Python sklearn.clone() Examples

def __init__(self,
                 test_indices=None,
                 estimator={'object': sklearn.linear_model.Lasso(alpha=20),
                            'fit': {}},
                 **kwargs):
        self.test_indices = np.asarray(test_indices)
        self.estimator = sklearn.clone(estimator['object'])
        self.estimator_fit = estimator.get('fit', {})
        self.models = []  # leave empty, fill in during `fit`

        self.n_record = 0
        self.record = []

        self.n_series, self.n_features = 0, 0
        self.px = kwargs.get('px', 0)
        self.py = kwargs.get('py', 0) 

def fit(self, X, y, **kwargs):
        """Fit the estimator.

        If `prefit` is set to `True` then the base estimator is kept as is.
        Otherwise it is fitted from the provided arguments.
        """
        if self.estimator is None:
            raise ValueError(BASE_ESTIMATOR_NONE_ERROR_MESSAGE)

        if not self.prefit:
            self.estimator_ = clone(self.estimator).fit(X, y, **kwargs)
        else:
            try:
                check_is_fitted(self.estimator)
            except NotFittedError:
                warn(BASE_ESTIMATOR_NOT_FITTED_WARNING.format(type(self).__name__))
            self.estimator_ = self.estimator
        return self 

def fit(self, X, y):
        """
        Fit the data after adapting the same weight.

        :param X: array-like, shape=(n_columns, n_samples,) training data.
        :param y: array-like, shape=(n_samples,) training data.
        :return: Returns an instance of self.
        """
        X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
        self.weights_ = np.cumprod(np.ones(X.shape[0]) * self.decay)[::-1]
        self.estimator_ = clone(self.model)
        try:
            self.estimator_.fit(X, y, sample_weight=self.weights_)
        except TypeError as e:
            if "sample_weight" in str(e):
                raise TypeError(
                    f"Model {type(self.model).__name__}.fit() does not have 'sample_weight'"
                )
        if self._is_classifier():
            self.classes_ = self.estimator_.classes_
        return self 

def fit(self, X, y):
        """
        Fit the data.

        :param X: array-like, shape=(n_columns, n_samples,) training data.
        :param y: array-like, shape=(n_samples,) training data.
        :return: Returns an instance of self.
        """
        X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
        self.estimator_ = clone(self.model)
        if not isinstance(self.estimator_, ProbabilisticClassifier):
            raise ValueError(
                "The Thresholder meta model only works on classifcation models with .predict_proba."
            )
        self.estimator_.fit(X, y)
        self.classes_ = self.estimator_.classes_
        if len(self.classes_) != 2:
            raise ValueError(
                "The Thresholder meta model only works on models with two classes."
            )
        return self 

def test_auto_init(n_samples, n_features, n_classes, n_components):
    # Test that auto choose the init as expected with every configuration
    # of order of n_samples, n_features, n_classes and n_components.
    rng = np.random.RandomState(42)
    nca_base = NeighborhoodComponentsAnalysis(init='auto',
                                              n_components=n_components,
                                              max_iter=1,
                                              random_state=rng)
    if n_classes >= n_samples:
        pass
        # n_classes > n_samples is impossible, and n_classes == n_samples
        # throws an error from lda but is an absurd case
    else:
        X = rng.randn(n_samples, n_features)
        y = np.tile(range(n_classes), n_samples // n_classes + 1)[:n_samples]
        if n_components > n_features:
            # this would return a ValueError, which is already tested in
            # test_params_validation
            pass
        else:
            nca = clone(nca_base)
            nca.fit(X, y)
            if n_components <= min(n_classes - 1, n_features):
                nca_other = clone(nca_base).set_params(init='lda')
            elif n_components < min(n_features, n_samples):
                nca_other = clone(nca_base).set_params(init='pca')
            else:
                nca_other = clone(nca_base).set_params(init='identity')
            nca_other.fit(X, y)
            assert_array_almost_equal(nca.components_, nca_other.components_) 

def fit(self, X, y):
        try:
            check_is_fitted(self.logistic_regression_estimator)
            self.logistic_regression_estimator_ = self.logistic_regression_estimator
        except NotFittedError:
            self.logistic_regression_estimator_ = clone(
                self.logistic_regression_estimator
            ).fit(X, y)
        return self 

def __fit_grouped_estimator(self, X, y, value_columns, group_columns):
        # Reset indices such that they are the same in X and y
        X, y = X.reset_index(drop=True), y.reset_index(drop=True)

        group_indices = X.groupby(group_columns).indices

        grouped_estimations = {
            group: clone(self.estimator).fit(
                X.loc[indices, value_columns], y.loc[indices]
            )
            for group, indices in group_indices.items()
        }

        return grouped_estimations 

def fit(self, X, y):
        """Fits the estimator"""
        X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)

        self.estimator_ = clone(self.estimator)
        self.estimator_.fit(X, y)
        return self 

def fit(self, X, y=None):
        self.estimator_ = clone(self.outlier_detector)
        if self.refit:
            super().fit(X, y)
            self.estimator_.fit(X, y)
        return self 

