Skip to content

Column one hot encoder

This file is part of the TPOT library.

The current version of TPOT was developed at Cedars-Sinai by: - Pedro Henrique Ribeiro (https://github.com/perib, https://www.linkedin.com/in/pedro-ribeiro/) - Anil Saini (anil.saini@cshs.org) - Jose Hernandez (jgh9094@gmail.com) - Jay Moran (jay.moran@cshs.org) - Nicholas Matsumoto (nicholas.matsumoto@cshs.org) - Hyunjun Choi (hyunjun.choi@cshs.org) - Gabriel Ketron (gabriel.ketron@cshs.org) - Miguel E. Hernandez (miguel.e.hernandez@cshs.org) - Jason Moore (moorejh28@gmail.com)

The original version of TPOT was primarily developed at the University of Pennsylvania by: - Randal S. Olson (rso@randalolson.com) - Weixuan Fu (weixuanf@upenn.edu) - Daniel Angell (dpa34@drexel.edu) - Jason Moore (moorejh28@gmail.com) - and many more generous open-source contributors

TPOT is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

TPOT is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details.

You should have received a copy of the GNU Lesser General Public License along with TPOT. If not, see http://www.gnu.org/licenses/.

ColumnOneHotEncoder

Bases: TransformerMixin, BaseEstimator

Source code in tpot/builtin_modules/column_one_hot_encoder.py 
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
class ColumnOneHotEncoder(TransformerMixin, BaseEstimator ):


    def __init__(self, columns='auto', drop=None, handle_unknown='infrequent_if_exist', sparse_output=False, min_frequency=None,max_categories=None):
        '''
        A wrapper for OneHotEncoder that allows for onehot encoding of specific columns in a DataFrame or np array.

        Parameters
        ----------

        columns : str, list, default='auto'
            Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder.
            - 'auto' : Automatically select categorical features based on columns with less than 10 unique values
            - 'categorical' : Automatically select categorical features
            - 'numeric' : Automatically select numeric features
            - 'all' : Select all features
            - list : A list of columns to select

        drop, handle_unknown, sparse_output, min_frequency, max_categories : see sklearn.preprocessing.OneHotEncoder

        '''

        self.columns = columns
        self.drop = drop
        self.handle_unknown = handle_unknown
        self.sparse_output = sparse_output
        self.min_frequency = min_frequency
        self.max_categories = max_categories



    def fit(self, X, y=None):
        """Fit OneHotEncoder to X, then transform X.

        Equivalent to self.fit(X).transform(X), but more convenient and more
        efficient. See fit for the parameters, transform for the return value.

        Parameters
        ----------
        X : array-like or sparse matrix, shape=(n_samples, n_features)
            Dense array or sparse matrix.
        y: array-like {n_samples,} (Optional, ignored)
            Feature labels
        """

        if (self.columns == "categorical" or self.columns == "numeric") and not isinstance(X, pd.DataFrame):
            raise ValueError(f"Invalid value for columns: {self.columns}. "
                             "Only 'all' or <list> is supported for np arrays")

        if self.columns == "categorical":
            self.columns_ = list(X.select_dtypes(exclude='number').columns)
        elif self.columns == "numeric":
            self.columns_ =  [col for col in X.columns if is_numeric_dtype(X[col])]
        elif self.columns == "auto":
            self.columns_ = auto_select_categorical_features(X)
        elif self.columns == "all":
            if isinstance(X, pd.DataFrame):
                self.columns_ = X.columns
            else:
                self.columns_ = list(range(X.shape[1]))
        elif isinstance(self.columns, list):
            self.columns_ = self.columns
        else:
            raise ValueError(f"Invalid value for columns: {self.columns}")



        if len(self.columns_) == 0:
            return self

        self.enc = sklearn.preprocessing.OneHotEncoder( categories='auto',   
                                                        drop = self.drop,
                                                        handle_unknown = self.handle_unknown,
                                                        sparse_output = self.sparse_output,
                                                        min_frequency = self.min_frequency,
                                                        max_categories = self.max_categories)

        #TODO make this more consistent with sklearn baseimputer/baseencoder
        if isinstance(X, pd.DataFrame):
            self.enc.set_output(transform="pandas")
            for col in X.columns:
                # check if the column name is not a string
                if not isinstance(col, str):
                    # if it's not a string, rename the column with "X" prefix
                    X.rename(columns={col: f"X{col}"}, inplace=True)


        if len(self.columns_) == X.shape[1]:
            X_sel = self.enc.fit(X)
        else:
            X_sel, X_not_sel = _X_selected(X, self.columns_)
            X_sel = self.enc.fit(X_sel)

        return self

    def transform(self, X):
        """Transform X using one-hot encoding.

