Update script for list

update_docstring_numpydoc_validation.py

from collections import defaultdict
from github import Github
import os

token = os.environ["GITHUB_TOKEN"]

gh = Github(token)

sk_repo = gh.get_repo("scikit-learn/scikit-learn")

global_issue = sk_repo.get_issue(21350)

all_functions = [
    "sklearn._config.config_context",
    "sklearn._config.get_config",
    "sklearn.base.clone",
    "sklearn.cluster._affinity_propagation.affinity_propagation",
    "sklearn.cluster._agglomerative.linkage_tree",
    "sklearn.cluster._kmeans.k_means",
    "sklearn.cluster._kmeans.kmeans_plusplus",
    "sklearn.cluster._mean_shift.estimate_bandwidth",
    "sklearn.cluster._mean_shift.get_bin_seeds",
    "sklearn.cluster._mean_shift.mean_shift",
    "sklearn.cluster._optics.cluster_optics_dbscan",
    "sklearn.cluster._optics.cluster_optics_xi",
    "sklearn.cluster._optics.compute_optics_graph",
    "sklearn.cluster._spectral.spectral_clustering",
    "sklearn.compose._column_transformer.make_column_transformer",
    "sklearn.covariance._empirical_covariance.empirical_covariance",
    "sklearn.covariance._empirical_covariance.log_likelihood",
    "sklearn.covariance._graph_lasso.graphical_lasso",
    "sklearn.covariance._robust_covariance.fast_mcd",
    "sklearn.covariance._shrunk_covariance.ledoit_wolf",
    "sklearn.covariance._shrunk_covariance.ledoit_wolf_shrinkage",
    "sklearn.covariance._shrunk_covariance.shrunk_covariance",
    "sklearn.datasets._base.get_data_home",
    "sklearn.datasets._base.load_boston",
    "sklearn.datasets._base.load_breast_cancer",
    "sklearn.datasets._base.load_diabetes",
    "sklearn.datasets._base.load_digits",
    "sklearn.datasets._base.load_files",
    "sklearn.datasets._base.load_iris",
    "sklearn.datasets._base.load_linnerud",
    "sklearn.datasets._base.load_sample_image",
    "sklearn.datasets._base.load_wine",
    "sklearn.datasets._california_housing.fetch_california_housing",
    "sklearn.datasets._covtype.fetch_covtype",
    "sklearn.datasets._kddcup99.fetch_kddcup99",
    "sklearn.datasets._lfw.fetch_lfw_pairs",
    "sklearn.datasets._lfw.fetch_lfw_people",
    "sklearn.datasets._olivetti_faces.fetch_olivetti_faces",
    "sklearn.datasets._openml.fetch_openml",
    "sklearn.datasets._rcv1.fetch_rcv1",
    "sklearn.datasets._samples_generator.make_biclusters",
    "sklearn.datasets._samples_generator.make_blobs",
    "sklearn.datasets._samples_generator.make_checkerboard",
    "sklearn.datasets._samples_generator.make_classification",
    "sklearn.datasets._samples_generator.make_gaussian_quantiles",
    "sklearn.datasets._samples_generator.make_hastie_10_2",
    "sklearn.datasets._samples_generator.make_multilabel_classification",
    "sklearn.datasets._samples_generator.make_regression",
    "sklearn.datasets._samples_generator.make_sparse_coded_signal",
    "sklearn.datasets._samples_generator.make_sparse_spd_matrix",
    "sklearn.datasets._samples_generator.make_spd_matrix",
    "sklearn.datasets._species_distributions.fetch_species_distributions",
    "sklearn.datasets._svmlight_format_io.dump_svmlight_file",
    "sklearn.datasets._svmlight_format_io.load_svmlight_file",
    "sklearn.datasets._svmlight_format_io.load_svmlight_files",
    "sklearn.datasets._twenty_newsgroups.fetch_20newsgroups",
    "sklearn.decomposition._dict_learning.dict_learning",
    "sklearn.decomposition._dict_learning.dict_learning_online",
    "sklearn.decomposition._dict_learning.sparse_encode",
    "sklearn.decomposition._fastica.fastica",
    "sklearn.decomposition._nmf.non_negative_factorization",
    "sklearn.externals._packaging.version.parse",
    "sklearn.feature_extraction.image.extract_patches_2d",
    "sklearn.feature_extraction.image.grid_to_graph",
    "sklearn.feature_extraction.image.img_to_graph",
    "sklearn.feature_extraction.text.strip_accents_ascii",
    "sklearn.feature_extraction.text.strip_accents_unicode",
    "sklearn.feature_extraction.text.strip_tags",
    "sklearn.feature_selection._univariate_selection.chi2",
    "sklearn.feature_selection._univariate_selection.f_oneway",
