B Zvd$I@sdZddlZddlmZddlmZddlmZddlm Z ddl m Z dd l m Z mZd d gZGd d d eje ZdddZedee dggdgdddddd ZdS)z The :mod:`imblearn.pipeline` module implements utilities to build a composite estimator, as a chain of transforms, samples and estimators. N)pipeline)clone)_print_elapsed_time) available_if)_ParamsValidationMixin) HasMethodsvalidate_paramsPipeline make_pipelinecseZdZUdZddeedggdgdZeed<dd Z dfd d Z dd dZ dddZ dddZ dddZeeddddZZS)r a:Pipeline of transforms and resamples with a final estimator. Sequentially apply a list of transforms, sampling, and a final estimator. Intermediate steps of the pipeline must be transformers or resamplers, that is, they must implement fit, transform and sample methods. The samplers are only applied during fit. The final estimator only needs to implement fit. The transformers and samplers in the pipeline can be cached using ``memory`` argument. The purpose of the pipeline is to assemble several steps that can be cross-validated together while setting different parameters. For this, it enables setting parameters of the various steps using their names and the parameter name separated by a '__', as in the example below. A step's estimator may be replaced entirely by setting the parameter with its name to another estimator, or a transformer removed by setting it to 'passthrough' or ``None``. Parameters ---------- steps : list List of (name, transform) tuples (implementing fit/transform/fit_resample) that are chained, in the order in which they are chained, with the last object an estimator. memory : Instance of joblib.Memory or str, default=None Used to cache the fitted transformers of the pipeline. By default, no caching is performed. If a string is given, it is the path to the caching directory. Enabling caching triggers a clone of the transformers before fitting. Therefore, the transformer instance given to the pipeline cannot be inspected directly. Use the attribute ``named_steps`` or ``steps`` to inspect estimators within the pipeline. Caching the transformers is advantageous when fitting is time consuming. verbose : bool, default=False If True, the time elapsed while fitting each step will be printed as it is completed. Attributes ---------- named_steps : :class:`~sklearn.utils.Bunch` Read-only attribute to access any step parameter by user given name. Keys are step names and values are steps parameters. classes_ : ndarray of shape (n_classes,) The classes labels. n_features_in_ : int Number of features seen during first step `fit` method. See Also -------- make_pipeline : Helper function to make pipeline. Notes ----- See :ref:`sphx_glr_auto_examples_pipeline_plot_pipeline_classification.py` .. warning:: A surprising behaviour of the `imbalanced-learn` pipeline is that it breaks the `scikit-learn` contract where one expects `estimmator.fit_transform(X, y)` to be equivalent to `estimator.fit(X, y).transform(X)`. The semantic of `fit_resample` is to be applied only during the fit stage. Therefore, resampling will happen when calling `fit_transform` while it will only happen on the `fit` stage when calling `fit` and `transform` separately. Practically, `fit_transform` will lead to a resampled dataset while `fit` and `transform` will not. Examples -------- >>> from collections import Counter >>> from sklearn.datasets import make_classification >>> from sklearn.model_selection import train_test_split as tts >>> from sklearn.decomposition import PCA >>> from sklearn.neighbors import KNeighborsClassifier as KNN >>> from sklearn.metrics import classification_report >>> from imblearn.over_sampling import SMOTE >>> from imblearn.pipeline import Pipeline >>> X, y = make_classification(n_classes=2, class_sep=2, ... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0, ... n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10) >>> print(f'Original dataset shape {Counter(y)}') Original dataset shape Counter({1: 900, 0: 100}) >>> pca = PCA() >>> smt = SMOTE(random_state=42) >>> knn = KNN() >>> pipeline = Pipeline([('smt', smt), ('pca', pca), ('knn', knn)]) >>> X_train, X_test, y_train, y_test = tts(X, y, random_state=42) >>> pipeline.fit(X_train, y_train) Pipeline(...) >>> y_hat = pipeline.predict(X_test) >>> print(classification_report(y_test, y_hat)) precision recall f1-score support 0 0.87 1.00 0.93 26 1 1.00 0.98 0.99 224 accuracy 0.98 250 macro avg 0.93 0.99 0.96 250 weighted avg 0.99 0.98 0.98 250 Z no_validationNcacheboolean)stepsmemoryverbose_parameter_constraintscCst|j\}}|||dd}|d}x|D]}|dks2|dkrHq2t|dsft|dsft|drzt|dst|dstd|t|ft|drt|dst|drtd|t|tjr2td q2W|dk r|dkrt|dstd |t|fdS) N passthroughfit fit_transform fit_resample transformzAll intermediate steps of the chain should be estimators that implement fit and transform or fit_resample (but not both) or be a string 'passthrough' '%s' (type %s) doesn't)zAll intermediate steps of the chain should be estimators that implement fit and transform or fit_resample. '%s' implements both)z;All intermediate steps of the chain should not be PipelineszaLast step of Pipeline should implement fit or be the string 'passthrough'. '%s' (type %s) doesn't) ziprZ_validate_nameshasattr TypeErrortype isinstancerr )selfnamesZ estimatorsZ transformersZ estimatortr C/var/www/html/venv/lib/python3.7/site-packages/imblearn/pipeline.py_validate_stepss8          zPipeline._validate_stepsTcs(t||}|r