""" The :mod:`sklearn.compose._column_transformer` module implements utilities to work with heterogeneous data and to apply different transformers to different columns. """ # Author: Andreas Mueller # Joris Van den Bossche # License: BSD from itertools import chain from collections import Counter import numpy as np from scipy import sparse from ..base import clone, TransformerMixin from ..utils._estimator_html_repr import _VisualBlock from ..pipeline import _fit_transform_one, _transform_one, _name_estimators from ..preprocessing import FunctionTransformer from ..utils import Bunch from ..utils import _safe_indexing from ..utils import _get_column_indices from ..utils._set_output import _get_output_config, _safe_set_output from ..utils import check_pandas_support from ..utils.metaestimators import _BaseComposition from ..utils.validation import check_array, check_is_fitted, _check_feature_names_in from ..utils.parallel import delayed, Parallel __all__ = ["ColumnTransformer", "make_column_transformer", "make_column_selector"] _ERR_MSG_1DCOLUMN = ( "1D data passed to a transformer that expects 2D data. " "Try to specify the column selection as a list of one " "item instead of a scalar." ) class ColumnTransformer(TransformerMixin, _BaseComposition): """Applies transformers to columns of an array or pandas DataFrame. This estimator allows different columns or column subsets of the input to be transformed separately and the features generated by each transformer will be concatenated to form a single feature space. This is useful for heterogeneous or columnar data, to combine several feature extraction mechanisms or transformations into a single transformer. Read more in the :ref:`User Guide `. .. versionadded:: 0.20 Parameters ---------- transformers : list of tuples List of (name, transformer, columns) tuples specifying the transformer objects to be applied to subsets of the data. name : str Like in Pipeline and FeatureUnion, this allows the transformer and its parameters to be set using ``set_params`` and searched in grid search. transformer : {'drop', 'passthrough'} or estimator Estimator must support :term:`fit` and :term:`transform`. Special-cased strings 'drop' and 'passthrough' are accepted as well, to indicate to drop the columns or to pass them through untransformed, respectively. columns : str, array-like of str, int, array-like of int, \ array-like of bool, slice or callable Indexes the data on its second axis. Integers are interpreted as positional columns, while strings can reference DataFrame columns by name. A scalar string or int should be used where ``transformer`` expects X to be a 1d array-like (vector), otherwise a 2d array will be passed to the transformer. A callable is passed the input data `X` and can return any of the above. To select multiple columns by name or dtype, you can use :obj:`make_column_selector`. remainder : {'drop', 'passthrough'} or estimator, default='drop' By default, only the specified columns in `transformers` are transformed and combined in the output, and the non-specified columns are dropped. (default of ``'drop'``). By specifying ``remainder='passthrough'``, all remaining columns that were not specified in `transformers`, but present in the data passed to `fit` will be automatically passed through. This subset of columns is concatenated with the output of the transformers. For dataframes, extra columns not seen during `fit` will be excluded from the output of `transform`. By setting ``remainder`` to be an estimator, the remaining non-specified columns will use the ``remainder`` estimator. The estimator must support :term:`fit` and :term:`transform`. Note that using this feature requires that the DataFrame columns input at :term:`fit` and :term:`transform` have identical order. sparse_threshold : float, default=0.3 If the output of the different transformers contains sparse matrices, these will be stacked as a sparse matrix if the overall density is lower than this value. Use ``sparse_threshold=0`` to always return dense. When the transformed output consists of all dense data, the stacked result will be dense, and this keyword will be ignored. n_jobs : int, default=None Number of jobs to run in parallel. