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


show_doc(Tokenizer)

show_doc(Tokenizer.process_text)

show_doc(Tokenizer.process_all)

path = untar_data(URLs.IMDB_SAMPLE)
path

df = pd.read_csv(path/'texts.csv', header=None)
example_text = df.iloc[2][1]; example_text

tokenizer = Tokenizer()
tok = SpacyTokenizer('en')
' '.join(tokenizer.process_text(example_text, tok))

df = pd.read_csv(path/'texts.csv', header=None)
texts = df[1].values
tokenizer = Tokenizer()
tokens = tokenizer.process_all(texts)
' '.join(tokens[2])

show_doc(BaseTokenizer)

show_doc(BaseTokenizer.tokenizer)

show_doc(BaseTokenizer.add_special_cases)

show_doc(SpacyTokenizer)

show_doc(deal_caps, doc_string=False)

show_doc(fix_html, doc_string=False)

fix_html("Some HTML&nbsp;text<br />")

show_doc(replace_all_caps)

show_doc(replace_rep, doc_string=False)

replace_rep("I'm so excited!!!!!!!!")

show_doc(replace_wrep, doc_string=False)

replace_wrep("I've never ever ever ever ever ever ever ever done this.")

show_doc(rm_useless_spaces)

rm_useless_spaces("Inconsistent   use  of     spaces.")

show_doc(spec_add_spaces)

spec_add_spaces('I #like to #put #hashtags #everywhere!')

show_doc(Vocab)

show_doc(Vocab.create)

show_doc(Vocab.numericalize)

show_doc(Vocab.textify)

vocab = Vocab.create(tokens, max_vocab=1000, min_freq=2)
vocab.numericalize(tokens[2])[:10]

show_doc(SpacyTokenizer.tokenizer)

show_doc(SpacyTokenizer.add_special_cases)