Multi-Hot

class category_encoders.multi_hot.MultiHotEncoder(verbose: int = 0, cols: list[str] | None = None, drop_invariant: bool = False, return_df: bool = True, handle_unknown: str = 'value', handle_missing: str = 'value', delimiter: str = '|', use_cat_names: bool = False)

Multi-hot encoding for cells that contain several delimiter-separated items.

Where OneHotEncoder treats each cell as one atomic category, MultiHotEncoder splits the cell on a delimiter and activates one binary column per item, so that 'mathematics|physics' lights both the mathematics and the physics column. The set of items is learned at fit time; the number of output columns is fixed by the fit, so get_feature_names_out always matches the transform output.

Items are the delimiter-split fragments of a cell with surrounding whitespace stripped; fragments that are empty after stripping are dropped. This means a cell such as 'a | b', 'a||b' or 'a|' contributes the items a and b (or, for the last two, only a), and a cell that is empty or consists solely of the delimiter contributes no items. Items cannot themselves contain the delimiter: a cell such as 'Smith, John' with the default delimiter is stored as two items, so choose a delimiter that does not occur inside the items.

The encoding is unsupervised and has no inverse_transform: a multi-hot row does not uniquely determine the original cell.

Parameters:

verbose: int

integer indicating verbosity of the output. 0 for none.

cols: list

a list of columns to encode, if None, all string and categorical columns will be encoded.

drop_invariant: bool

boolean for whether to drop columns with 0 variance.

return_df: bool

boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).

handle_unknown: str

how to handle items that were not seen at fit time. Options are ‘error’, ‘return_nan’, ‘value’, and ‘indicator’. The default is ‘value’.

‘error’ will raise a ValueError at transform time if an unknown item appears. ‘return_nan’ will encode a row that contains an unknown item as np.nan in every dummy column of the affected input column. ‘value’ will ignore unknown items; the known items of the same cell still activate their columns, so a fully unknown cell becomes all zeros. ‘indicator’ behaves like ‘value’ and additionally adds one dummy column per input column (in both training and test data) that is activated whenever an unknown item appears.

handle_missing: str

how to handle missing values (NaN). Options are ‘error’, ‘return_nan’, ‘value’, ‘ignore’, and ‘indicator’. The default is ‘value’.

‘error’ will raise a ValueError if a missing value is encountered. ‘return_nan’ will encode a row that contains a missing value as np.nan in every dummy column of the affected input column. ‘value’ will treat missing values as another valid item at fit time, so a missing cell activates the missing-item column. ‘ignore’ will encode missing values as 0 in every dummy column, NOT adding an additional category. ‘indicator’ behaves like ‘ignore’ and additionally adds one dummy column per input column that is activated whenever a value is missing.

delimiter: str

the string that separates multiple items within one cell. Must be a non-empty string and must not occur inside a single item.

use_cat_names: bool

if True, the seen item values will be included in the encoded column names (e.g. city_paris); collisions are suffixed with ‘#’. If False, columns are named by order of first appearance (e.g. city_1), which keeps the names stable under category relabeling.

Methods

fit(X[, y])	Fits the encoder according to X and y.
fit_transform(X[, y])	Fit to data, then transform it.
get_feature_names()	Deprecated method to get feature names.
get_feature_names_in()	Get the names of all input columns present when fitting.
get_feature_names_out([input_features])	Get the names of all transformed / added columns.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_output(*[, transform])	Set output container.
set_params(**params)	Set the parameters of this estimator.
set_transform_request(*[, override_return_df])	Configure whether metadata should be requested to be passed to the transform method.
transform(X[, override_return_df])	Perform the transformation to new categorical data.

fit(X: ndarray | DataFrame | list | generic | csr_matrix, y: list | Series | ndarray | tuple | DataFrame | None = None, **kwargs)

Fits the encoder according to X and y.

Parameters:

Xarray-like, shape = [n_samples, n_features]

Training vectors, where n_samples is the number of samples and n_features is the number of features.

yarray-like, shape = [n_samples]

Target values.

Returns:

selfencoder

Returns self.

fit_transform(X, y=None, **fit_params)

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

Parameters:

Xarray-like of shape (n_samples, n_features)

Input samples.

yarray-like of shape (n_samples,) or (n_samples, n_outputs), default=None

Target values (None for unsupervised transformations).

**fit_paramsdict

Additional fit parameters. Pass only if the estimator accepts additional params in its fit method.

Returns:

X_newndarray array of shape (n_samples, n_features_new)

Transformed array.

get_feature_names() → ndarray

Deprecated method to get feature names. Use get_feature_names_out instead.

get_feature_names_in() → ndarray

Get the names of all input columns present when fitting.

These columns are necessary for the transform step.

get_feature_names_out(input_features=None) → ndarray

Get the names of all transformed / added columns.

Note that in sklearn the get_feature_names_out function takes the feature_names_in as an argument and determines the output feature names using the input. A fit is usually not necessary and if so a NotFittedError is raised. We just require a fit all the time and return the fitted output columns.

Returns:

feature_names: np.ndarray

A numpy array with all feature names transformed or added. Note: potentially dropped features (because the feature is constant/invariant) are not included!

get_metadata_routing()

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routingMetadataRequest

A MetadataRequest encapsulating routing information.

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict

Parameter names mapped to their values.

set_output(*, transform=None)

Set output container.

Refer to the user guide for more details and sphx_glr_auto_examples_miscellaneous_plot_set_output.py for an example on how to use the API.

Parameters:

transform{“default”, “pandas”, “polars”}, default=None

Configure output of transform and fit_transform.

• “default”: Default output format of a transformer

• “pandas”: DataFrame output

• “polars”: Polars output

• None: Transform configuration is unchanged

Added in version 1.4: “polars” option was added.

Returns:

selfestimator instance

Estimator instance.

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict

Estimator parameters.

Returns:

selfestimator instance

Estimator instance.

set_transform_request(*, override_return_df: bool | None | str = '$UNCHANGED$') → MultiHotEncoder

Configure whether metadata should be requested to be passed to the transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to transform.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

override_return_dfstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for override_return_df parameter in transform.

Returns:

selfobject

The updated object.

transform(X: ndarray | DataFrame | list | generic | csr_matrix, override_return_df: bool = False)

Perform the transformation to new categorical data.

Parameters:

Xarray-like, shape = [n_samples, n_features]

override_return_dfbool

override self.return_df to force to return a data frame

Returns:

parray or DataFrame, shape = [n_samples, n_features_out]

Transformed values with encoding applied.

Notes

If the encoder was fitted on a DataFrame, arraylike input (e.g. the numpy array emitted by the previous step of a scikit-learn pipeline) is accepted: the fitted column names are re-attached positionally, so the result matches transforming the equivalent DataFrame (GH #406). A DataFrame may additionally carry extra pass-through columns beyond the encoded ones (GH #367).