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. transformer_weights : dict, default=None Multiplicative weights for features per transformer. The output of the transformer is multiplied by these weights. Keys are transformer names, values the weights. verbose : bool, default=False If True, the time elapsed while fitting each transformer will be printed as it is completed. verbose_feature_names_out : bool, default=True If True, :meth:`get_feature_names_out` will prefix all feature names with the name of the transformer that generated that feature. If False, :meth:`get_feature_names_out` will not prefix any feature names and will error if feature names are not unique. .. versionadded:: 1.0 Attributes ---------- transformers_ : list The collection of fitted transformers as tuples of (name, fitted_transformer, column). `fitted_transformer` can be an estimator, 'drop', or 'passthrough'. In case there were no columns selected, this will be the unfitted transformer. If there are remaining columns, the final element is a tuple of the form: ('remainder', transformer, remaining_columns) corresponding to the ``remainder`` parameter. If there are remaining columns, then ``len(transformers_)==len(transformers)+1``, otherwise ``len(transformers_)==len(transformers)``. named_transformers_ : :class:`~sklearn.utils.Bunch` Read-only attribute to access any transformer by given name. Keys are transformer names and values are the fitted transformer objects. sparse_output_ : bool Boolean flag indicating whether the output of ``transform`` is a sparse matrix or a dense numpy array, which depends on the output of the individual transformers and the `sparse_threshold` keyword. output_indices_ : dict A dictionary from each transformer name to a slice, where the slice corresponds to indices in the transformed output. This is useful to inspect which transformer is responsible for which transformed feature(s). .. versionadded:: 1.0 n_features_in_ : int Number of features seen during :term:`fit`. Only defined if the underlying transformers expose such an attribute when fit. .. versionadded:: 0.24 See Also -------- make_column_transformer : Convenience function for combining the outputs of multiple transformer objects applied to column subsets of the original feature space. make_column_selector : Convenience function for selecting columns based on datatype or the columns name with a regex pattern. Notes ----- The order of the columns in the transformed feature matrix follows the order of how the columns are specified in the `transformers` list. Columns of the original feature matrix that are not specified are dropped from the resulting transformed feature matrix, unless specified in the `passthrough` keyword. Those columns specified with `passthrough` are added at the right to the output of the transformers. Examples -------- >>> import numpy as np >>> from sklearn.compose import ColumnTransformer >>> from sklearn.preprocessing import Normalizer >>> ct = ColumnTransformer( ... [("norm1", Normalizer(norm='l1'), [0, 1]), ... ("norm2", Normalizer(norm='l1'), slice(2, 4))]) >>> X = np.array([[0., 1., 2., 2.], ... [1., 1., 0., 1.]]) >>> # Normalizer scales each row of X to unit norm. A separate scaling >>> # is applied for the two first and two last elements of each >>> # row independently. >>> ct.fit_transform(X) array([[0. , 1. , 0.5, 0.5], [0.5, 0.5, 0. , 1. ]]) :class:`ColumnTransformer` can be configured with a transformer that requires a 1d array by setting the column to a string: >>> from sklearn.feature_extraction import FeatureHasher >>> from sklearn.preprocessing import MinMaxScaler >>> import pandas as pd # doctest: +SKIP >>> X = pd.DataFrame({ ... "documents": ["First item", "second one here", "Is this the last?"], ... "width": [3, 4, 5], ... }) # doctest: +SKIP >>> # "documents" is a string which configures ColumnTransformer to >>> # pass the documents column as a 1d array to the FeatureHasher >>> ct = ColumnTransformer( ... [("text_preprocess", FeatureHasher(input_type="string"), "documents"), ... ("num_preprocess", MinMaxScaler(), ["width"])]) >>> X_trans = ct.fit_transform(X) # doctest: +SKIP """ _required_parameters = ["transformers"] def __init__( self, transformers, *, remainder="drop", sparse_threshold=0.3, n_jobs=None, transformer_weights=None, verbose=False, verbose_feature_names_out=True, ): self.transformers = transformers self.remainder = remainder self.sparse_threshold = sparse_threshold self.n_jobs = n_jobs self.transformer_weights = transformer_weights self.verbose = verbose