Skip to content

ExperimentalDiscretizer

Bases: ExperimentalTableTransformer

The Discretizer bins continuous data into intervals.

Parameters:

Name Type Description Default
number_of_bins int

The number of bins to be created.

 5

Raises:

Type Description
OutOfBoundsError

If the given number_of_bins is less than 2.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.py 
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 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
207
208
209
210
211
212
213
214
215
class ExperimentalDiscretizer(ExperimentalTableTransformer):
    """
    The Discretizer bins continuous data into intervals.

    Parameters
    ----------
    number_of_bins:
        The number of bins to be created.

    Raises
    ------
    OutOfBoundsError
        If the given number_of_bins is less than 2.
    """

    def __init__(self, number_of_bins: int = 5):
        self._column_names: list[str] | None = None
        self._wrapped_transformer: sk_KBinsDiscretizer | None = None

        if number_of_bins < 2:
            raise OutOfBoundsError(number_of_bins, name="number_of_bins", lower_bound=ClosedBound(2))
        self._number_of_bins = number_of_bins

    def fit(self, table: ExperimentalTable, column_names: list[str] | None) -> ExperimentalDiscretizer:
        """
        Learn a transformation for a set of columns in a table.

        This transformer is not modified.

        Parameters
        ----------
        table:
            The table used to fit the transformer.
        column_names:
            The list of columns from the table used to fit the transformer. If `None`, all columns are used.

        Returns
        -------
        fitted_transformer:
            The fitted transformer.

        Raises
        ------
        ValueError
            If the table is empty.
        NonNumericColumnError
            If one of the columns, that should be fitted is non-numeric.
        UnknownColumnNameError
            If one of the columns, that should be fitted is not in the table.
        """
        from sklearn.preprocessing import KBinsDiscretizer as sk_KBinsDiscretizer

        if table.number_of_rows == 0:
            raise ValueError("The Discretizer cannot be fitted because the table contains 0 rows")

        if column_names is None:
            column_names = table.column_names
        else:
            missing_columns = set(column_names) - set(table.column_names)
            if len(missing_columns) > 0:
                raise UnknownColumnNameError(
                    sorted(
                        missing_columns,
                        key={val: ix for ix, val in enumerate(column_names)}.__getitem__,
                    ),
                )

            for column in column_names:
                if not table.get_column(column).type.is_numeric:
                    raise NonNumericColumnError(f"{column} is of type {table.get_column(column).type}.")

        wrapped_transformer = sk_KBinsDiscretizer(n_bins=self._number_of_bins, encode="ordinal")
        wrapped_transformer.set_output(transform="polars")
        wrapped_transformer.fit(
            table.remove_columns_except(column_names)._data_frame,
        )

        result = ExperimentalDiscretizer(self._number_of_bins)
        result._wrapped_transformer = wrapped_transformer
        result._column_names = column_names

        return result

    def transform(self, table: ExperimentalTable) -> ExperimentalTable:
        """
        Apply the learned transformation to a table.

        The table is not modified.

        Parameters
        ----------
        table:
            The table to which the learned transformation is applied.

        Returns
        -------
        transformed_table:
            The transformed table.

        Raises
        ------
        TransformerNotFittedError
            If the transformer has not been fitted yet.
        ValueError
            If the table is empty.
        UnknownColumnNameError
            If one of the columns, that should be transformed is not in the table.
        NonNumericColumnError
            If one of the columns, that should be fitted is non-numeric.
        """
        # Transformer has not been fitted yet
        if self._wrapped_transformer is None or self._column_names is None:
            raise TransformerNotFittedError

        if table.number_of_rows == 0:
            raise ValueError("The table cannot be transformed because it contains 0 rows")

        # Input table does not contain all columns used to fit the transformer
        missing_columns = set(self._column_names) - set(table.column_names)
        if len(missing_columns) > 0:
            raise UnknownColumnNameError(
                sorted(
                    missing_columns,
                    key={val: ix for ix, val in enumerate(self._column_names)}.__getitem__,
                ),
            )

        for column in self._column_names:
            if not table.get_column(column).type.is_numeric:
                raise NonNumericColumnError(f"{column} is of type {table.get_column(column).type}.")

        new_data = self._wrapped_transformer.transform(
            table.remove_columns_except(self._column_names)._data_frame,
        )
        return ExperimentalTable._from_polars_lazy_frame(
            table._lazy_frame.update(new_data.lazy()),
        )

    @property
    def is_fitted(self) -> bool:
        """Whether the transformer is fitted."""
        return self._wrapped_transformer is not None

    def get_names_of_added_columns(self) -> list[str]:
        """
        Get the names of all new columns that have been added by the Discretizer.

