Skip to content

Imputer

Copyright (c) 2015 The auto-sklearn developers. All rights reserved.

Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:

a. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. b. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution. c. Neither the name of the auto-sklearn Developers nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

ColumnSimpleImputer

Bases: BaseEstimator, TransformerMixin

Source code in tpot2/builtin_modules/imputer.py 
 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
class ColumnSimpleImputer(BaseEstimator, TransformerMixin):
    def __init__(self,  columns="all",         
                        missing_values=np.nan,
                        strategy="mean",
                        fill_value=None,
                        copy=True,
                        add_indicator=False,
                        keep_empty_features=False,):

        self.columns = columns
        self.missing_values = missing_values
        self.strategy = strategy
        self.fill_value = fill_value
        self.copy = copy
        self.add_indicator = add_indicator
        self.keep_empty_features = keep_empty_features


    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 == "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.imputer = sklearn.impute.SimpleImputer(missing_values=self.missing_values,
                                                    strategy=self.strategy,
                                                    fill_value=self.fill_value,
                                                    copy=self.copy,
                                                    add_indicator=self.add_indicator,
                                                    keep_empty_features=self.keep_empty_features)

        if isinstance(X, pd.DataFrame):
            self.imputer.set_output(transform="pandas")

        if isinstance(X, pd.DataFrame):
            self.imputer.fit(X[self.columns_], y)
        else:
            self.imputer.fit(X[:, self.columns_], y)

        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

        if isinstance(X, pd.DataFrame):
            X = X.copy()
            X[self.columns_] = self.imputer.transform(X[self.columns_])
            return X
        else:
            X = np.copy(X)
            X[:, self.columns_] = self.imputer.transform(X[:, self.columns_])
            return X

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 tpot2/builtin_modules/imputer.py 
 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
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 == "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.imputer = sklearn.impute.SimpleImputer(missing_values=self.missing_values,
                                                strategy=self.strategy,
                                                fill_value=self.fill_value,
                                                copy=self.copy,
                                                add_indicator=self.add_indicator,
                                                keep_empty_features=self.keep_empty_features)

    if isinstance(X, pd.DataFrame):
        self.imputer.set_output(transform="pandas")

    if isinstance(X, pd.DataFrame):
        self.imputer.fit(X[self.columns_], y)
    else:
        self.imputer.fit(X[:, self.columns_], y)

    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 tpot2/builtin_modules/imputer.py 
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
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

    if isinstance(X, pd.DataFrame):
        X = X.copy()
        X[self.columns_] = self.imputer.transform(X[self.columns_])
        return X
    else:
        X = np.copy(X)
        X[:, self.columns_] = self.imputer.transform(X[:, self.columns_])
        return X