self.verbose_feature_names_out = verbose_feature_names_out @property def _transformers(self): """ Internal list of transformer only containing the name and transformers, dropping the columns. This is for the implementation of get_params via BaseComposition._get_params which expects lists of tuples of len 2. """ try: return [(name, trans) for name, trans, _ in self.transformers] except (TypeError, ValueError): return self.transformers @_transformers.setter def _transformers(self, value): try: self.transformers = [ (name, trans, col) for ((name, trans), (_, _, col)) in zip(value, self.transformers) ] except (TypeError, ValueError): self.transformers = value def set_output(self, *, transform=None): """Set the output container when `"transform"` and `"fit_transform"` are called. Calling `set_output` will set the output of all estimators in `transformers` and `transformers_`. Parameters ---------- transform : {"default", "pandas"}, default=None Configure output of `transform` and `fit_transform`. - `"default"`: Default output format of a transformer - `"pandas"`: DataFrame output - `None`: Transform configuration is unchanged Returns ------- self : estimator instance Estimator instance. """ super().set_output(transform=transform) transformers = ( trans for _, trans, _ in chain( self.transformers, getattr(self, "transformers_", []) ) if trans not in {"passthrough", "drop"} ) for trans in transformers: _safe_set_output(trans, transform=transform) return self def get_params(self, deep=True): """Get parameters for this estimator. Returns the parameters given in the constructor as well as the estimators contained within the `transformers` of the `ColumnTransformer`. Parameters ---------- deep : bool, default=True If True, will return the parameters for this estimator and contained subobjects that are estimators. Returns ------- params : dict Parameter names mapped to their values. """ return self._get_params("_transformers", deep=deep) def set_params(self, **kwargs): """Set the parameters of this estimator. Valid parameter keys can be listed with ``get_params()``. Note that you can directly set the parameters of the estimators contained in `transformers` of `ColumnTransformer`. Parameters ---------- **kwargs : dict Estimator parameters. Returns ------- self : ColumnTransformer This estimator. """ self._set_params("_transformers", **kwargs) return self def _iter(self, fitted=False, replace_strings=False, column_as_strings=False): """ Generate (name, trans, column, weight) tuples. If fitted=True, use the fitted transformers, else use the user specified transformers updated with converted column names and potentially appended with transformer for remainder. """ if fitted: if replace_strings: # Replace "passthrough" with the fitted version in # _name_to_fitted_passthrough def replace_passthrough(name, trans, columns): if name not in self._name_to_fitted_passthrough: return name, trans, columns return name, self._name_to_fitted_passthrough[name], columns transformers = [ replace_passthrough(*trans) for trans in self.transformers_ ] else: transformers = self.transformers_ else: # interleave the validated column specifiers transformers = [ (name, trans, column) for (name, trans, _), column in zip(self.transformers, self._columns) ] # add transformer tuple for remainder if self._remainder[2]: transformers = chain(transformers, [self._remainder]) get_weight = (self.transformer_weights or {}).get output_config = _get_output_config("transform", self) for name, trans, columns in transformers: if replace_strings: # replace 'passthrough' with identity transformer and # skip in case of 'drop' if trans == "passthrough": trans = FunctionTransformer( accept_sparse=True, check_inverse=False, feature_names_out="one-to-one", ).set_output(transform=output_config["dense"]) elif trans == "drop": continue elif _is_empty_column_selection(columns): continue if column_as_strings: # Convert all columns to using their string labels columns_is_scalar = np.isscalar(columns) indices = self._transformer_to_input_indices[name] columns = self.feature_names_in_[indices] if columns_is_scalar: # selection is done with one dimension columns = columns[0] yield (name, trans, columns, get_weight(name)) def _validate_transformers(self): if not self.transformers: return names, transformers, _ = zip(*self.transformers) # validate names self._validate_names(names) # validate