def test_values_uniform(random_xy_dataset_clf):
    X, y = random_xy_dataset_clf
    X, y = check_X_y(X, y)
    clf = DummyClassifier(strategy="most_frequent")
    transformer = EstimatorTransformer(clone(clf))
    transformed = transformer.fit(X, y).transform(X)

    assert transformed.shape == (y.shape[0], 1)
    assert np.all(transformed == clf.fit(X, y).predict(X)) 

def test_splits_not_fitted(cluster_method, random_xy_dataset_regr):
    cluster_method = clone(cluster_method)
    X, y = random_xy_dataset_regr
    kf = KlusterFoldValidation(cluster_method=cluster_method)
    for train_index, test_index in kf.split(X):
        assert len(train_index) > 0
        assert len(test_index) > 0 

def test_splits_fitted(cluster_method, random_xy_dataset_regr):
    cluster_method = clone(cluster_method)
    X, y = random_xy_dataset_regr
    cluster_method = cluster_method.fit(X)
    kf = KlusterFoldValidation(cluster_method=cluster_method)
    for train_index, test_index in kf.split(X):
        assert len(train_index) > 0
        assert len(test_index) > 0 

def check_clone(Estimator):
    # Check we can call clone from scikit-learn
    estimator = _construct_instance(Estimator)
    clone(estimator) 

def test_estimators_compatibility(self):
        """Tests that dislib estimators are compatible with GridSearchCV.

        GridSearchCV uses sklearn.clone(estimator), that requires estimators to
        have methods get_params() and set_params() working properly. This is
        what this test checks, and it can be easily achieved by making the
        estimators inherit from sklearn BaseEstimator"""
        estimators = (CascadeSVM, RandomForestClassifier,
                      DBSCAN, KMeans, GaussianMixture,
                      PCA, NearestNeighbors, ALS, LinearRegression)

        for estimator_class in estimators:
            self.assertIsInstance(estimator_class, type)
            est = estimator_class()
            # test __repr__
            repr(est)
            # test cloning
            cloned = clone(est)
            # test that set_params returns self
            self.assertIs(cloned.set_params(), cloned)
            # Checks if get_params(deep=False) is a subset of
            # get_params(deep=True)
            shallow_params = est.get_params(deep=False)
            deep_params = est.get_params(deep=True)
            self.assertTrue(all(item in deep_params.items()
                                for item in shallow_params.items())) 

def test_auto_init(n_samples, n_features, n_classes, n_components):
    # Test that auto choose the init as expected with every configuration
    # of order of n_samples, n_features, n_classes and n_components.
    rng = np.random.RandomState(42)
    nca_base = NeighborhoodComponentsAnalysis(init='auto',
                                              n_components=n_components,
                                              max_iter=1,
                                              random_state=rng)
    if n_classes >= n_samples:
        pass
        # n_classes > n_samples is impossible, and n_classes == n_samples
        # throws an error from lda but is an absurd case
    else:
        X = rng.randn(n_samples, n_features)
        y = np.tile(range(n_classes), n_samples // n_classes + 1)[:n_samples]
        if n_components > n_features:
            # this would return a ValueError, which is already tested in
            # test_params_validation
            pass
        else:
            nca = clone(nca_base)
            nca.fit(X, y)
            if n_components <= min(n_classes - 1, n_features):
                nca_other = clone(nca_base).set_params(init='lda')
            elif n_components < min(n_features, n_samples):
                nca_other = clone(nca_base).set_params(init='pca')
            else:
                nca_other = clone(nca_base).set_params(init='identity')
            nca_other.fit(X, y)
            assert_array_almost_equal(nca.components_, nca_other.components_) 

def setup_dummy_YATSM(X, Y, dates, i_breaks):
    """ Setup a dummy YATSM model

    Args:
        X (np.ndarray): n x p features
        Y (np.ndarray): n_series x n independent data
        dates (np.ndarray): n dates
        i_breaks (iterable): indices of ``dates`` representing break dates
            (can be zero or nonzero, but len(i_breaks) is len(yatsm.record))

    Returns:
        YATSM model
    """
    n = dates.size
    yatsm = YATSM()
    yatsm.X, yatsm.Y, yatsm.dates = X, Y, dates
    yatsm.n_coef, yatsm.n_series = X.shape[1], Y.shape[0]
    yatsm.models = np.array([sklearn.clone(yatsm.estimator)
                             for i in range(yatsm.n_series)])
    yatsm.test_indices = np.arange(yatsm.n_series)
    n_models = len(i_breaks)
    yatsm.record = np.hstack([yatsm.record_template] * n_models)

    def populate_record(yatsm, i_rec, i_start, i_end, i_break):
        yatsm.record[i_rec]['start'] = yatsm.dates[i_start]
        yatsm.record[i_rec]['end'] = yatsm.dates[i_end]
        yatsm.record[i_rec]['break'] = (yatsm.dates[i_break] if i_break
                                        else i_break)
        yatsm.fit_models(X[i_start:i_end, :], Y[:, i_start:i_end])
        for i, m in enumerate(yatsm.models):
            yatsm.record[i_rec]['coef'][:, i] = m.coef
            yatsm.record[i_rec]['rmse'][i] = m.rmse
        return yatsm

