def build_first_name_data():
print('\n***** Build first names.')
first_name_data = read_csv(FIRST_NAMES_PATHS['csv'],
FIRST_NAMES_PATHS['columns'])
max_length_first_name = get_longest_item(first_name_data)
dump_data_to_pickle(FIRST_NAMES_PATHS['pkl'], first_name_data,
max_length_first_name)
def build_word_data():
print('***** Build words.\n')
words = []
for word in wn.words():
words.append(word)
max_length_word = get_longest_item(words)
dump_data_to_pickle(WORDS_PATHS['pkl'], words, max_length_word)
def build_word_counts():
"""Build word counts."""
print('***** Build word counts.\n')
words = load_pickle(WORDS_PATHS['pkl'])
counts_word = get_counts(words)
counts_word_normalized = normalize_counts(counts_word)
dump_data_to_pickle(WORDS_PATHS['pkl_cnts'], counts_word)
dump_data_to_pickle(WORDS_PATHS['pkl_cnts_norm'], counts_word_normalized)
def build_surname_counts():
"""Build surname counts."""
print('***** Build surname counts.')
surnames = load_pickle(SURNAMES_PATHS['pkl'])
counts_surname = get_counts(surnames)
counts_surname_normalized = normalize_counts(counts_surname)
dump_data_to_pickle(SURNAMES_PATHS['pkl_cnts'], counts_surname)
dump_data_to_pickle(SURNAMES_PATHS['pkl_cnts_norm'], counts_surname_normalized)
def build_first_name_counts():
"""Build first name counts."""
print('\n***** Build first name counts.')
first_names = load_pickle(FIRST_NAMES_PATHS['pkl'])
counts_first = get_counts(first_names)
counts_first_normalized = normalize_counts(counts_first)
dump_data_to_pickle(FIRST_NAMES_PATHS['pkl_cnts'], counts_first)
dump_data_to_pickle(FIRST_NAMES_PATHS['pkl_cnts_norm'], counts_first_normalized)
def build_surname_data():
print('***** Build surnames.')
surname_data = read_csv(SURNAMES_PATHS['csv'], SURNAMES_PATHS['columns'])
max_length_surname = get_longest_item(surname_data)
dump_data_to_pickle(SURNAMES_PATHS['pkl'], surname_data,
max_length_surname)