xgboost+sklearn python包，解压在环境中可以直接使用

import warnings import pickle import re from copy import deepcopy from functools import partial, wraps from inspect import signature from numbers import Real import numpy as np from scipy import sparse from scipy.stats import rankdata import joblib from . import IS_PYPY from .. import config_context from ._param_validation import Interval from ._testing import _get_args from ._testing import assert_raise_message from ._testing import assert_array_equal from ._testing import assert_array_almost_equal from ._testing import assert_allclose from ._testing import assert_allclose_dense_sparse from ._testing import assert_array_less from ._testing import set_random_state from ._testing import SkipTest from ._testing import ignore_warnings from ._testing import create_memmap_backed_data from ._testing import raises from . import is_scalar_nan from ..linear_model import LinearRegression from ..linear_model import LogisticRegression from ..linear_model import RANSACRegressor from ..linear_model import Ridge from ..linear_model import SGDRegressor from ..base import ( clone, ClusterMixin, is_classifier, is_regressor, is_outlier_detector, RegressorMixin, ) from ..metrics import accuracy_score, adjusted_rand_score, f1_score from ..random_projection import BaseRandomProjection from ..feature_selection import SelectKBest from ..feature_selection import SelectFromModel from ..pipeline import make_pipeline from ..exceptions import DataConversionWarning from ..exceptions import NotFittedError from ..exceptions import SkipTestWarning from ..model_selection import train_test_split from ..model_selection import ShuffleSplit from ..model_selection._validation import _safe_split from ..metrics.pairwise import rbf_kernel, linear_kernel, pairwise_distances from ..utils.fixes import sp_version from ..utils.fixes import parse_version from ..utils.validation import check_is_fitted from ..utils._param_validation import make_constraint from ..utils._param_validation import generate_invalid_param_val from ..utils._param_validation import InvalidParameterError from . import shuffle from ._tags import ( _DEFAULT_TAGS, _safe_tags, ) from .validation import has_fit_parameter, _num_samples from ..preprocessing import StandardScaler from ..preprocessing import scale from ..datasets import ( load_iris, make_blobs, make_multilabel_classification, make_regression, ) REGRESSION_DATASET = None CROSS_DECOMPOSITION = ["PLSCanonical", "PLSRegression", "CCA", "PLSSVD"] def _yield_checks(estimator): name = estimator.__class__.__name__ tags = _safe_tags(estimator) yield check_no_attributes_set_in_init yield check_estimators_dtypes yield check_fit_score_takes_y if has_fit_parameter(estimator, "sample_weight"): yield check_sample_weights_pandas_series yield check_sample_weights_not_an_array yield check_sample_weights_list if not tags["pairwise"]: # We skip pairwise because the data is not pairwise yield check_sample_weights_shape yield check_sample_weights_not_overwritten yield partial(check_sample_weights_invariance, kind="ones") yield partial(check_sample_weights_invariance, kind="zeros") yield check_estimators_fit_returns_self yield partial(check_estimators_fit_returns_self, readonly_memmap=True) # Check that all estimator yield informative messages when # trained on empty datasets if not tags["no_validation"]: yield check_complex_data yield check_dtype_object yield check_estimators_empty_data_messages if name not in CROSS_DECOMPOSITION: # cross-decomposition's "transform" returns X and Y yield check_pipeline_consistency if not tags["allow_nan"] and not tags["no_validation"]: # Test that all estimators check their input for NaN's and infs yield check_estimators_nan_inf if tags["pairwise"]: # Check that pairwise estimator throws error on non-square input yield check_nonsquare_error yield check_estimators_overwrite_params if hasattr(estimator, "sparsify"): yield check_sparsify_coefficients yield check_estimator_sparse_data # Test that estimators can be pickled, and once pickled # give the same answer as before. yield check_estimators_pickle yield check_estimator_get_tags_default_keys def _yield_classifier_checks(classifier): tags = _safe_tags(classifier) # test classifiers can handle non-array data and pandas objects yield check_classifier_data_not_an_array # test classifiers trained on a single label always return this label yield check_classifiers_one_label yield check_classifiers_one_label_sample_weights yield check_classifiers_classes yield check_estimators_partial_fit_n_features if tags["multioutput"]: yield check_classifier_multioutput # basic consistency testing yield check_classifiers_train yield partial(check_classifiers_train, readonly_memmap=True) yield partial(check_classifiers_train, readonly_memmap=True, X_dtype="float32") yield check_classifiers_regression_target if tags["multilabel"]: yield check_classifiers_multilabel_representation_invariance yield check_classifiers_multilabel_output_format_predict yield check_classifiers_multilabel_output_format_predict_proba yield check_classifiers_multilabel_output_format_decision_function if not tags["no_validation"]: yield check_supervised_y_no_nan if not tags["multioutput_only"]: yield check_supervised_y_2d if tags["requires_fit"]: yield check_estimators_unfitted if "class_weight" in classifier.get_params().keys(): yield check_class_weight_classifiers yield check_non_transformer_estimators_n_iter # test if predict_proba is a monotonic transformation of decision_function yield check_decision_proba_consistency @ignore_warnings(category=FutureWarning) def check_supervised_y_no_nan(name, estimator_orig): # Checks that the Estimator targets are not NaN. estimator = clone(estimator_orig) rng = np.random.RandomState(888) X = rng.standard_normal(size=(10, 5)) for value in [np.nan, np.inf]: y = np.full(10, value) y = _enforce_estimator_tags_y(estimator, y) module_name = estimator.__module__ if module_name.startswith("sklearn.") and not ( "test_" in module_name or module_name.endswith("_testing") ): # In scikit-learn we want the error message to mention the input # name and be specific about the kind of unexpected value. if np.isinf(value): match = ( r"Input (y|Y) contains infinity or a value too large for" r" dtype\('float64'\)." ) else: match = r"Input (y|Y) contains NaN." else: # Do not impose a particular error message to third-party libraries. match = None err_msg = ( f"Estimator {name} should have raised error on fitting array y with inf" " value." ) with raises(ValueError, match=match, err_msg=err_msg): estimator.fit(X, y) def _yield_regressor_checks(regressor): tags = _safe_tags(regressor) # TODO: test with intercept # TODO: test with multiple responses # basic testing yield check_regressors_train yield partial(check_regressors_train, readonly_memmap=True) yield partial(check_regressors_train, readonly_memmap=True, X_dtype="float32") yield check_regressor_data_not_an_array yield check_estimators_partial_fit_n_features if tags["multioutput"]: yield check_regressor_multioutput yield check_regressors_no_decision_function if not tags["no_validation"] and not tags["multioutput_only"]: yield check_sup