tdd|S|SdS)a Generate (idx, (name, trans)) tuples from self.steps. When `filter_passthrough` is `True`, 'passthrough' and None transformers are filtered out. When `filter_resample` is `True`, estimator with a method `fit_resample` are filtered out. cSst|dd S)Nrr)r)xr r r!z Pipeline._iter..N)super_iterfilter)r with_finalfilter_passthroughfilter_resampleit) __class__r r!r'szPipeline._iterc Kstt|j|_||jdks*t|jtr object Parameters passed to the ``fit`` method of each step, where each parameter name is prefixed such that parameter ``p`` for step ``s`` has key ``s__p``. Returns ------- self : Pipeline This estimator. r rrrrN) _validate_params_check_fit_paramsr;rr5lenr_final_estimatorr)rr7r8 fit_paramsr9Xtytfit_params_last_stepr r r!rs  z Pipeline.fitc Ks||jf|}|j||f|\}}|j}td|t|jdT|dkrV|S||jdd}t|dr|j ||f|S|j ||f| |SWdQRXdS)aFit the model and transform with the final estimator. Fits all the transformers/samplers one after the other and transform/sample the data, then uses fit_transform on transformed data with the final estimator. Parameters ---------- X : iterable Training data. Must fulfill input requirements of first step of the pipeline. y : iterable, default=None Training targets. Must fulfill label requirements for all steps of the pipeline. **fit_params : dict of string -> object Parameters passed to the ``fit`` method of each step, where each parameter name is prefixed such that parameter ``p`` for step ``s`` has key ``s__p``. Returns ------- Xt : array-like of shape (n_samples, n_transformed_features) Transformed samples. r rrrrrN) r<r=r;r?rr5r>rrrrr) rr7r8r@r9rArB last_steprCr r r!r,s  zPipeline.fit_transformc Ks||jf|}|j||f|\}}|j}td|t|jd>|dkrV|S||jdd}t|dr|j ||f|SWdQRXdS)aFit the model and sample with the final estimator. Fits all the transformers/samplers one after the other and transform/sample the data, then uses fit_resample on transformed data with the final estimator. Parameters ---------- X : iterable Training data. Must fulfill input requirements of first step of the pipeline. y : iterable, default=None Training targets. Must fulfill label requirements for all steps of the pipeline. **fit_params : dict of string -> object Parameters passed to the ``fit`` method of each step, where each parameter name is prefixed such that parameter ``p`` for step ``s`` has key ``s__p``. Returns ------- Xt : array-like of shape (n_samples, n_transformed_features) Transformed samples. yt : array-like of shape (n_samples, n_transformed_features) Transformed target. r rrrrrN) r<r=r;r?rr5r>rrr) rr7r8r@r9rArBrDrCr r r!rUs  zPipeline.fit_resample fit_predictc Ks~||jf|}|j||f|\}}||jdd}td|t|jd |jddj||f|}WdQRX|S)aApply `fit_predict` of last step in pipeline after transforms. Applies fit_transforms of a pipeline to the data, followed by the fit_predict method of the final estimator in the pipeline. Valid only if the final estimator implements fit_predict. Parameters ---------- X : iterable Training data. Must fulfill input requirements of first step of the pipeline. y : iterable, default=None Training targets. Must fulfill label requirements for all steps of the pipeline. **fit_params : dict of string -> object Parameters passed to the ``fit`` method of each step, where each parameter name is prefixed such that parameter ``p`` for step ``s`` has key ``s__p``. Returns ------- y_pred : ndarray of shape (n_samples,) The predicted target. rrr rN)r<r=r;rrr5r>rE) rr7r8r@r9rArBrCZy_predr r r!rE~s $zPipeline.fit_predict)TTT)N)N)N)N)N)__name__ __module__ __qualname____doc__r2rrdict__annotations__r"r'r;rrrrrZ_final_estimator_hasrE __classcell__r r )r-r!r s i4 7 $ ) ) c Ks4t|| |j||f|\}}|||fSQRXdS)N)rr)Zsamplerr7r8r/r0r@ZX_resZy_resr r r!r4s r4r r )rrFcGstt|||dS)aConstruct a Pipeline from the given estimators. This is a shorthand for the Pipeline constructor; it does not require, and does not permit, naming the estimators. Instead, their names will be set to the lowercase of their types automatically. Parameters ---------- *steps : list of estimators A list of estimators. memory : None, str or object with the joblib.Memory interface, default=None Used to cache the fitted transformers of the pipeline. By default, no caching is performed. If a string is given, it is the path to the caching directory. Enabling caching triggers a clone of the transformers before fitting. Therefore, the transformer instance given to the pipeline cannot be inspected directly. Use the attribute ``named_steps`` or ``steps`` to inspect estimators within the pipeline. Caching the transformers is advantageous when fitting is time consuming. verbose : bool, default=False If True, the time elapsed while fitting each step will be printed as it is completed. Returns ------- p : Pipeline Returns an imbalanced-learn `Pipeline` instance that handles samplers. See Also -------- imblearn.pipeline.Pipeline : Class for creating a pipeline of transforms with a final estimator. Examples -------- >>> from sklearn.naive_bayes import GaussianNB >>> from sklearn.preprocessing import StandardScaler >>> make_pipeline(StandardScaler(), GaussianNB(priors=None)) Pipeline(steps=[('standardscaler', StandardScaler()), ('gaussiannb', GaussianNB())]) )rr)r rZ_name_estimators)rrrr r r!r s-)rMN)rIr3ZsklearnrZ sklearn.baserZ sklearn.utilsrZsklearn.utils.metaestimatorsrbaserZutils._param_validationrr __all__r r4r2r r r r r!s