File size: 3,508 Bytes
4c28b8d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
import ast
import logging
import os
import sys
from dataclasses import dataclass, field
import pandas as pd
from tqdm import tqdm
from typing import Dict, List, Optional, Tuple
from datasets import load_dataset
from transformers import (
HfArgumentParser,
)
logger = logging.getLogger(__name__)
@dataclass
class DataArguments:
"""
Arguments to which dataset we are going to set up.
"""
output_dir: str = field(
default=".",
metadata={"help": "The output directory where the config will be written."},
)
dataset_name: str = field(
default=None,
metadata={"help": "The name of the dataset to use (via the datasets library)."}
)
dataset_data_dir: Optional[str] = field(
default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
)
cache_dir: Optional[str] = field(
default=None,
metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
)
def main():
parser = HfArgumentParser([DataArguments])
if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
# If we pass only one argument to the script and it's the path to a json file,
# let's parse it to get our arguments.
data_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))[0]
else:
data_args = parser.parse_args_into_dataclasses()[0]
# Setup logging
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
handlers=[logging.StreamHandler(sys.stdout)],
)
logger.setLevel(logging.INFO)
logger.info(f"Preparing the dataset")
if data_args.dataset_name is not None:
dataset = load_dataset(
data_args.dataset_name,
data_dir=data_args.dataset_data_dir,
cache_dir=data_args.cache_dir
)
else:
dataset = load_dataset(
data_args.dataset_name,
cache_dir=data_args.cache_dir
)
def cleaning(text, item_type="ner"):
# NOTE: DO THE CLEANING LATER
return text
def recipe_preparation(item_dict):
requirements = ["ner", "ingredients", "steps"]
constraints = [3, 3, 10]
if not all([
True if requirements[i] in item_dict and len(item_dict[requirements[i]].split()) > constraints[i] else False
for i in range(len(requirements))
]):
return None
ner = cleaning(item_dict["ner"], "ner")
ingredients = cleaning(item_dict["ingredients"], "ingredients")
steps = cleaning(item_dict["steps"], "steps")
return {
"inputs": ner,
"targets": f"{ingredients}<sep>{steps}"
}
for subset in dataset.keys():
data_dict = []
for item in tqdm(dataset[subset], position=0, total=len(dataset[subset])):
item = recipe_preparation(item)
if item:
data_dict.append(item)
data_df = pd.DataFrame(data_dict)
logger.info(f"Preparation of [{subset}] set consists of {len(data_df)} records!")
output_path = os.path.join(data_args.output_dir, f"{subset}.csv")
os.makedirs(os.path.dirname(output_path), exist_ok=True)
data_df.to_csv(output_path, sep="\t", encoding="utf-8", index=False)
logger.info(f"Data saved here {output_path}")
if __name__ == '__main__':
main()
|