        Returns
        -------
        added_columns:
            A list of names of the added columns, ordered as they will appear in the table.

        Raises
        ------
        TransformerNotFittedError
            If the transformer has not been fitted yet.
        """
        if not self.is_fitted:
            raise TransformerNotFittedError
        return []

    def get_names_of_changed_columns(self) -> list[str]:
        """
         Get the names of all columns that may have been changed by the Discretizer.

        Returns
        -------
        changed_columns:
             The list of (potentially) changed column names, as passed to fit.

        Raises
        ------
        TransformerNotFittedError
            If the transformer has not been fitted yet.
        """
        if self._column_names is None:
            raise TransformerNotFittedError
        return self._column_names

    def get_names_of_removed_columns(self) -> list[str]:
        """
        Get the names of all columns that have been removed by the Discretizer.

        Returns
        -------
        removed_columns:
            A list of names of the removed columns, ordered as they appear in the table the Discretizer was fitted on.

        Raises
        ------
        TransformerNotFittedError
            If the transformer has not been fitted yet.
        """
        if not self.is_fitted:
            raise TransformerNotFittedError
        return []

is_fitted: bool property

Whether the transformer is fitted.

fit(table, column_names)

Learn a transformation for a set of columns in a table.

This transformer is not modified.

Parameters:

Name Type Description Default
table ExperimentalTable

The table used to fit the transformer.

 required
column_names list[str] | None

The list of columns from the table used to fit the transformer. If None, all columns are used.

 required

Returns:

Name Type Description
fitted_transformer ExperimentalDiscretizer

The fitted transformer.

Raises:

Type Description
ValueError

If the table is empty.
NonNumericColumnError

If one of the columns, that should be fitted is non-numeric.
UnknownColumnNameError

If one of the columns, that should be fitted is not in the table.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.py 
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 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
def fit(self, table: ExperimentalTable, column_names: list[str] | None) -> ExperimentalDiscretizer:
    """
    Learn a transformation for a set of columns in a table.

    This transformer is not modified.

    Parameters
    ----------
    table:
        The table used to fit the transformer.
    column_names:
        The list of columns from the table used to fit the transformer. If `None`, all columns are used.

    Returns
    -------
    fitted_transformer:
        The fitted transformer.

    Raises
    ------
    ValueError
        If the table is empty.
    NonNumericColumnError
        If one of the columns, that should be fitted is non-numeric.
    UnknownColumnNameError
        If one of the columns, that should be fitted is not in the table.
    """
    from sklearn.preprocessing import KBinsDiscretizer as sk_KBinsDiscretizer

    if table.number_of_rows == 0:
        raise ValueError("The Discretizer cannot be fitted because the table contains 0 rows")

    if column_names is None:
        column_names = table.column_names
    else:
        missing_columns = set(column_names) - set(table.column_names)
        if len(missing_columns) > 0:
            raise UnknownColumnNameError(
                sorted(
                    missing_columns,
                    key={val: ix for ix, val in enumerate(column_names)}.__getitem__,
                ),
            )

        for column in column_names:
            if not table.get_column(column).type.is_numeric:
                raise NonNumericColumnError(f"{column} is of type {table.get_column(column).type}.")

    wrapped_transformer = sk_KBinsDiscretizer(n_bins=self._number_of_bins, encode="ordinal")
    wrapped_transformer.set_output(transform="polars")
    wrapped_transformer.fit(
        table.remove_columns_except(column_names)._data_frame,
    )

    result = ExperimentalDiscretizer(self._number_of_bins)
    result._wrapped_transformer = wrapped_transformer
    result._column_names = column_names

    return result

get_names_of_added_columns()

Get the names of all new columns that have been added by the Discretizer.

Returns:

Name Type Description
added_columns list[str]

A list of names of the added columns, ordered as they will appear in the table.

