mohitbadwal

import threading

threads = []


class encodeClass(threading.Thread):
    def __init__(self, threadID, dataset, columns):
        threading.Thread.__init__(self)
        self.threadID = threadID
        self.dataset = dataset

mohitbadwal

def encode(dataset, list_columns_to_encode):
    # using dictionary of dictionary to save the values which will be used later
    dictionary_of_dictionary = {}
    for column in list_columns_to_encode:
        temp_dictionary = {}
        temp = dataset[column].astype('category').value_counts().keys()
        for j in range(0, len(temp)):
            temp_dictionary[j] = temp[j]
            dataset[column].replace(temp[j], j+1, inplace=True)
        dictionary_of_dictionary[column] = temp_dictionary