        Parameters
        ----------
        X : array-like or sparse matrix, shape=(n_samples, n_features)
            Dense array or sparse matrix.

        Returns
        -------
        X_out : sparse matrix if sparse=True else a 2-d array, dtype=int
            Transformed input.
        """


        if len(self.columns_) == 0:
            return X

        #TODO make this more consistent with sklearn baseimputer/baseencoder
        if isinstance(X, pd.DataFrame):
            for col in X.columns:
                # check if the column name is not a string
                if not isinstance(col, str):
                    # if it's not a string, rename the column with "X" prefix
                    X.rename(columns={col: f"X{col}"}, inplace=True)

        if len(self.columns_) == X.shape[1]:
            return self.enc.transform(X)
        else:

            X_sel, X_not_sel= _X_selected(X, self.columns_)
            X_sel = self.enc.transform(X_sel)

            #If X is dataframe
            if isinstance(X, pd.DataFrame):

                X_sel = pd.DataFrame(X_sel, columns=self.enc.get_feature_names_out())
                return pd.concat([X_not_sel.reset_index(drop=True), X_sel.reset_index(drop=True)], axis=1)
            else:
                return np.hstack((X_not_sel, X_sel))

__init__(columns='auto', drop=None, handle_unknown='infrequent_if_exist', sparse_output=False, min_frequency=None, max_categories=None)

A wrapper for OneHotEncoder that allows for onehot encoding of specific columns in a DataFrame or np array.

Parameters:

Name Type Description Default
columns (str, list)

Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder. - 'auto' : Automatically select categorical features based on columns with less than 10 unique values - 'categorical' : Automatically select categorical features - 'numeric' : Automatically select numeric features - 'all' : Select all features - list : A list of columns to select

 'auto'
drop see sklearn.preprocessing.OneHotEncoder
None
handle_unknown see sklearn.preprocessing.OneHotEncoder
None
sparse_output see sklearn.preprocessing.OneHotEncoder
None
min_frequency see sklearn.preprocessing.OneHotEncoder
None
max_categories see sklearn.preprocessing.OneHotEncoder
None
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
def __init__(self, columns='auto', drop=None, handle_unknown='infrequent_if_exist', sparse_output=False, min_frequency=None,max_categories=None):
    '''
    A wrapper for OneHotEncoder that allows for onehot encoding of specific columns in a DataFrame or np array.

    Parameters
    ----------

    columns : str, list, default='auto'
        Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder.
        - 'auto' : Automatically select categorical features based on columns with less than 10 unique values
        - 'categorical' : Automatically select categorical features
        - 'numeric' : Automatically select numeric features
        - 'all' : Select all features
        - list : A list of columns to select

    drop, handle_unknown, sparse_output, min_frequency, max_categories : see sklearn.preprocessing.OneHotEncoder

    '''

    self.columns = columns
    self.drop = drop
    self.handle_unknown = handle_unknown
    self.sparse_output = sparse_output
    self.min_frequency = min_frequency
    self.max_categories = max_categories

fit(X, y=None)

Fit OneHotEncoder to X, then transform X.

Equivalent to self.fit(X).transform(X), but more convenient and more efficient. See fit for the parameters, transform for the return value.

Parameters:

Name Type Description Default
X array-like or sparse matrix, shape=(n_samples, n_features)

Dense array or sparse matrix.

 required
y

Feature labels

 None
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
def fit(self, X, y=None):
    """Fit OneHotEncoder to X, then transform X.

    Equivalent to self.fit(X).transform(X), but more convenient and more
    efficient. See fit for the parameters, transform for the return value.

    Parameters
    ----------
    X : array-like or sparse matrix, shape=(n_samples, n_features)
        Dense array or sparse matrix.
    y: array-like {n_samples,} (Optional, ignored)
        Feature labels
    """

    if (self.columns == "categorical" or self.columns == "numeric") and not isinstance(X, pd.DataFrame):
        raise ValueError(f"Invalid value for columns: {self.columns}. "
                         "Only 'all' or <list> is supported for np arrays")

    if self.columns == "categorical":
        self.columns_ = list(X.select_dtypes(exclude='number').columns)
    elif self.columns == "numeric":
        self.columns_ =  [col for col in X.columns if is_numeric_dtype(X[col])]
    elif self.columns == "auto":
        self.columns_ = auto_select_categorical_features(X)
    elif self.columns == "all":
        if isinstance(X, pd.DataFrame):
            self.columns_ = X.columns
        else:
            self.columns_ = list(range(X.shape[1]))
    elif isinstance(self.columns, list):
        self.columns_ = self.columns
    else:
        raise ValueError(f"Invalid value for columns: {self.columns}")



    if len(self.columns_) == 0:
        return self

    self.enc = sklearn.preprocessing.OneHotEncoder( categories='auto',   
                                                    drop = self.drop,
                                                    handle_unknown = self.handle_unknown,
                                                    sparse_output = self.sparse_output,
                                                    min_frequency = self.min_frequency,
                                                    max_categories = self.max_categories)