estimators for t in transformers: if t in ("drop", "passthrough"): continue if not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not hasattr( t, "transform" ): raise TypeError( "All estimators should implement fit and " "transform, or can be 'drop' or 'passthrough' " "specifiers. '%s' (type %s) doesn't." % (t, type(t)) ) def _validate_column_callables(self, X): """ Converts callable column specifications. """ all_columns = [] transformer_to_input_indices = {} for name, _, columns in self.transformers: if callable(columns): columns = columns(X) all_columns.append(columns) transformer_to_input_indices[name] = _get_column_indices(X, columns) self._columns = all_columns self._transformer_to_input_indices = transformer_to_input_indices def _validate_remainder(self, X): """ Validates ``remainder`` and defines ``_remainder`` targeting the remaining columns. """ is_transformer = ( hasattr(self.remainder, "fit") or hasattr(self.remainder, "fit_transform") ) and hasattr(self.remainder, "transform") if self.remainder not in ("drop", "passthrough") and not is_transformer: raise ValueError( "The remainder keyword needs to be one of 'drop', " "'passthrough', or estimator. '%s' was passed instead" % self.remainder ) self._n_features = X.shape[1] cols = set(chain(*self._transformer_to_input_indices.values())) remaining = sorted(set(range(self._n_features)) - cols) self._remainder = ("remainder", self.remainder, remaining) self._transformer_to_input_indices["remainder"] = remaining @property def named_transformers_(self): """Access the fitted transformer by name. Read-only attribute to access any transformer by given name. Keys are transformer names and values are the fitted transformer objects. """ # Use Bunch object to improve autocomplete return Bunch(**{name: trans for name, trans, _ in self.transformers_}) def _get_feature_name_out_for_transformer( self, name, trans, column, feature_names_in ): """Gets feature names of transformer. Used in conjunction with self._iter(fitted=True) in get_feature_names_out. """ column_indices = self._transformer_to_input_indices[name] names = feature_names_in[column_indices] if trans == "drop" or _is_empty_column_selection(column): return elif trans == "passthrough": return names # An actual transformer if not hasattr(trans, "get_feature_names_out"): raise AttributeError( f"Transformer {name} (type {type(trans).__name__}) does " "not provide get_feature_names_out." ) return trans.get_feature_names_out(names) def get_feature_names_out(self, input_features=None): """Get output feature names for transformation. Parameters ---------- input_features : array-like of str or None, default=None Input features. - If `input_features` is `None`, then `feature_names_in_` is used as feature names in. If `feature_names_in_` is not defined, then the following input feature names are generated: `["x0", "x1", ..., "x(n_features_in_ - 1)"]`. - If `input_features` is an array-like, then `input_features` must match `feature_names_in_` if `feature_names_in_` is defined. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. """ check_is_fitted(self) input_features = _check_feature_names_in(self, input_features) # List of tuples (name, feature_names_out) transformer_with_feature_names_out = [] for name, trans, column, _ in self._iter(fitted=True): feature_names_out = self._get_feature_name_out_for_transformer( name, trans, column, input_features ) if feature_names_out is None: continue transformer_with_feature_names_out.append((name, feature_names_out)) if not transformer_with_feature_names_out: # No feature names return np.array([], dtype=object) return self._add_prefix_for_feature_names_out( transformer_with_feature_names_out ) def _add_prefix_for_feature_names_out(self, transformer_with_feature_names_out): """Add prefix for feature names out that includes the transformer names. Parameters ---------- transformer_with_feature_names_out : list of tuples of (str, array-like of str) The tuple consistent of the transformer's name and its feature names out. Returns ------- feature_names_out : ndarray of shape (n_features,), dtype=str Transformed feature names. """ if self.verbose_feature_names_out: # Prefix the feature names out with the transformers name names = list( chain.from_iterable( (f"{name}__{i}" for i in feature_names_out) for name, feature_names_out in transformer_with_feature_names_out ) ) return np.asarray(names, dtype=object) # verbose_feature_names_out is False # Check that names are all unique without a prefix feature_names_count = Counter( chain.from_iterable(s for _, s in transformer_with_feature_names_out) ) top_6_overlap = [ name for name, count in feature_names_count.most_common(6) if count > 1 ] top_6_overlap.sort() if top_6_overlap: if len(top_6_overlap) == 6: # There are more than 5 overlapping names, we only show the 5 # of the feature names names_repr = str(top_6_overlap[:5])[:-1] + ", ...]" else: names_repr = str(top_6_overlap) raise ValueError( f"Output feature names: {names_repr} are not unique. Please set " "verbose_feature_names_out=True to add prefixes to feature names" ) return np.concatenate( [name for _, name in transformer_with_feature_names_out], ) def _update_fitted_transformers(self, transformers): # transformers are fitted; excludes 'drop' cases fitted_transformers = iter(transformers) transformers_ = [] self._name_to_fitted_passthrough = {} for name, old, column, _ in self._iter(): if old == "drop": trans = "drop" elif old == "passthrough": # FunctionTransformer is present in list of transformers, # so get next transformer, but save original string func_transformer = next(fitted_transformers) trans = "passthrough" # The fitted FunctionTransformer is saved in another attribute, # so it can be used during transform for set_output. self._name_to_fitted_passthrough[name] = func_transformer elif _is_empty_column_selection(column): trans = old else: trans = next(fitted_transformers) transformers_.append((name, trans, column)) # sanity check that transformers is exhausted assert not list(fitted_transformers) self.transformers_ = transformers_ def _validate_output(self, result): """ Ensure that the output of each transformer is 2D. Otherwise hstack can raise an error or produce incorrect results. """ names = [ name for name, _, _, _ in self._iter(fitted=True, replace_strings=True) ] for Xs, name in zip(result, names): if not getattr(Xs, "ndim", 0) == 2: raise ValueError( "The output of the '{0}' transformer should be 2D (scipy " "matrix, array, or pandas DataFrame).".format(name) ) def _record_output_indices(self, Xs): """ Record which transformer produced which column. """ idx = 0 self.output_indices_ = {} for transformer_idx, (name, _, _, _) in enumerate( self._iter(fitted=True, replace_strings=True) ): n_columns = Xs[transformer_idx].shape[1] self.output_indices_[name] = slice(idx, idx + n_columns) idx += n_columns # `_iter` only generates transformers that have a non empty # selection. Here we set empty slices for transformers that # generate no output, which are safe for indexing all_names = [t[0] for t in self.transformers] + ["remainder"] for name in all_names: if name not in self.output_indices_: self.output_indices_[name] = slice(0, 0) def _log_message(self, name, idx, total): if not self.verbose: return None return "(%d of %d) Processing %s" % (idx, total, name) def _fit_transform(self, X, y, func, fitted=False, column_as_strings=False): """ Private function to fit and/or transform on demand. Return value (transformers and/or transformed X data) depends on the passed function. ``fitted=True`` ensures the fitted transformers are used. """ transformers = list( self._iter( fitted=fitted, replace_strings=True, column_as_strings=column_as_strings ) ) try: return Parallel(n_jobs=self.n_jobs)( delayed(func)( transformer=clone(trans) if not fitted else trans, X=_safe_indexing(X, column, axis=1), y=y, weight=weight, message_clsname="ColumnTransformer", message=self._log_message(name, idx, len(transformers)), ) for idx, (name, trans, column, weight) in enumerate(transformers, 1) ) except ValueError as e: if "Expected 2D array, got 1D array instead" in str(e): raise ValueError(_ERR_MSG_1DCOLUMN) from e else: raise def fit(self, X, y=None): """Fit all transformers using X. Parameters ---------- X : {array-like, dataframe} of shape (n_samples, n_features) Input data, of which specified subsets are used to fit the transformers. y : array-like of shape (n_samples,...), default=None Targets for supervised learning. Returns ------- self : ColumnTransformer This estimator. """ # we use fit_transform to make sure to set sparse_output_ (for which we # need the transformed data) to have consistent output type in predict self.fit_transform(X, y=y) return self def