN_VERSION: 'min'
         KERAS_VERSION: 'min'
         TEST_DOCS: 'true'
         TEST_DOCSTRINGS: 'false'  # it is going to fail because of scikit-learn inheritance
         CHECK_WARNINGS: 'true'
 
-- template: build_tools/azure/posix-docker.yml
-  parameters:
-    name: Linux_Docker
-    vmImage: ubuntu-20.04
-    dependsOn: [linting, git_commit]
-    condition: |
-      and(
-        succeeded(),
-        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
-        ne(variables['Build.Reason'], 'Schedule')
-      )
-    matrix:
-      debian_atlas_32bit:
-        DISTRIB: 'debian-32'
-        DOCKER_CONTAINER: 'i386/debian:10.9'
-        JOBLIB_VERSION: 'min'
-        # disable pytest xdist due to unknown bug with 32-bit container
-        PYTEST_XDIST_VERSION: 'none'
-        PYTEST_VERSION: 'min'
-        THREADPOOLCTL_VERSION: '2.2.0'
+# Currently runs on Python 3.8 while only Python 3.7 available
+# - template: build_tools/azure/posix-docker.yml
+#   parameters:
+#     name: Linux_Docker
+#     vmImage: ubuntu-20.04
+#     dependsOn: [linting, git_commit]
+#     condition: |
+#       and(
+#         succeeded(),
+#         not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
+#         ne(variables['Build.Reason'], 'Schedule')
+#       )
+#     matrix:
+#       debian_atlas_32bit:
+#         DISTRIB: 'debian-32'
+#         DOCKER_CONTAINER: 'i386/debian:10.9'
+#         JOBLIB_VERSION: 'min'
+#         # disable pytest xdist due to unknown bug with 32-bit container
+#         PYTEST_XDIST_VERSION: 'none'
+#         PYTEST_VERSION: 'min'
+#         THREADPOOLCTL_VERSION: '2.2.0'
 
 - template: build_tools/azure/posix.yml
   parameters:
@@ -266,14 +267,14 @@ jobs:
         ne(variables['Build.Reason'], 'Schedule')
       )
     matrix:
-      py37_conda_forge_mkl:
+      8_conda_forge_mkl:
         DISTRIB: 'conda'
         CONDA_CHANNEL: 'conda-forge'
-        PYTHON_VERSION: '3.7'
+        PYTHON_VERSION: '3.8'
         CHECK_WARNINGS: 'true'
         PYTHON_ARCH: '64'
         PYTEST_VERSION: '*'
         COVERAGE: 'true'
-      py37_pip_openblas_32bit:
-        PYTHON_VERSION: '3.7'
+      py38_pip_openblas_32bit:
+        PYTHON_VERSION: '3.8'
         PYTHON_ARCH: '32'

imblearn/_min_dependencies.py

@@ -1,25 +1,16 @@
 """All minimum dependencies for imbalanced-learn."""
 import argparse
 
-# numpy scipy and cython should by in sync with pyproject.toml
-# We pinned PyWavelet (a scikit-image dependence) to 1.1.1 in the minimum
-# documentation CI builds that is the latest version that support our
-# minimum NumPy version required. If PyWavelets 1.2+ is installed, it would
-# require NumPy 1.17+ that trigger a bug with Pandas 0.25:
-# https://github.com/numpy/numpy/issues/18355#issuecomment-774610226
-# When upgrading NumPy, we can unpin PyWavelets but we need to update the
-# minimum version of Pandas >= 1.0.5.
-NUMPY_MIN_VERSION = "1.14.6"
-SCIPY_MIN_VERSION = "1.1.0"
-PANDAS_MIN_VERSION = "0.25.0"
-SKLEARN_MIN_VERSION = "1.0.1"
+NUMPY_MIN_VERSION = "1.17.3"
+SCIPY_MIN_VERSION = "1.3.2"
+PANDAS_MIN_VERSION = "1.0.5"
+SKLEARN_MIN_VERSION = "1.1.0"
 TENSORFLOW_MIN_VERSION = "2.4.3"
 KERAS_MIN_VERSION = "2.4.3"
-JOBLIB_MIN_VERSION = "0.11"
+JOBLIB_MIN_VERSION = "1.0.0"
 THREADPOOLCTL_MIN_VERSION = "2.0.0"
 PYTEST_MIN_VERSION = "5.0.1"
 
-
 # 'build' and 'install' is included to have structured metadata for CI.
 # It will NOT be included in setup's extras_require
 # The values are (version_spec, comma separated tags)
@@ -32,13 +23,13 @@
     "pandas": (PANDAS_MIN_VERSION, "optional, docs, examples, tests"),
     "tensorflow": (TENSORFLOW_MIN_VERSION, "optional, docs, examples, tests"),
     "keras": (KERAS_MIN_VERSION, "optional, docs, examples, tests"),
-    "matplotlib": ("2.2.3", "docs, examples"),
+    "matplotlib": ("3.1.2", "docs, examples"),
     "seaborn": ("0.9.0", "docs, examples"),
     "memory_profiler": ("0.57.0", "docs"),
     "pytest": (PYTEST_MIN_VERSION, "tests"),
     "pytest-cov": ("2.9.0", "tests"),
     "flake8": ("3.8.2", "tests"),
-    "black": ("21.6b0", "tests"),
+    "black": ("22.3.0", "tests"),
     "mypy": ("0.770", "tests"),
     "sphinx": ("4.2.0", "docs"),
     "sphinx-gallery": ("0.7.0", "docs"),

imblearn/datasets/tests/test_imbalance.py

@@ -9,7 +9,6 @@
 import numpy as np
 
 from sklearn.datasets import load_iris
-from sklearn.datasets import fetch_openml
 
 from imblearn.datasets import make_imbalance
 
@@ -60,18 +59,20 @@ def test_make_imbalance_dict(iris, sampling_strategy, expected_counts):
     "sampling_strategy, expected_counts",
     [
         (
-            {"Iris-setosa": 10, "Iris-versicolor": 20, "Iris-virginica": 30},
-            {"Iris-setosa": 10, "Iris-versicolor": 20, "Iris-virginica": 30},
+            {"setosa": 10, "versicolor": 20, "virginica": 30},
+            {"setosa": 10, "versicolor": 20, "virginica": 30},
         ),
         (
-            {"Iris-setosa": 10, "Iris-versicolor": 20},
-            {"Iris-setosa": 10, "Iris-versicolor": 20, "Iris-virginica": 50},
+            {"setosa": 10, "versicolor": 20},
+            {"setosa": 10, "versicolor": 20, "virginica": 50},
         ),
     ],
 )
 def test_make_imbalanced_iris(as_frame, sampling_strategy, expected_counts):
     pytest.importorskip("pandas")
-    X, y = fetch_openml("iris", version=1, return_X_y=True, as_frame=as_frame)
+    iris = load_iris(as_frame=True)
+    X, y = iris.data, iris.target
+    y = iris.target_names[iris.target]
     X_res, y_res = make_imbalance(X, y, sampling_strategy=sampling_strategy)
     if as_frame:
         assert hasattr(X_res, "loc")