Label encoding across multiple columns in scikit-learn

Question

I\'m trying to use scikit-learn\'s LabelEncoder to encode a pandas DataFrame of string labels. As the dataframe has many (50+) columns, I want to a

Answer 1

This is a year-and-a-half after the fact, but I too, needed to be able to .transform() multiple pandas dataframe columns at once (and be able to .inverse_transform() them as well). This expands upon the excellent suggestion of @PriceHardman above:

class MultiColumnLabelEncoder(LabelEncoder):
    """
    Wraps sklearn LabelEncoder functionality for use on multiple columns of a
    pandas dataframe.

    """
    def __init__(self, columns=None):
        self.columns = columns

    def fit(self, dframe):
        """
        Fit label encoder to pandas columns.

        Access individual column classes via indexig `self.all_classes_`

        Access individual column encoders via indexing
        `self.all_encoders_`
        """
        # if columns are provided, iterate through and get `classes_`
        if self.columns is not None:
            # ndarray to hold LabelEncoder().classes_ for each
            # column; should match the shape of specified `columns`
            self.all_classes_ = np.ndarray(shape=self.columns.shape,
                                           dtype=object)
            self.all_encoders_ = np.ndarray(shape=self.columns.shape,
                                            dtype=object)
            for idx, column in enumerate(self.columns):
                # fit LabelEncoder to get `classes_` for the column
                le = LabelEncoder()
                le.fit(dframe.loc[:, column].values)
                # append the `classes_` to our ndarray container
                self.all_classes_[idx] = (column,
                                          np.array(le.classes_.tolist(),
                                                  dtype=object))
                # append this column's encoder
                self.all_encoders_[idx] = le
        else:
            # no columns specified; assume all are to be encoded
            self.columns = dframe.iloc[:, :].columns
            self.all_classes_ = np.ndarray(shape=self.columns.shape,
                                           dtype=object)
            for idx, column in enumerate(self.columns):
                le = LabelEncoder()
                le.fit(dframe.loc[:, column].values)
                self.all_classes_[idx] = (column,
                                          np.array(le.classes_.tolist(),
                                                  dtype=object))
                self.all_encoders_[idx] = le
        return self

    def fit_transform(self, dframe):
        """
        Fit label encoder and return encoded labels.

        Access individual column classes via indexing
        `self.all_classes_`

        Access individual column encoders via indexing
        `self.all_encoders_`

        Access individual column encoded labels via indexing
        `self.all_labels_`
        """
        # if columns are provided, iterate through and get `classes_`
        if self.columns is not None:
            # ndarray to hold LabelEncoder().classes_ for each
            # column; should match the shape of specified `columns`
            self.all_classes_ = np.ndarray(shape=self.columns.shape,
                                           dtype=object)
            self.all_encoders_ = np.ndarray(shape=self.columns.shape,
                                            dtype=object)
            self.all_labels_ = np.ndarray(shape=self.columns.shape,
                                          dtype=object)
            for idx, column in enumerate(self.columns):
                # instantiate LabelEncoder
                le = LabelEncoder()
                # fit and transform labels in the column
                dframe.loc[:, column] =\
                    le.fit_transform(dframe.loc[:, column].values)
                # append the `classes_` to our ndarray container
                self.all_classes_[idx] = (column,
                                          np.array(le.classes_.tolist(),
                                                  dtype=object))
                self.all_encoders_[idx] = le
                self.all_labels_[idx] = le
        else:
            # no columns specified; assume all are to be encoded
            self.columns = dframe.iloc[:, :].columns
            self.all_classes_ = np.ndarray(shape=self.columns.shape,
                                           dtype=object)
            for idx, column in enumerate(self.columns):
                le = LabelEncoder()
                dframe.loc[:, column] = le.fit_transform(
                        dframe.loc[:, column].values)
                self.all_classes_[idx] = (column,
                                          np.array(le.classes_.tolist(),
                                                  dtype=object))
                self.all_encoders_[idx] = le
        return dframe.loc[:, self.columns].values

    def transform(self, dframe):
        """
        Transform labels to normalized encoding.
        """
        if self.columns is not None:
            for idx, column in enumerate(self.columns):
                dframe.loc[:, column] = self.all_encoders_[
                    idx].transform(dframe.loc[:, column].values)
        else:
            self.columns = dframe.iloc[:, :].columns
            for idx, column in enumerate(self.columns):
                dframe.loc[:, column] = self.all_encoders_[idx]\
                    .transform(dframe.loc[:, column].values)
        return dframe.loc[:, self.columns].values

    def inverse_transform(self, dframe):
        """
        Transform labels back to original encoding.
        """
        if self.columns is not None:
            for idx, column in enumerate(self.columns):
                dframe.loc[:, column] = self.all_encoders_[idx]\
                    .inverse_transform(dframe.loc[:, column].values)
        else:
            self.columns = dframe.iloc[:, :].columns
            for idx, column in enumerate(self.columns):
                dframe.loc[:, column] = self.all_encoders_[idx]\
                    .inverse_transform(dframe.loc[:, column].values)
        return dframe.loc[:, self.columns].values

Example:

If df and df_copy() are mixed-type pandas dataframes, you can apply the MultiColumnLabelEncoder() to the dtype=object columns in the following way:

# get `object` columns
df_object_columns = df.iloc[:, :].select_dtypes(include=['object']).columns
df_copy_object_columns = df_copy.iloc[:, :].select_dtypes(include=['object']).columns