fit_transform(self, X, y=None): """Fit all transformers, transform the data and concatenate results. Parameters ---------- X : {array-like, dataframe} of shape (n_samples, n_features) Input data, of which specified subsets are used to fit the transformers. y : array-like of shape (n_samples,), default=None Targets for supervised learning. Returns ------- X_t : {array-like, sparse matrix} of \ shape (n_samples, sum_n_components) Horizontally stacked results of transformers. sum_n_components is the sum of n_components (output dimension) over transformers. If any result is a sparse matrix, everything will be converted to sparse matrices. """ self._check_feature_names(X, reset=True) X = _check_X(X) # set n_features_in_ attribute self._check_n_features(X, reset=True) self._validate_transformers() self._validate_column_callables(X) self._validate_remainder(X) result = self._fit_transform(X, y, _fit_transform_one) if not result: self._update_fitted_transformers([]) # All transformers are None return np.zeros((X.shape[0], 0)) Xs, transformers = zip(*result) # determine if concatenated output will be sparse or not if any(sparse.issparse(X) for X in Xs): nnz = sum(X.nnz if sparse.issparse(X) else X.size for X in Xs) total = sum( X.shape[0] * X.shape[1] if sparse.issparse(X) else X.size for X in Xs ) density = nnz / total self.sparse_output_ = density < self.sparse_threshold else: self.sparse_output_ = False self._update_fitted_transformers(transformers) self._validate_output(Xs) self._record_output_indices(Xs) return self._hstack(list(Xs)) def transform(self, X): """Transform X separately by each transformer, concatenate results. Parameters ---------- X : {array-like, dataframe} of shape (n_samples, n_features) The data to be transformed by subset. Returns ------- X_t : {array-like, sparse matrix} of \ shape (n_samples, sum_n_components) Horizontally stacked results of transformers. sum_n_components is the sum of n_components (output dimension) over transformers. If any result is a sparse matrix, everything will be converted to sparse matrices. """ check_is_fitted(self) X = _check_X(X) fit_dataframe_and_transform_dataframe = hasattr( self, "feature_names_in_" ) and hasattr(X, "columns") if fit_dataframe_and_transform_dataframe: named_transformers = self.named_transformers_ # check that all names seen in fit are in transform, unless # they were dropped non_dropped_indices = [ ind for name, ind in self._transformer_to_input_indices.items() if name in named_transformers and isinstance(named_transformers[name], str) and named_transformers[name] != "drop" ] all_indices = set(chain(*non_dropped_indices)) all_names = set(self.feature_names_in_[ind] for ind in all_indices) diff = all_names - set(X.columns) if diff: raise ValueError(f"columns are missing: {diff}") else: # ndarray was used for fitting or transforming, thus we only # check that n_features_in_ is consistent self._check_n_features(X, reset=False) Xs = self._fit_transform( X, None, _transform_one, fitted=True, column_as_strings=fit_dataframe_and_transform_dataframe, ) self._validate_output(Xs) if not Xs: # All transformers are None return np.zeros((X.shape[0], 0)) return self._hstack(list(Xs)) def _hstack(self, Xs): """Stacks Xs horizontally. This allows subclasses to control the stacking behavior, while reusing everything else from ColumnTransformer. Parameters ---------- Xs : list of {array-like, sparse matrix, dataframe} """ if self.sparse_output_: try: # since all columns should be numeric before stacking them # in a sparse matrix, `check_array` is used for the # dtype conversion if necessary. converted_Xs = [ check_array(X, accept_sparse=True, force_all_finite=False) for X in Xs ] except ValueError as e: raise ValueError( "For a sparse output, all columns should " "be a numeric or convertible to a numeric." ) from e return sparse.hstack(converted_Xs).tocsr() else: Xs = [f.toarray() if sparse.issparse(f) else f for f in Xs] config = _get_output_config("transform", self) if config["dense"] == "pandas" and all(hasattr(X, "iloc") for X in Xs): pd = check_pandas_support("transform") output = pd.concat(Xs, axis=1) # If all transformers define `get_feature_names_out`, then transform # will adjust the column names to be consistent with # verbose_feature_names_out. Here we prefix the feature names if # verbose_feature_names_out=True. if not self.verbose_feature_names_out: return output