Raises:

Type Description
TransformerNotFittedError

If the transformer has not been fitted yet.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.py 
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
def get_names_of_added_columns(self) -> list[str]:
    """
    Get the names of all new columns that have been added by the Discretizer.

    Returns
    -------
    added_columns:
        A list of names of the added columns, ordered as they will appear in the table.

    Raises
    ------
    TransformerNotFittedError
        If the transformer has not been fitted yet.
    """
    if not self.is_fitted:
        raise TransformerNotFittedError
    return []

get_names_of_changed_columns()

Get the names of all columns that may have been changed by the Discretizer.

Returns:

Name Type Description
changed_columns list[str]

The list of (potentially) changed column names, as passed to fit.

Raises:

Type Description
TransformerNotFittedError

If the transformer has not been fitted yet.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.py 
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
def get_names_of_changed_columns(self) -> list[str]:
    """
     Get the names of all columns that may have been changed by the Discretizer.

    Returns
    -------
    changed_columns:
         The list of (potentially) changed column names, as passed to fit.

    Raises
    ------
    TransformerNotFittedError
        If the transformer has not been fitted yet.
    """
    if self._column_names is None:
        raise TransformerNotFittedError
    return self._column_names

get_names_of_removed_columns()

Get the names of all columns that have been removed by the Discretizer.

Returns:

Name Type Description
removed_columns list[str]

A list of names of the removed columns, ordered as they appear in the table the Discretizer was fitted on.

Raises:

Type Description
TransformerNotFittedError

If the transformer has not been fitted yet.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.py 
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
def get_names_of_removed_columns(self) -> list[str]:
    """
    Get the names of all columns that have been removed by the Discretizer.

    Returns
    -------
    removed_columns:
        A list of names of the removed columns, ordered as they appear in the table the Discretizer was fitted on.

    Raises
    ------
    TransformerNotFittedError
        If the transformer has not been fitted yet.
    """
    if not self.is_fitted:
        raise TransformerNotFittedError
    return []

transform(table)

Apply the learned transformation to a table.

The table is not modified.

Parameters:

Name Type Description Default
table ExperimentalTable

The table to which the learned transformation is applied.

 required

Returns:

Name Type Description
transformed_table ExperimentalTable

The transformed table.

Raises:

Type Description
TransformerNotFittedError

If the transformer has not been fitted yet.
ValueError

If the table is empty.
UnknownColumnNameError

If one of the columns, that should be transformed is not in the table.
NonNumericColumnError

If one of the columns, that should be fitted is non-numeric.
Source code in src/safeds/data/tabular/transformation/_experimental_discretizer.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
def transform(self, table: ExperimentalTable) -> ExperimentalTable:
    """
    Apply the learned transformation to a table.

    The table is not modified.

    Parameters
    ----------
    table:
        The table to which the learned transformation is applied.

    Returns
    -------
    transformed_table:
        The transformed table.

    Raises
    ------
    TransformerNotFittedError
        If the transformer has not been fitted yet.
    ValueError
        If the table is empty.
    UnknownColumnNameError
        If one of the columns, that should be transformed is not in the table.
    NonNumericColumnError
        If one of the columns, that should be fitted is non-numeric.
    """
    # Transformer has not been fitted yet
    if self._wrapped_transformer is None or self._column_names is None:
        raise TransformerNotFittedError

    if table.number_of_rows == 0:
        raise ValueError("The table cannot be transformed because it contains 0 rows")

    # Input table does not contain all columns used to fit the transformer
    missing_columns = set(self._column_names) - set(table.column_names)
    if len(missing_columns) > 0:
        raise UnknownColumnNameError(
            sorted(
                missing_columns,
                key={val: ix for ix, val in enumerate(self._column_names)}.__getitem__,
            ),
        )

    for column in self._column_names:
        if not table.get_column(column).type.is_numeric:
            raise NonNumericColumnError(f"{column} is of type {table.get_column(column).type}.")

    new_data = self._wrapped_transformer.transform(
        table.remove_columns_except(self._column_names)._data_frame,
    )
    return ExperimentalTable._from_polars_lazy_frame(
        table._lazy_frame.update(new_data.lazy()),
    )