databunch_error.py

import pandas as pd
from pathlib import Path
from fastai.text import TextLMDataBunch as lmdb, load_data
from fastai.text.transform import Tokenizer

def pass_through(x):
    return x

valid_df = pd.read_csv('https://storage.googleapis.com/issue_label_bot/pre_processed_data/processed_part0000.csv')
train_df = valid_df
tokenizer = Tokenizer(pre_rules=[pass_through], n_cpus=30)
path = Path('lang_model_test/')

tst_data_lm = lmdb.from_df(path=path,
                           train_df=train_df,
                           valid_df=valid_df,
                           text_cols='text',
                           tokenizer=tokenizer,
                           chunksize=3000000)

path.mkdir(exist_ok=True)
tst_data_lm.save()

############################################
### PART2: NOW, RESTART KERNEL and TRY THIS
############################################

from fastai.text import TextLMDataBunch as lmdb, load_data
from pathlib import Path

path = Path('lang_model_test/')
tst_data_lm = load_data(path)