File size: 6,089 Bytes
cea4a4b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
import os
from dotenv import load_dotenv
import pandas as pd
from sklearn.model_selection import train_test_split
from transformers import BertTokenizerFast, AutoTokenizer
from datasets import Dataset, DatasetDict, load_dataset
from src.utils import (
detect_language,
add_emoji_tokens,
add_new_line_token,
user_id,
)
from src.utils.text_functions import clean_text
from src.utils.s3 import read_csv, save_csv
load_dotenv()
class MLMDataset:
def __init__(
self,
s3: bool = False,
bucket: str = "lebesgue-data-science",
folder: str = os.getenv("GLOBAL_PATH_TO_REPO") + "/data/pretrain",
s3_folder: str = "transformers/data/pretrain",
):
self.s3 = s3
self.bucket = bucket
if self.s3:
self.folder = s3_folder
else:
self.folder = folder
self.primaries_path = f"{self.folder}/primaries.csv"
self.competitors_path = f"{self.folder}/competitor_ads.csv"
self.ad_copies_path = f"{self.folder}/ad_copies.csv"
self.english_copies_path = f"{self.folder}/english_copies.csv"
self.train_path = f"{self.folder}/train.csv"
self.val_path = f"{self.folder}/val.csv"
self.test_path = f"{self.folder}/test.csv"
self.tokenizer_id = f"{user_id}/lebesgue_ad_tokenizer"
self.hub_datasetdict_id = f"{user_id}/lebesgue_ad_datasets"
@property
def primaries(self) -> pd.DataFrame:
df = read_csv(self.primaries_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def competitors(self) -> pd.DataFrame:
df = read_csv(self.competitors_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def ad_copies(self) -> pd.DataFrame:
df = read_csv(self.ad_copies_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def english_copies(self) -> pd.DataFrame:
args = {"lineterminator": "\n"}
df = read_csv(
self.english_copies_path,
s3=self.s3,
s3_args={"bucket": self.bucket} | args,
pd_args=args,
)
return df
@property
def train(self) -> pd.DataFrame:
df = read_csv(self.train_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def val(self) -> pd.DataFrame:
df = read_csv(self.val_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def test(self) -> pd.DataFrame:
df = read_csv(self.test_path, s3=self.s3, s3_args={"bucket": self.bucket})
return df
@property
def datasets(self) -> DatasetDict:
return load_dataset(self.hub_datasetdict_id)
def tokenizer(self, checkpoint: str = "bert-base-uncased") -> AutoTokenizer:
return AutoTokenizer.from_pretrained(f"{self.tokenizer_id}_{checkpoint}")
def concat_and_remove_duplicates(self) -> pd.DataFrame:
comp = self.competitors
prim = self.primaries
primaries = prim.value.to_list()
primaries = [primary for primary in primaries if type(primary) == list]
list_of_primaries = []
for primary in primaries:
list_of_primaries.extend(primary)
competitors = comp.ad_text.to_list()
ad_copies = list_of_primaries + competitors
ad_copies = pd.Series(ad_copies).drop_duplicates()
ad_copies = pd.DataFrame(ad_copies, columns=["text"])
save_csv(
df=ad_copies,
path=self.ad_copies_path,
s3=self.s3,
s3_args={"bucket": self.bucket},
)
def get_language(self) -> pd.DataFrame:
ad_copies = self.ad_copies
ad_copies["language"] = ad_copies.text.apply(lambda text: detect_language(text))
save_csv(
df=ad_copies,
path=self.ad_copies_path,
s3=self.s3,
s3_args={"bucket": self.bucket},
)
return ad_copies
def filter_english(self) -> pd.DataFrame:
ad_copies = self.ad_copies
english = ad_copies[ad_copies.language == "en"]
save_csv(
df=english,
path=self.english_copies_path,
s3=self.s3,
s3_args={"bucket": self.bucket},
)
return english
def clean_english(self) -> pd.DataFrame:
english = self.english_copies
english["text_clean"] = english.text.apply(clean_text)
# remove empty ones
english = english[english.text_clean.apply(len) != 0]
save_csv(
df=english,
path=self.english_copies_path,
s3=self.s3,
s3_args={"bucket": self.bucket},
)
return english
def train_tokenizer(self, checkpoint: str = "bert-base-uncased"):
tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
tokenizer = add_emoji_tokens(tokenizer=tokenizer)
tokenizer = add_new_line_token(tokenizer=tokenizer)
tokenizer.push_to_hub(f"{self.tokenizer_id}_{checkpoint}")
def get_tokenizer(self):
return BertTokenizerFast.from_pretrained(self.tokenizer_id)
def split_into_train_and_test(
self,
) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
df = self.english_copies
train, test = train_test_split(df, train_size=0.9, random_state=42)
train, val = train_test_split(train, train_size=0.85, random_state=42)
dataset_dict = DatasetDict()
for df, local_path, dataset_dict_key in zip(
[train, val, test],
[self.train_path, self.val_path, self.train_path],
["train", "val", "test"],
):
save_csv(df=df, path=local_path, s3=self.s3, s3_args={"bucket": self.bucket})
df_hf = Dataset.from_pandas(df, preserve_index=False)
dataset_dict[dataset_dict_key] = df_hf
dataset_dict.push_to_hub(self.hub_datasetdict_id)
return train, val, test
mlm_dataset = MLMDataset()
mlm_dataset_s3 = MLMDataset(s3=True)
|