    "sklearn.feature_selection._univariate_selection.r_regression",
    "sklearn.inspection._partial_dependence.partial_dependence",
    "sklearn.inspection._plot.partial_dependence.plot_partial_dependence",
    "sklearn.isotonic.isotonic_regression",
    "sklearn.linear_model._least_angle.lars_path",
    "sklearn.linear_model._least_angle.lars_path_gram",
    "sklearn.linear_model._omp.orthogonal_mp",
    "sklearn.linear_model._omp.orthogonal_mp_gram",
    "sklearn.linear_model._ridge.ridge_regression",
    "sklearn.manifold._locally_linear.locally_linear_embedding",
    "sklearn.manifold._t_sne.trustworthiness",
    "sklearn.metrics._classification.accuracy_score",
    "sklearn.metrics._classification.balanced_accuracy_score",
    "sklearn.metrics._classification.brier_score_loss",
    "sklearn.metrics._classification.classification_report",
    "sklearn.metrics._classification.cohen_kappa_score",
    "sklearn.metrics._classification.confusion_matrix ",
    "sklearn.metrics._classification.f1_score",
    "sklearn.metrics._classification.fbeta_score",
    "sklearn.metrics._classification.hamming_loss",
    "sklearn.metrics._classification.hinge_loss",
    "sklearn.metrics._classification.jaccard_score",
    "sklearn.metrics._classification.log_loss",
    "sklearn.metrics._classification.precision_recall_fscore_support",
    "sklearn.metrics._classification.precision_score",
    "sklearn.metrics._classification.recall_score",
    "sklearn.metrics._classification.zero_one_loss",
    "sklearn.metrics._plot.confusion_matrix.plot_confusion_matrix",
    "sklearn.metrics._plot.det_curve.plot_det_curve",
    "sklearn.metrics._plot.precision_recall_curve.plot_precision_recall_curve",
    "sklearn.metrics._plot.roc_curve.plot_roc_curve",
    "sklearn.metrics._ranking.auc",
    "sklearn.metrics._ranking.average_precision_score",
    "sklearn.metrics._ranking.coverage_error",
    "sklearn.metrics._ranking.dcg_score",
    "sklearn.metrics._ranking.label_ranking_average_precision_score",
    "sklearn.metrics._ranking.label_ranking_loss",
    "sklearn.metrics._ranking.ndcg_score",
    "sklearn.metrics._ranking.precision_recall_curve",
    "sklearn.metrics._ranking.roc_auc_score",
    "sklearn.metrics._ranking.roc_curve",
    "sklearn.metrics._ranking.top_k_accuracy_score",
    "sklearn.metrics._regression.max_error",
    "sklearn.metrics._regression.mean_absolute_error",
    "sklearn.metrics._regression.mean_pinball_loss",
    "sklearn.metrics._scorer.make_scorer",
    "sklearn.metrics.cluster._bicluster.consensus_score",
    "sklearn.metrics.cluster._supervised.adjusted_mutual_info_score",
    "sklearn.metrics.cluster._supervised.adjusted_rand_score",
    "sklearn.metrics.cluster._supervised.completeness_score",
    "sklearn.metrics.cluster._supervised.entropy",
    "sklearn.metrics.cluster._supervised.fowlkes_mallows_score",
    "sklearn.metrics.cluster._supervised.homogeneity_completeness_v_measure",
    "sklearn.metrics.cluster._supervised.homogeneity_score",
    "sklearn.metrics.cluster._supervised.mutual_info_score",
    "sklearn.metrics.cluster._supervised.normalized_mutual_info_score",
    "sklearn.metrics.cluster._supervised.pair_confusion_matrix",
    "sklearn.metrics.cluster._supervised.rand_score",
    "sklearn.metrics.cluster._supervised.v_measure_score",
    "sklearn.metrics.cluster._unsupervised.davies_bouldin_score",
    "sklearn.metrics.cluster._unsupervised.silhouette_samples",
    "sklearn.metrics.cluster._unsupervised.silhouette_score",
    "sklearn.metrics.pairwise.additive_chi2_kernel",
    "sklearn.metrics.pairwise.check_paired_arrays",
    "sklearn.metrics.pairwise.check_pairwise_arrays",
    "sklearn.metrics.pairwise.chi2_kernel",
    "sklearn.metrics.pairwise.cosine_distances",
    "sklearn.metrics.pairwise.cosine_similarity",
    "sklearn.metrics.pairwise.distance_metrics",
    "sklearn.metrics.pairwise.euclidean_distances",
    "sklearn.metrics.pairwise.haversine_distances",
    "sklearn.metrics.pairwise.kernel_metrics",
    "sklearn.metrics.pairwise.laplacian_kernel",
