Minor fixes

This commit is contained in:
Andras Schmelczer 2022-07-12 19:17:10 +02:00
parent 8c7a31a513
commit b1a66cb579
No known key found for this signature in database
GPG key ID: 0EA1BC97D0AB076E
7 changed files with 30 additions and 13 deletions

View file

@ -92,7 +92,13 @@
"from typing import List, Tuple\n",
"import json\n",
"import gzip\n",
"from great_ai.utilities import simple_parallel_map, clean, is_english, predict_language, unchunk\n",
"from great_ai.utilities import (\n",
" simple_parallel_map,\n",
" clean,\n",
" is_english,\n",
" predict_language,\n",
" unchunk,\n",
")\n",
"\n",
"\n",
"def preprocess_chunk(chunk_key: str) -> List[Tuple[str, List[str]]]:\n",
@ -119,7 +125,9 @@
" ]\n",
"\n",
"\n",
"preprocessed_data = unchunk(simple_parallel_map(preprocess_chunk, chunks, concurrency=4))"
"preprocessed_data = unchunk(\n",
" simple_parallel_map(preprocess_chunk, chunks, concurrency=4)\n",
")"
]
},
{