File size: 4,340 Bytes
c92ce97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
import ast
import logging
import os
import sys
from dataclasses import dataclass, field
import pandas as pd
from sklearn.model_selection import train_test_split
from tqdm import tqdm
from typing import Dict, List, Optional, Tuple
from datasets import load_dataset
from transformers import (
    HfArgumentParser,
)
from data_utils import (
    filter_by_lang_regex,
    filter_by_num_tokens,
    filter_by_num_sents,
    filter_by_adv,
    normalizer
)


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_config_name: Optional[str] = field(
        default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
    )
    train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
    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_args.dataset_config_name,
            cache_dir=data_args.cache_dir,
            split="train"
        )
    else:
        data_files = {"train": data_args.train_file}
        extension = data_args.train_file.split(".")[-1]
        if extension == "txt":
            extension = "text"

        dataset = load_dataset(
            extension,
            data_files=data_files,
            delimiter="\t",
            cache_dir=data_args.cache_dir,
        )
    
    logger.info(f"dataset: {dataset}")

    def data_preparation(item_dict):
        if "text" not in item_dict:
            return None

        text = item_dict["text"]

        status = filter_by_lang_regex(text, ratio=0.75)
        if not status:
            return None

        status = filter_by_num_tokens(text, gt=64)
        if not status:
            return None
        
        status = filter_by_num_sents(text, gt=2)
        if not status:
            return None
        
        status = filter_by_adv(text, ratio=50)
        if not status:
            return None

        text = normalizer(text)
        return {"text": text}

    data_dict = []
    for item in tqdm(dataset, position=0, total=len(dataset)):
        item = data_preparation(item)

        if item:
            data_dict.append(item)

    data_df = pd.DataFrame(data_dict)

    logger.info(f"Preparation - [before] consists of {len(dataset)} records!")
    logger.info(f"Preparation - [after]  consists of {len(data_df)} records!")

    train, test = train_test_split(data_df, test_size=0.01, random_state=101)

    train = train.reset_index(drop=True)
    test = test.reset_index(drop=True)

    logger.info(f"Preparation of [train] set consists of {len(train)} records!")
    logger.info(f"Preparation of [test] set consists of {len(test)} records!")

    os.makedirs(data_args.output_dir, exist_ok=True)
    train.to_csv(os.path.join(data_args.output_dir, "train.csv"), sep="\t", encoding="utf-8", index=False)
    test.to_csv(os.path.join(data_args.output_dir, "test.csv"), sep="\t", encoding="utf-8", index=False)
    logger.info(f"Data saved here {data_args.output_dir}")

if __name__ == '__main__':
    main()