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

show_doc(TextLMDataBunch, title_level=3, doc_string=False)

show_doc(TextLMDataBunch.show_batch)

show_doc(TextClasDataBunch, title_level=3, doc_string=False)

show_doc(TextClasDataBunch.show_batch)

show_doc(TextDataBunch, title_level=3, doc_string=False)

show_doc(TextDataBunch.from_folder, doc_string=False)

show_doc(TextDataBunch.from_csv, doc_string=False)

show_doc(TextDataBunch.from_df, doc_string=False)

show_doc(TextDataBunch.from_tokens, doc_string=False)

show_doc(TextDataBunch.from_ids, doc_string=False)

show_doc(TextDataBunch.load)

show_doc(TextDataBunch.save)

path = untar_data(URLs.IMDB_SAMPLE)
path

pd.read_csv(path/'texts.csv').head()

data_lm = TextLMDataBunch.from_csv(Path(path), 'texts.csv')
data_clas = TextClasDataBunch.from_csv(Path(path), 'texts.csv')

show_doc(Text, doc_string=False, title_level=3)

show_doc(Text.show_xys)

show_doc(Text.show_xyzs)

show_doc(TextList, title_level=3)

show_doc(TextList.label_for_lm)

show_doc(TextList.from_folder)

show_doc(OpenFileProcessor, title_level=3)

show_doc(open_text)

show_doc(TokenizeProcessor, title_level=3)

show_doc(NumericalizeProcessor, title_level=3, doc_string=False)

path = untar_data(URLs.IMDB_SAMPLE)
data = TextLMDataBunch.from_csv(path, 'texts.csv')
x,y = next(iter(data.train_dl))
example = x[:20,:10].cpu()
texts = pd.DataFrame([data.train_ds.vocab.textify(l).split(' ') for l in example])
texts

iter_dl = iter(data.train_dl)
for _ in range(5):
    x,y = next(iter_dl)
    print(x.size())

show_doc(LanguageModelLoader, doc_string=False)

show_doc(LanguageModelLoader.batchify, doc_string=False)

show_doc(LanguageModelLoader.get_batch)

path = untar_data(URLs.IMDB_SAMPLE)
data = TextClasDataBunch.from_csv(path, 'texts.csv')
iter_dl = iter(data.train_dl)
_ = next(iter_dl)
x,y = next(iter_dl)
x[:20,-10:]

show_doc(SortSampler, doc_string=False)

show_doc(SortishSampler, doc_string=False)

show_doc(pad_collate, doc_string=False)

show_doc(TextLMDataBunch.create)

show_doc(TextClasDataBunch.create)

show_doc(TextList.new)

show_doc(TextList.get)

show_doc(TokenizeProcessor.process_one)

show_doc(TokenizeProcessor.process)

show_doc(OpenFileProcessor.process_one)

show_doc(NumericalizeProcessor.process)

show_doc(NumericalizeProcessor.process_one)

show_doc(Text)

show_doc(TextList.from_folder)