    #TODO make this more consistent with sklearn baseimputer/baseencoder
    if isinstance(X, pd.DataFrame):
        self.enc.set_output(transform="pandas")
        for col in X.columns:
            # check if the column name is not a string
            if not isinstance(col, str):
                # if it's not a string, rename the column with "X" prefix
                X.rename(columns={col: f"X{col}"}, inplace=True)


    if len(self.columns_) == X.shape[1]:
        X_sel = self.enc.fit(X)
    else:
        X_sel, X_not_sel = _X_selected(X, self.columns_)
        X_sel = self.enc.fit(X_sel)

    return self

transform(X)

Transform X using one-hot encoding.

Parameters:

Name Type Description Default
X array-like or sparse matrix, shape=(n_samples, n_features)

Dense array or sparse matrix.

 required

Returns:

Name Type Description
X_out sparse matrix if sparse=True else a 2-d array, dtype=int

Transformed input.
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
def transform(self, X):
    """Transform X using one-hot encoding.

    Parameters
    ----------
    X : array-like or sparse matrix, shape=(n_samples, n_features)
        Dense array or sparse matrix.

    Returns
    -------
    X_out : sparse matrix if sparse=True else a 2-d array, dtype=int
        Transformed input.
    """


    if len(self.columns_) == 0:
        return X

    #TODO make this more consistent with sklearn baseimputer/baseencoder
    if isinstance(X, pd.DataFrame):
        for col in X.columns:
            # check if the column name is not a string
            if not isinstance(col, str):
                # if it's not a string, rename the column with "X" prefix
                X.rename(columns={col: f"X{col}"}, inplace=True)

    if len(self.columns_) == X.shape[1]:
        return self.enc.transform(X)
    else:

        X_sel, X_not_sel= _X_selected(X, self.columns_)
        X_sel = self.enc.transform(X_sel)

        #If X is dataframe
        if isinstance(X, pd.DataFrame):

            X_sel = pd.DataFrame(X_sel, columns=self.enc.get_feature_names_out())
            return pd.concat([X_not_sel.reset_index(drop=True), X_sel.reset_index(drop=True)], axis=1)
        else:
            return np.hstack((X_not_sel, X_sel))

ColumnOrdinalEncoder

Bases: TransformerMixin, BaseEstimator

Source code in tpot/builtin_modules/column_one_hot_encoder.py 
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
class ColumnOrdinalEncoder(TransformerMixin, BaseEstimator ):


    def __init__(self, columns='auto', handle_unknown='error', unknown_value = -1, encoded_missing_value = np.nan, min_frequency=None,max_categories=None):
        '''

        Parameters
        ----------

        columns : str, list, default='auto'
            Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder.
            - 'auto' : Automatically select categorical features based on columns with less than 10 unique values
            - 'categorical' : Automatically select categorical features
            - 'numeric' : Automatically select numeric features
            - 'all' : Select all features
            - list : A list of columns to select

        drop, handle_unknown, sparse_output, min_frequency, max_categories : see sklearn.preprocessing.OneHotEncoder

        '''

        self.columns = columns
        self.handle_unknown = handle_unknown
        self.unknown_value = unknown_value
        self.encoded_missing_value = encoded_missing_value
        self.min_frequency = min_frequency
        self.max_categories = max_categories



    def fit(self, X, y=None):
        """Fit OneHotEncoder to X, then transform X.

        Equivalent to self.fit(X).transform(X), but more convenient and more
        efficient. See fit for the parameters, transform for the return value.