    "sklearn.metrics.pairwise.linear_kernel",
    "sklearn.metrics.pairwise.manhattan_distances",
    "sklearn.metrics.pairwise.nan_euclidean_distances",
    "sklearn.metrics.pairwise.paired_cosine_distances",
    "sklearn.metrics.pairwise.paired_distances",
    "sklearn.metrics.pairwise.paired_euclidean_distances",
    "sklearn.metrics.pairwise.paired_manhattan_distances",
    "sklearn.metrics.pairwise.pairwise_distances_argmin",
    "sklearn.metrics.pairwise.pairwise_distances_argmin_min",
    "sklearn.metrics.pairwise.pairwise_distances_chunked",
    "sklearn.metrics.pairwise.pairwise_kernels",
    "sklearn.metrics.pairwise.polynomial_kernel",
    "sklearn.metrics.pairwise.rbf_kernel",
    "sklearn.metrics.pairwise.sigmoid_kernel",
    "sklearn.model_selection._split.check_cv",
    "sklearn.model_selection._split.train_test_split",
    "sklearn.model_selection._validation.cross_val_predict",
    "sklearn.model_selection._validation.cross_val_score",
    "sklearn.model_selection._validation.cross_validate",
    "sklearn.model_selection._validation.learning_curve",
    "sklearn.model_selection._validation.permutation_test_score",
    "sklearn.model_selection._validation.validation_curve",
    "sklearn.neighbors._graph.kneighbors_graph",
    "sklearn.neighbors._graph.radius_neighbors_graph",
    "sklearn.pipeline.make_union",
    "sklearn.preprocessing._data.binarize",
    "sklearn.preprocessing._data.maxabs_scale",
    "sklearn.preprocessing._data.normalize",
    "sklearn.preprocessing._data.power_transform",
    "sklearn.preprocessing._data.quantile_transform",
    "sklearn.preprocessing._data.robust_scale",
    "sklearn.preprocessing._data.scale",
    "sklearn.preprocessing._label.label_binarize",
    "sklearn.random_projection.johnson_lindenstrauss_min_dim",
    "sklearn.svm._bounds.l1_min_c",
    "sklearn.tree._export.plot_tree",
    "sklearn.utils.axis0_safe_slice",
    "sklearn.utils.check_pandas_support",
    "sklearn.utils.extmath.cartesian",
    "sklearn.utils.extmath.density",
    "sklearn.utils.extmath.fast_logdet",
    "sklearn.utils.extmath.randomized_range_finder",
    "sklearn.utils.extmath.randomized_svd",
    "sklearn.utils.extmath.safe_sparse_dot",
    "sklearn.utils.extmath.squared_norm",
    "sklearn.utils.extmath.stable_cumsum",
    "sklearn.utils.extmath.svd_flip",
    "sklearn.utils.extmath.weighted_mode",
    "sklearn.utils.fixes.delayed",
    "sklearn.utils.fixes.linspace",
    "sklearn.utils.fixes.threadpool_info",
    "sklearn.utils.fixes.threadpool_limits",
    "sklearn.utils.gen_batches",
    "sklearn.utils.gen_even_slices",
    "sklearn.utils.get_chunk_n_rows",
    "sklearn.utils.graph.graph_shortest_path",
    "sklearn.utils.graph.single_source_shortest_path_length",
    "sklearn.utils.is_scalar_nan",
    "sklearn.utils.metaestimators.available_if",
    "sklearn.utils.metaestimators.if_delegate_has_method",
    "sklearn.utils.multiclass.check_classification_targets",
    "sklearn.utils.multiclass.class_distribution",
    "sklearn.utils.multiclass.type_of_target",
    "sklearn.utils.multiclass.unique_labels",
    "sklearn.utils.resample",
    "sklearn.utils.safe_mask",
    "sklearn.utils.safe_sqr",
    "sklearn.utils.shuffle",
    "sklearn.utils.sparsefuncs.count_nonzero",
    "sklearn.utils.sparsefuncs.csc_median_axis_0",
    "sklearn.utils.sparsefuncs.incr_mean_variance_axis",
    "sklearn.utils.sparsefuncs.inplace_swap_column",
    "sklearn.utils.sparsefuncs.inplace_swap_row",
    "sklearn.utils.sparsefuncs.inplace_swap_row_csc",
    "sklearn.utils.sparsefuncs.inplace_swap_row_csr",
    "sklearn.utils.sparsefuncs.mean_variance_axis",
    "sklearn.utils.sparsefuncs.min_max_axis",
    "sklearn.utils.tosequence",
    "sklearn.utils.validation.as_float_array",
    "sklearn.utils.validation.assert_all_finite",
    "sklearn.utils.validation.check_is_fitted",
    "sklearn.utils.validation.check_memory",
    "sklearn.utils.validation.check_random_state",
    "sklearn.utils.validation.column_or_1d",
    "sklearn.utils.validation.has_fit_parameter",
    "sklearn.utils.validation.indexable",
]