transformer_names = [ t[0] for t in self._iter(fitted=True, replace_strings=True) ] # Selection of columns might be empty. # Hence feature names are filtered for non-emptiness. feature_names_outs = [X.columns for X in Xs if X.shape[1] != 0] names_out = self._add_prefix_for_feature_names_out( list(zip(transformer_names, feature_names_outs)) ) output.columns = names_out return output return np.hstack(Xs) def _sk_visual_block_(self): if isinstance(self.remainder, str) and self.remainder == "drop": transformers = self.transformers elif hasattr(self, "_remainder"): remainder_columns = self._remainder[2] if ( hasattr(self, "feature_names_in_") and remainder_columns and not all(isinstance(col, str) for col in remainder_columns) ): remainder_columns = self.feature_names_in_[remainder_columns].tolist() transformers = chain( self.transformers, [("remainder", self.remainder, remainder_columns)] ) else: transformers = chain(self.transformers, [("remainder", self.remainder, "")]) names, transformers, name_details = zip(*transformers) return _VisualBlock( "parallel", transformers, names=names, name_details=name_details ) def _check_X(X): """Use check_array only on lists and other non-array-likes / sparse""" if hasattr(X, "__array__") or sparse.issparse(X): return X return check_array(X, force_all_finite="allow-nan", dtype=object) def _is_empty_column_selection(column): """ Return True if the column selection is empty (empty list or all-False boolean array). """ if hasattr(column, "dtype") and np.issubdtype(column.dtype, np.bool_): return not column.any() elif hasattr(column, "__len__"): return ( len(column) == 0 or all(isinstance(col, bool) for col in column) and not any(column) ) else: return False def _get_transformer_list(estimators): """ Construct (name, trans, column) tuples from list """ transformers, columns = zip(*estimators) names, _ = zip(*_name_estimators(transformers)) transformer_list = list(zip(names, transformers, columns)) return transformer_list def make_column_transformer( *transformers, remainder="drop", sparse_threshold=0.3, n_jobs=None, verbose=False, verbose_feature_names_out=True, ): """Construct a ColumnTransformer from the given transformers. This is a shorthand for the ColumnTransformer constructor; it does not require, and does not permit, naming the transformers. Instead, they will be given names automatically based on their types. It also does not allow weighting with ``transformer_weights``. Read more in the :ref:`User Guide `. Parameters ---------- *transformers : tuples Tuples of the form (transformer, columns) specifying the transformer objects to be applied to subsets of the data. transformer : {'drop', 'passthrough'} or estimator Estimator must support :term:`fit` and :term:`transform`. Special-cased strings 'drop' and 'passthrough' are accepted as well, to indicate to drop the columns or to pass them through untransformed, respectively. columns : str, array-like of str, int, array-like of int, slice, \ array-like of bool or callable Indexes the data on its second axis. Integers are interpreted as positional columns, while strings can reference DataFrame columns by name. A scalar string or int should be used where ``transformer`` expects X to be a 1d array-like (vector), otherwise a 2d array will be passed to the transformer. A callable is passed the input data `X` and can return any of the above. To select multiple columns by name or dtype, you can use :obj:`make_column_selector`. remainder : {'drop', 'passthrough'} or estimator, default='drop' By default, only the specified columns in `transformers` are transformed and combined in the output, and the non-specified columns are dropped. (default of ``'drop'``). By specifying ``remainder='passthrough'``, all remaining columns that were not specified in `transformers` will be automatically passed through. This subset of columns is concatenated with the output of the transformers. By setting ``remainder`` to be an estimator, the remaining non-specified columns will use the ``remainder`` estimator. The estimator must support :term:`fit` and :term:`transform`. sparse_threshold : float, default=0.3 If the transformed output consists of a mix of sparse and dense data, it will be stacked as a sparse matrix if the density is lower than this value. Use ``sparse_threshold=0`` to always return dense. When the transformed output consists of all sparse or all dense data, the stacked result will be sparse or dense, respectively, and this keyword will be ignored. n_jobs : int, default=None Number of jobs to run in parallel. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. verbose : bool, default=False If True, the time elapsed while fitting each transformer will be printed as it is completed. verbose_feature_names_out : bool, default=True If True, :meth:`get_feature_names_out` will prefix all feature names with the name of the transformer that generated that feature. If False, :meth:`get_feature_names_out` will not prefix any feature names and will error if feature names are not unique. .. versionadded:: 1.0 Returns ------- ct : ColumnTransformer Returns a :class:`ColumnTransformer` object. See Also -------- ColumnTransformer : Class that allows combining the outputs of multiple transformer objects used on column subsets of the data into a single feature space. Examples -------- >>> from sklearn.preprocessing import StandardScaler, OneHotEncoder >>> from sklearn.compose import make_column_transformer >>> make_column_transformer( ... (StandardScaler(), ['numerical_column']), ... (OneHotEncoder(), ['categorical_column'])) ColumnTransformer(transformers=[('standardscaler', StandardScaler(...), ['numerical_column']), ('onehotencoder', OneHotEncoder(...), ['categorical_column'])]) """ # transformer_weights keyword is not passed through because the user # would need to know the automatically generated names of the transformers transformer_list = _get_transformer_list(transformers) return ColumnTransformer( transformer_list, n_jobs=n_jobs, remainder=remainder, sparse_threshold=sparse_threshold, verbose=verbose, verbose_feature_names_out=verbose_feature_names_out, ) class make_column_selector: """Create a callable to select columns to be used with :class:`ColumnTransformer`. :func:`make_column_selector` can select columns based on datatype or the columns name with a regex. When using multiple selection criteria, **all** criteria must match for a column to be selected. Parameters ---------- pattern : str, default=None Name of columns containing this regex pattern will be included. If None, column selection will not be selected based on pattern. dtype_include : column dtype or list of column dtypes, default=None A selection of dtypes to include. For more details, see :meth:`pandas.DataFrame.select_dtypes`. dtype_exclude : column dtype or list of column dtypes, default=None A selection of dtypes to exclude. For more details, see :meth:`pandas.DataFrame.select_dtypes`. Returns ------- selector : callable Callable for column selection to be used by a :class:`ColumnTransformer`. See Also -------- ColumnTransformer : Class that allows combining the outputs of multiple transformer objects used on column subsets of the data into a single feature space. Examples -------- >>> from sklearn.preprocessing import StandardScaler, OneHotEncoder >>> from sklearn.compose import make_column_transformer >>> from sklearn.compose import make_column_selector >>> import numpy as np >>> import pandas as pd # doctest: +SKIP >>> X = pd.DataFrame({'city': ['London', 'London', 'Paris', 'Sallisaw'], ... 'rating': [5, 3, 4, 5]}) # doctest: +SKIP >>> ct = make_column_transformer( ... (StandardScaler(), ... make_column_selector(dtype_include=np.number)), # rating ... (OneHotEncoder(), ... make_column_selector(dtype_include=object))) # city >>> ct.fit_transform(X) # doctest: +SKIP array([[ 0.90453403, 1. , 0. , 0. ], [-1.50755672, 1. , 0. , 0. ], [-0.30151134, 0. , 1. , 0. ], [ 0.90453403, 0. , 0. , 1. ]]) """ def __init__(self, pattern=None, *, dtype_include=None, dtype_exclude=None): self.pattern = pattern self.dtype_include = dtype_include self.dtype_exclude = dtype_exclude def __call__(self, df): """Callable for column selection to be used by a :class:`ColumnTransformer`. Parameters ---------- df : dataframe of shape (n_features, n_samples) DataFrame to select columns from. """ if not hasattr(df, "iloc"): raise ValueError( "make_column_selector can only be applied to pandas dataframes" ) df_row = df.iloc[:1] if self.dtype_include is not None or self.dtype_exclude is not None: df_row = df_row.select_dtypes( include=self.dtype_include, exclude=self.dtype_exclude ) cols = df_row.columns if self.pattern is not None: cols = cols[cols.str.contains(self.pattern, regex=True)] return cols.tolist()