    i_start = 0
    i_end = i_breaks[0] - 1 if i_breaks[0] else n - 1
    i_break = i_breaks[0]
    yatsm = populate_record(yatsm, 0, i_start, i_end, i_break)

    for idx, i_break in enumerate(i_breaks[1:]):
        i_start = i_breaks[idx] + 1
        i_end = i_break - 1 if i_break else n - 1
        yatsm = populate_record(yatsm, idx + 1, i_start, i_end, i_break)

    return yatsm 

def fit(self, X, y=None):
        """
        Fit the model using X, y as training data. Will also learn the groups that exist within the dataset.

        :param X: array-like, shape=(n_columns, n_samples,) training data.
        :param y: array-like, shape=(n_samples,) training data.
        :return: Returns an instance of self.
        """
        X, y = self.__prepare_input_data(X, y)

        if self.shrinkage is not None:
            self.__set_shrinkage_function()

        self.group_colnames_ = [str(_) for _ in as_list(self.groups)]

        if self.value_columns is not None:
            self.value_colnames_ = [str(_) for _ in as_list(self.value_columns)]
        else:
            self.value_colnames_ = [
                _ for _ in X.columns if _ not in self.group_colnames_
            ]
        self.__validate(X, y)

        # List of all hierarchical subsets of columns
        self.group_colnames_hierarchical_ = expanding_list(self.group_colnames_, list)

        self.fallback_ = None

        if self.shrinkage is None and self.use_global_model:
            subset_x = X[self.value_colnames_]
            self.fallback_ = clone(self.estimator).fit(subset_x, y)

        if self.shrinkage is not None:
            self.estimators_ = {}

            for level_colnames in self.group_colnames_hierarchical_:
                self.estimators_.update(
                    self.__fit_grouped_estimator(
                        X, y, self.value_colnames_, level_colnames
                    )
                )
        else:
            self.estimators_ = self.__fit_grouped_estimator(
                X, y, self.value_colnames_, self.group_colnames_
            )

        self.groups_ = as_list(self.estimators_.keys())

        if self.shrinkage is not None:
            self.shrinkage_factors_ = self.__get_shrinkage_factor(X)

        return self 

def fit(self, X, y, max_iterations=20, sample_weight=None):
        """
        Fit DeepSuperLearner on training data (X,y).

        Parameters
        ----------
        X : numpy array of shape [n,l] (Training samples with their l-features per sample) 
        y : numpy array of shape [n] (Classification Ground-truth)
        
        Attributes
        ----------
        max_iterations: maximum number of iterations until convergance.
        sample_weight: numpy array of shape [n,]
        
        Returns
        -------
        self : returns an instance of self.
        """
        n, j = len(y) , len(np.unique(y))
        self.__classes_n = j
        latest_loss = np.finfo(np.double).max
        weights_per_iteration = []
        fitted_learners_per_iteration = []
        for iteration in range(max_iterations):
            fitted_learners_per_fold = np.empty(shape=(self.Kfolds, self.n_baselearners),
                                                dtype=np.object)
            y_pred_fold = np.empty(shape=(n, self.n_baselearners, j))
            folds = StratifiedKFold(n_splits=self.Kfolds, shuffle=False)
            for fold_i, fold_indexes in enumerate(folds.split(X, y)):
                train_index, test_index = fold_indexes
                X_train, X_test = X[train_index], X[test_index]
                y_train, y_test = y[train_index], y[test_index]
                for i, baselrn in enumerate(self.BL.items()):
                    name, bl = baselrn
                    baselearner = clone(bl)
                    try:
                        baselearner.fit(X_train, y_train, sample_weight=sample_weight)
                    except TypeError as e:
                        baselearner.fit(X_train, y_train)
                    fitted_learners_per_fold[fold_i, i] = baselearner
                    y_pred_fold[test_index, i, :] = self._get_prediction(baselearner, X_test)
            
            fitted_learners_per_iteration.append(fitted_learners_per_fold)
            tmp_weights = self._get_weights(y, y_pred_fold)
            avg_probs = self._get_weighted_prediction(y_pred_fold, tmp_weights)
            loss = self._get_logloss(y, avg_probs)
            weights_per_iteration.append(tmp_weights)
            print("Iteration: {} Loss: {}".format(iteration, loss))
            print("Weights: ", tmp_weights)
            if loss < latest_loss:
                latest_loss = loss
                X = np.hstack((X, avg_probs))
            else:
                weights_per_iteration = weights_per_iteration[:-1]
                fitted_learners_per_iteration = fitted_learners_per_iteration[:-1]
                break
        
        self.weights_per_iteration = weights_per_iteration
        self.fitted_learners_per_iteration = fitted_learners_per_iteration

        return self