        Parameters
        ----------
        X : array-like or sparse matrix, shape=(n_samples, n_features)
            Dense array or sparse matrix.
        y: array-like {n_samples,} (Optional, ignored)
            Feature labels
        """

        if (self.columns == "categorical" or self.columns == "numeric") and not isinstance(X, pd.DataFrame):
            raise ValueError(f"Invalid value for columns: {self.columns}. "
                             "Only 'all' or <list> is supported for np arrays")

        if self.columns == "categorical":
            self.columns_ = list(X.select_dtypes(exclude='number').columns)
        elif self.columns == "numeric":
            self.columns_ =  [col for col in X.columns if is_numeric_dtype(X[col])]
        elif self.columns == "auto":
            self.columns_ = auto_select_categorical_features(X)
        elif self.columns == "all":
            if isinstance(X, pd.DataFrame):
                self.columns_ = X.columns
            else:
                self.columns_ = list(range(X.shape[1]))
        elif isinstance(self.columns, list):
            self.columns_ = self.columns
        else:
            raise ValueError(f"Invalid value for columns: {self.columns}")

        if len(self.columns_) == 0:
            return self

        self.enc = sklearn.preprocessing.OrdinalEncoder(categories='auto',   
                                                        handle_unknown = self.handle_unknown,
                                                        unknown_value = self.unknown_value, 
                                                        encoded_missing_value = self.encoded_missing_value,
                                                        min_frequency = self.min_frequency,
                                                        max_categories = self.max_categories)
        #TODO make this more consistent with sklearn baseimputer/baseencoder
        '''
        if isinstance(X, pd.DataFrame):
            self.enc.set_output(transform="pandas")
            for col in X.columns:
                # check if the column name is not a string
                if not isinstance(col, str):
                    # if it's not a string, rename the column with "X" prefix
                    X.rename(columns={col: f"X{col}"}, inplace=True)
        '''

        if len(self.columns_) == X.shape[1]:
            X_sel = self.enc.fit(X)
        else:
            X_sel, X_not_sel = _X_selected(X, self.columns_)
            X_sel = self.enc.fit(X_sel)

        return self

    def transform(self, X):
        """Transform X using one-hot encoding.

        Parameters
        ----------
        X : array-like or sparse matrix, shape=(n_samples, n_features)
            Dense array or sparse matrix.

        Returns
        -------
        X_out : sparse matrix if sparse=True else a 2-d array, dtype=int
            Transformed input.
        """


        if len(self.columns_) == 0:
            return X

        #TODO make this more consistent with sklearn baseimputer/baseencoder
        '''
        if isinstance(X, pd.DataFrame):
            for col in X.columns:
                # check if the column name is not a string
                if not isinstance(col, str):
                    # if it's not a string, rename the column with "X" prefix
                    X.rename(columns={col: f"X{col}"}, inplace=True)
        '''

        if len(self.columns_) == X.shape[1]:
            return self.enc.transform(X)
        else:

            X_sel, X_not_sel= _X_selected(X, self.columns_)
            X_sel = self.enc.transform(X_sel)

            #If X is dataframe
            if isinstance(X, pd.DataFrame):

                X_sel = pd.DataFrame(X_sel, columns=self.enc.get_feature_names_out())
                return pd.concat([X_not_sel.reset_index(drop=True), X_sel.reset_index(drop=True)], axis=1)
            else:
                return np.hstack((X_not_sel, X_sel))

__init__(columns='auto', handle_unknown='error', unknown_value=-1, encoded_missing_value=np.nan, min_frequency=None, max_categories=None)

Parameters:

Name Type Description Default
columns (str, list)

Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder. - 'auto' : Automatically select categorical features based on columns with less than 10 unique values - 'categorical' : Automatically select categorical features - 'numeric' : Automatically select numeric features - 'all' : Select all features - list : A list of columns to select

 'auto'
drop see sklearn.preprocessing.OneHotEncoder
'error'
handle_unknown see sklearn.preprocessing.OneHotEncoder
'error'
sparse_output see sklearn.preprocessing.OneHotEncoder
'error'
min_frequency see sklearn.preprocessing.OneHotEncoder
'error'
max_categories see sklearn.preprocessing.OneHotEncoder
'error'
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
def __init__(self, columns='auto', handle_unknown='error', unknown_value = -1, encoded_missing_value = np.nan, min_frequency=None,max_categories=None):
    '''

    Parameters
    ----------

    columns : str, list, default='auto'
        Determines which columns to onehot encode with sklearn.preprocessing.OneHotEncoder.
        - 'auto' : Automatically select categorical features based on columns with less than 10 unique values
        - 'categorical' : Automatically select categorical features
        - 'numeric' : Automatically select numeric features
        - 'all' : Select all features
        - list : A list of columns to select

    drop, handle_unknown, sparse_output, min_frequency, max_categories : see sklearn.preprocessing.OneHotEncoder

    '''

    self.columns = columns
    self.handle_unknown = handle_unknown
    self.unknown_value = unknown_value
    self.encoded_missing_value = encoded_missing_value
    self.min_frequency = min_frequency
    self.max_categories = max_categories

fit(X, y=None)

Fit OneHotEncoder to X, then transform X.

