from fastai.gen_doc.nbdoc import *
from fastai.text import * 
from fastai.text.interpret import *

from fastai.gen_doc.nbdoc import *
from fastai.vision import *

show_doc(TextClassificationInterpretation)

show_doc(TextClassificationInterpretation.intrinsic_attention)

show_doc(TextClassificationInterpretation.html_intrinsic_attention)

show_doc(TextClassificationInterpretation.show_intrinsic_attention)

show_doc(TextClassificationInterpretation.show_top_losses)

imdb = untar_data(URLs.IMDB_SAMPLE)

data_lm = (TextList.from_csv(imdb, 'texts.csv', cols='text')
                   .split_by_rand_pct()
                   .label_for_lm()
                   .databunch())
data_lm.save()

data_lm.show_batch()

learn = language_model_learner(data_lm, AWD_LSTM)
learn.fit_one_cycle(2, 1e-2)
learn.save('mini_train_lm')
learn.save_encoder('mini_train_encoder')

data_clas = (TextList.from_csv(imdb, 'texts.csv', cols='text', vocab=data_lm.vocab)
                   .split_from_df(col='is_valid')
                   .label_from_df(cols='label')
                   .databunch(bs=42))

learn = text_classifier_learner(data_clas, AWD_LSTM)
learn.load_encoder('mini_train_encoder')
learn.fit_one_cycle(2, slice(1e-3,1e-2))
learn.save('mini_train_clas')

interp = TextClassificationInterpretation.from_learner(learn) 

interp.show_intrinsic_attention("I really like this movie, it is amazing!")