# instantiate `MultiColumnLabelEncoder`
mcle = MultiColumnLabelEncoder(columns=object_columns)

# fit to `df` data
mcle.fit(df)

# transform the `df` data
mcle.transform(df)

# returns output like below
array([[1, 0, 0, ..., 1, 1, 0],
       [0, 5, 1, ..., 1, 1, 2],
       [1, 1, 1, ..., 1, 1, 2],
       ..., 
       [3, 5, 1, ..., 1, 1, 2],

# transform `df_copy` data
mcle.transform(df_copy)

# returns output like below (assuming the respective columns 
# of `df_copy` contain the same unique values as that particular 
# column in `df`
array([[1, 0, 0, ..., 1, 1, 0],
       [0, 5, 1, ..., 1, 1, 2],
       [1, 1, 1, ..., 1, 1, 2],
       ..., 
       [3, 5, 1, ..., 1, 1, 2],

# inverse `df` data
mcle.inverse_transform(df)

# outputs data like below
array([['August', 'Friday', '2013', ..., 'N', 'N', 'CA'],
       ['April', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['August', 'Monday', '2014', ..., 'N', 'N', 'NJ'],
       ..., 
       ['February', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['April', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['March', 'Tuesday', '2013', ..., 'N', 'N', 'NJ']], dtype=object)

# inverse `df_copy` data
mcle.inverse_transform(df_copy)

# outputs data like below
array([['August', 'Friday', '2013', ..., 'N', 'N', 'CA'],
       ['April', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['August', 'Monday', '2014', ..., 'N', 'N', 'NJ'],
       ..., 
       ['February', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['April', 'Tuesday', '2014', ..., 'N', 'N', 'NJ'],
       ['March', 'Tuesday', '2013', ..., 'N', 'N', 'NJ']], dtype=object)

You can access individual column classes, column labels, and column encoders used to fit each column via indexing:

mcle.all_classes_
mcle.all_encoders_
mcle.all_labels_

Answer 2

import pandas as pd
from sklearn.preprocessing import LabelEncoder

train=pd.read_csv('.../train.csv')

#X=train.loc[:,['waterpoint_type_group','status','waterpoint_type','source_class']].values
# Create a label encoder object 
def MultiLabelEncoder(columnlist,dataframe):
    for i in columnlist:

        labelencoder_X=LabelEncoder()
        dataframe[i]=labelencoder_X.fit_transform(dataframe[i])
columnlist=['waterpoint_type_group','status','waterpoint_type','source_class','source_type']
MultiLabelEncoder(columnlist,train)

Here i am reading a csv from location and in function i am passing the column list i want to labelencode and the dataframe I want to apply this.

Answer 3

After lots of search and experimentation with some answers here and elsewhere, I think your answer is here:

pd.DataFrame(columns=df.columns, data=LabelEncoder().fit_transform(df.values.flatten()).reshape(df.shape))

This will preserve category names across columns:

import pandas as pd
from sklearn.preprocessing import LabelEncoder

df = pd.DataFrame([['A','B','C','D','E','F','G','I','K','H'],
                   ['A','E','H','F','G','I','K','','',''],
                   ['A','C','I','F','H','G','','','','']], 
                  columns=['A1', 'A2', 'A3','A4', 'A5', 'A6', 'A7', 'A8', 'A9', 'A10'])

pd.DataFrame(columns=df.columns, data=LabelEncoder().fit_transform(df.values.flatten()).reshape(df.shape))

    A1  A2  A3  A4  A5  A6  A7  A8  A9  A10
0   1   2   3   4   5   6   7   9   10  8
1   1   5   8   6   7   9   10  0   0   0
2   1   3   9   6   8   7   0   0   0   0

Answer 4

Following up on the comments raised on the solution of @PriceHardman I would propose the following version of the class:

class LabelEncodingColoumns(BaseEstimator, TransformerMixin):
def __init__(self, cols=None):
    pdu._is_cols_input_valid(cols)
    self.cols = cols
    self.les = {col: LabelEncoder() for col in cols}
    self._is_fitted = False

def transform(self, df, **transform_params):
    """
    Scaling ``cols`` of ``df`` using the fitting

    Parameters
    ----------
    df : DataFrame
        DataFrame to be preprocessed
    """
    if not self._is_fitted:
        raise NotFittedError("Fitting was not preformed")
    pdu._is_cols_subset_of_df_cols(self.cols, df)

    df = df.copy()

    label_enc_dict = {}
    for col in self.cols:
        label_enc_dict[col] = self.les[col].transform(df[col])

    labelenc_cols = pd.DataFrame(label_enc_dict,
        # The index of the resulting DataFrame should be assigned and
        # equal to the one of the original DataFrame. Otherwise, upon
        # concatenation NaNs will be introduced.
        index=df.index
    )

    for col in self.cols:
        df[col] = labelenc_cols[col]
    return df

def fit(self, df, y=None, **fit_params):
    """
    Fitting the preprocessing

    Parameters
    ----------
    df : DataFrame
        Data to use for fitting.
        In many cases, should be ``X_train``.
    """
    pdu._is_cols_subset_of_df_cols(self.cols, df)
    for col in self.cols:
        self.les[col].fit(df[col])
    self._is_fitted = True
    return self

This class fits the encoder on the training set and uses the fitted version when transforming. Initial version of the code can be found here.