print("Searching for pulls")
issues = gh.search_issues("repo:scikit-learn/scikit-learn 21350 in:body is:pr")

all_pulls = [sk_repo.get_pull(issue.number) for issue in issues]

pull_infos = [
    (pull.title, pull.number, pull.state == "open", pull.merged) for pull in all_pulls
]

function_with_pulls = defaultdict(list)

print("Connecting pulls to functions")
for title, number, open, merged in pull_infos:
    if not open and not merged:
        continue
    for func in all_functions:
        if func.split(".")[-1] in title:
            function_with_pulls[func].append((f"#{number}", merged))

updated_functions = ["### Functions to Update", ""]
for func in all_functions:
    if func not in function_with_pulls:
        updated_functions.append(f"- [ ] {func}")
        continue

    pulls = function_with_pulls[func]
    list_str = "- [ ] "
    if any(pull[1] for pull in pulls):
        list_str = "- [x] "
    issue_numbers = " ".join([pull[0] for pull in pulls])
    if issue_numbers:
        issue_numbers = f" {issue_numbers}"
    updated_functions.append(f"{list_str}{func}{issue_numbers}")

function_idx = global_issue.body.index("### Functions to Update")

header = global_issue.body[:function_idx]

updated_list_str = "\n".join(updated_functions)

updated_body = f"{header}\n{updated_list_str}"

global_issue.edit(body=updated_body)