ashok0587

import pandas as pd
from sklearn.feature_extraction import DictVectorizer

def one_hot_dataframe(data, cols, replace=False):
    """ Takes a dataframe and a list of columns that need to be encoded.
        Returns a 3-tuple comprising the data, the vectorized data,
        and the fitted vectorizor."""
    vec = DictVectorizer(sparse=False)
    vecData = pd.DataFrame(vec.fit_transform(data[cols].T.to_dict().values()))
    vecData.columns = vec.get_feature_names()