This commit is contained in:
Mateusz 2024-05-15 20:40:39 +02:00
parent a3db769933
commit bf33351acc
5 changed files with 924 additions and 938 deletions

File diff suppressed because it is too large Load Diff

22
run.py
View File

@ -5,25 +5,9 @@ import numpy as np
def read_data(): def read_data():
train_dataset = pd.read_csv( train_dataset = pd.read_csv("train/train.tsv", sep="\t", names=["Class", "Text"])
"train/train.tsv.gz", dev_0_dataset = pd.read_csv("dev-0/in.tsv", sep="\t", names=["Text"])
sep="\t", test_A_dataset = pd.read_csv("test-A/in.tsv", sep="\t", names=["Text"])
compression="gzip",
names=["Class", "Text"],
on_bad_lines="skip",
)
dev_0_dataset = pd.read_csv(
"dev-0/in.tsv",
sep="\t",
names=["Text"],
on_bad_lines="skip",
)
test_A_dataset = pd.read_csv(
"test-A/in.tsv",
sep="\t",
names=["Text"],
on_bad_lines="skip",
)
return train_dataset, dev_0_dataset, test_A_dataset return train_dataset, dev_0_dataset, test_A_dataset

File diff suppressed because it is too large Load Diff