Converts data with categorical values as string into the right format for LIME, with categorical values as integers labels.

Convert to LIME format.py

import pandas as pd


def convert_to_lime_format(X, categorical_names, col_names=None, invert=False):
    """Converts data with categorical values as string into the right format 
    for LIME, with categorical values as integers labels.

    It takes categorical_names, the same dictionary that has to be passed
    to LIME to ensure consistency. 

    col_names and invert allow to rebuild the original dataFrame from
    a numpy array in LIME format to be passed to a Pipeline or sklearn
    OneHotEncoder
    """

    # If the data isn't a dataframe, we need to be able to build it
    if not isinstance(X, pd.DataFrame):
        X_lime = pd.DataFrame(X, columns=col_names)
    else:
        X_lime = X.copy()

    for k, v in categorical_names.items():
        if not invert:
            label_map = {
                str_label: int_label for int_label, str_label in enumerate(v)
            }
        else:
            label_map = {
                int_label: str_label for int_label, str_label in enumerate(v)
            }

        X_lime.iloc[:, k] = X_lime.iloc[:, k].map(label_map)

    return X_lime