{% set version = "1.2.1" %}

package:
  name: scikit-learn
  version: {{ version }}

source:
  url: https://github.com/scikit-learn/scikit-learn/archive/{{ version }}.tar.gz
  sha256: 50613365b0c118b07ad51902d46b9f7779b8f81ea932a205bd12e64b829eea9a
  patches:
   - patches/0001-ignore-errors-when-tearing-down-modules.patch

build:
  number: 0
  skip: true  # [py<38]
  script:
    - rm $PREFIX/include/cblas.h  # [not win]
    - del /f %LIBRARY_INC%\cblas.h  # [win]
    # build the C files in parallel. This helps beat the
    # time limit consistently on drone.io
    - {{ PYTHON }} setup.py build_ext -j{{ CPU_COUNT }}
    - {{ PYTHON }} -m pip install . -vv

requirements:
  build:
    - python                                 # [build_platform != target_platform]
    - cross-python_{{ target_platform }}     # [build_platform != target_platform]
    - cython                                 # [build_platform != target_platform]
    - numpy                                  # [build_platform != target_platform]
    - scipy                                  # [build_platform != target_platform]
    - {{ compiler('c') }}
    - {{ compiler('cxx') }}
    - llvm-openmp  # [osx]
  host:
    - python
    # temporary pin pip to avoid missing oldest-supported-numpy error
    - pip ==22.0.4
    - setuptools <60.0
    - cython >=0.29.24
    - libcblas
    - numpy
    - scipy >=1.3.2  # [not aarch64]
    - scipy >=1.8  # [aarch64]
    - joblib >=1.1.1
    - threadpoolctl >=2.0.0
    - llvm-openmp  # [osx]
  run:
    - python
    - {{ pin_compatible('numpy') }}
    - scipy
    - joblib >=1.1.1
    - threadpoolctl >=2.0.0

{% set tests_to_skip = "_not_a_real_test" %}
{% set extra_pytest_args = "" %}
# https://github.com/scikit-learn/scikit-learn/issues/20335
{% set tests_to_skip = tests_to_skip + " or test_loadings_converges" %}
# Numerically unstable test numerical difference in test
{% set tests_to_skip = tests_to_skip + " or test_mlp_regressor_dtypes_casting" %}         # [ppc64le]
{% if aarch64 and CI %}
    # due to emulation through QEMU, the tests for aarch run very long;
    # azure has different linux agents, and the weaker ones can be a factor 2 slower;
    # skip longest-running ones; all run >60sec (on fast agents) resp. >90sec (on slow agents);
    # since pytest -k skips on string matches, try to match accurately to avoid skipping more than intended
    {% set tests_to_skip = tests_to_skip + " or (test_quantile and (test_asymmetric_error
                                                 or test_quantile_estimates_calibration or test_quantile_sample_weight))"
                                         + " or test_kernel_pca_solvers_equivalence or test_n_iter_no_change_inf"
                                         + " or test_iterative_imputer_no_missing or (test_voting and test_gridsearch)"
                                         + " or test_svc_ovr_tie_breaking or test_check_estimator_clones"
                                         + " or (test_estimators and QuantileRegressor)"
                                         + " or (test_pairwise and test_cosine_distances)"
                                         + " or test_randomized_eigsh_reconst_low_rank"
                                         + " or test_randomized_svd_power_iteration_normalizer"
                                         + " or test_SGDClassifier_fit_for_all_backends"
                                         + " or test_classifier_chain_fit_and_predict_with_linear_svc"
                                         + " or (test_gradient_boosting and test_poisson)"
                                         + " or (test_ridge and test_lbfgs_solver_consistency)"
                                         + " or (test_linear_models_cv_fit_for_all_backends and MultiTask)"
                                         + " or test_spectral_embedding_callable_affinity"
                                         + " or test_spectral_embedding_precomputed_affinity" %}
    # this problem is exacerbated for PyPy; skip some more tests there
    {% if python_impl == "pypy" %}
        {% set tests_to_skip = tests_to_skip + " or (test_bagging and (test_regression or test_classification))"
                                             + " or (check_estimator_sparse_data and (Sequential or TSNE or RFECV))"
                                             + " or (test_ensemble_heterogeneous_estimators_behavior and stacking)"
                                             + " or test_rfe_cv_groups or test_nan_support"
                                             + " or (test_tsne_different_square_distances and exact)"
                                             + " or (test_forest and test_class_weights[RandomForestClassifier])"
                                             + " or test_kde_sample_weights or test_uniform_grid[exact]"
                                             + " or test_parallel_classification or test_sparse_coder_parallel_mmap"
                                             + " or test_sparse_precomputed_distance or test_n_iter_no_change_inf"
                                             + " or test_randomized_eigsh_compared_to_others"
                                             + " or (test_quantile and test_equivariance)"
                                             + " or (test_estimators and GaussianProcessClassifier)"
                                             + " or (test_stacking_with_sample_weight and StackingClassifier)"
                                             + " or (test_mlp and test_partial_fit_classification)"
                                             + " or (test_tree and test_min_impurity_decrease)"
                                             + " or test_scores_attribute_layout_elasticnet"
                                             + " or (test_warning_default_transform_alpha and MiniBatch)"
                                             + " or (test_tsne_different_square_distances and barnes_hut)"
                                             + " or (test_kernel_approximation and test_polynomial_count_sketch)"
                                             + " or test_sample_without_replacement_algorithms" %}
    {% endif %}
{% endif %}

test:
  requires:
    - pytest >=5.3.1
    - cython >=0.29.24
    - pytest-xdist
    - pytest-timeout
  imports:
    - sklearn
  commands:
    # reduce contention for parallelism (xdist-workers, openblas, openmp) that
    # actually increases the runtime and can lead to timeouts
    - export OMP_NUM_THREADS=1                 # [aarch64 or ppc64le]
    - pytest --pyargs sklearn -k "not ({{ tests_to_skip }})" -nauto --timeout=1200 --durations=50  # [not ppc64le]
    # NOTE: test suite is skipped on ppc due to bugs in QEMU code that cause
    # CI to fail, even though the tests should run through on native hardware

about:
  home: http://scikit-learn.org/
  license: BSD-3-Clause
  license_file: COPYING
  summary: A set of python modules for machine learning and data mining
  dev_url: https://github.com/scikit-learn/scikit-learn

extra:
  recipe-maintainers:
    - amueller
    - astaric
    - jakirkham
    - ogrisel
    - ocefpaf
    - lesteve
    - jnothman
    - rth
    - adrinjalali
    - glemaitre
    - jeremiedbb
    - thomasjpfan
    - jjerphan