Equivalent to self.fit(X).transform(X), but more convenient and more efficient. See fit for the parameters, transform for the return value.

Parameters:

Name Type Description Default
X array-like or sparse matrix, shape=(n_samples, n_features)

Dense array or sparse matrix.

 required
y

Feature labels

 None
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
def fit(self, X, y=None):
    """Fit OneHotEncoder to X, then transform X.

    Equivalent to self.fit(X).transform(X), but more convenient and more
    efficient. See fit for the parameters, transform for the return value.

    Parameters
    ----------
    X : array-like or sparse matrix, shape=(n_samples, n_features)
        Dense array or sparse matrix.
    y: array-like {n_samples,} (Optional, ignored)
        Feature labels
    """

    if (self.columns == "categorical" or self.columns == "numeric") and not isinstance(X, pd.DataFrame):
        raise ValueError(f"Invalid value for columns: {self.columns}. "
                         "Only 'all' or <list> is supported for np arrays")

    if self.columns == "categorical":
        self.columns_ = list(X.select_dtypes(exclude='number').columns)
    elif self.columns == "numeric":
        self.columns_ =  [col for col in X.columns if is_numeric_dtype(X[col])]
    elif self.columns == "auto":
        self.columns_ = auto_select_categorical_features(X)
    elif self.columns == "all":
        if isinstance(X, pd.DataFrame):
            self.columns_ = X.columns
        else:
            self.columns_ = list(range(X.shape[1]))
    elif isinstance(self.columns, list):
        self.columns_ = self.columns
    else:
        raise ValueError(f"Invalid value for columns: {self.columns}")

    if len(self.columns_) == 0:
        return self

    self.enc = sklearn.preprocessing.OrdinalEncoder(categories='auto',   
                                                    handle_unknown = self.handle_unknown,
                                                    unknown_value = self.unknown_value, 
                                                    encoded_missing_value = self.encoded_missing_value,
                                                    min_frequency = self.min_frequency,
                                                    max_categories = self.max_categories)
    #TODO make this more consistent with sklearn baseimputer/baseencoder
    '''
    if isinstance(X, pd.DataFrame):
        self.enc.set_output(transform="pandas")
        for col in X.columns:
            # check if the column name is not a string
            if not isinstance(col, str):
                # if it's not a string, rename the column with "X" prefix
                X.rename(columns={col: f"X{col}"}, inplace=True)
    '''

    if len(self.columns_) == X.shape[1]:
        X_sel = self.enc.fit(X)
    else:
        X_sel, X_not_sel = _X_selected(X, self.columns_)
        X_sel = self.enc.fit(X_sel)

    return self

transform(X)

Transform X using one-hot encoding.

Parameters:

Name Type Description Default
X array-like or sparse matrix, shape=(n_samples, n_features)

Dense array or sparse matrix.

 required

Returns:

Name Type Description
X_out sparse matrix if sparse=True else a 2-d array, dtype=int

Transformed input.
Source code in tpot/builtin_modules/column_one_hot_encoder.py 
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
def transform(self, X):
    """Transform X using one-hot encoding.

    Parameters
    ----------
    X : array-like or sparse matrix, shape=(n_samples, n_features)
        Dense array or sparse matrix.

    Returns
    -------
    X_out : sparse matrix if sparse=True else a 2-d array, dtype=int
        Transformed input.
    """


    if len(self.columns_) == 0:
        return X

    #TODO make this more consistent with sklearn baseimputer/baseencoder
    '''
    if isinstance(X, pd.DataFrame):
        for col in X.columns:
            # check if the column name is not a string
            if not isinstance(col, str):
                # if it's not a string, rename the column with "X" prefix
                X.rename(columns={col: f"X{col}"}, inplace=True)
    '''

    if len(self.columns_) == X.shape[1]:
        return self.enc.transform(X)
    else:

        X_sel, X_not_sel= _X_selected(X, self.columns_)
        X_sel = self.enc.transform(X_sel)

        #If X is dataframe
        if isinstance(X, pd.DataFrame):

            X_sel = pd.DataFrame(X_sel, columns=self.enc.get_feature_names_out())
            return pd.concat([X_not_sel.reset_index(drop=True), X_sel.reset_index(drop=True)], axis=1)
        else:
            return np.hstack((X_not_sel, X_sel))