books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add backup url for Spam Dataset (#543)

Browse Source 
* Add backup url for Spam Dataset

* import urllib

* fix url
This commit is contained in:
Sebastian Raschka
2025-02-20 08:08:28 -06:00
committed by GitHub
parent 2254102270
commit eb6787397c
5 changed files with 44 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ch06/01_main-chapter-code/gpt_class_finetune.py
View File

@@ -276,7 +276,16 @@ if __name__ == "__main__":
extracted_path = "sms_spam_collection"
data_file_path = Path(extracted_path) / "SMSSpamCollection.tsv"
download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode)
try:
download_and_unzip_spam_data(
url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode
)
except urllib.error.HTTPError:
backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
download_and_unzip_spam_data(
backup_url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode
)
df = pd.read_csv(data_file_path, sep="\t", header=None, names=["Label", "Text"])
balanced_df = create_balanced_dataset(df)
balanced_df["Label"] = balanced_df["Label"].map({"ham": 0, "spam": 1})