chariot_demo

chariot_demo1.py

import chariot.transformer as ct
from chariot.preprocessor import Preprocessor


preprocessor = Preprocessor()
preprocessor\
    .stack(ct.text.UnicodeNormalizer())\
    .stack(ct.Tokenizer("en"))\
    .stack(ct.token.StopwordFilter("en"))\
    .stack(ct.Vocabulary(min_df=5, max_df=0.5))\
    .fit(train_data)

preprocessor.save("my_preprocessor.pkl")

loaded = Preprocessor.load("my_preprocessor.pkl")