yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-10-12 08:29:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix timeout issue related to spam data backup url (#544)

Browse Source 
* Add backup url for Spam Dataset

* import urllib

* fix url

* fix timeout issue
This commit is contained in:
Sebastian Raschka 2025-02-20 09:26:23 -06:00 committed by GitHub
parent c39aa32ef5
commit d1e99f6092
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
appendix-E/01_main-chapter-code/appendix-E.ipynb
View File

@ -207,9 +207,8 @@
"\n", "\n",
"try:\n", "try:\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n", " download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"except urllib.error.HTTPError:\n", "except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:\n",
" print(\"UCI Machine Learning Repository (https://archive.ics.uci.edu)\"\n", " print(f\"Primary URL failed: {e}. Trying backup URL...\")\n",
" \" temporary unavailable. Using backup URL.\")\n",
" url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n", " url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n", " download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"\n", "\n",

5
ch06/01_main-chapter-code/ch06.ipynb
View File

@ -217,9 +217,8 @@
"\n", "\n",
"try:\n", "try:\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n", " download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"except urllib.error.HTTPError:\n", "except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:\n",
" print(\"UCI Machine Learning Repository (https://archive.ics.uci.edu)\"\n", " print(f\"Primary URL failed: {e}. Trying backup URL...\")\n",
" \" temporary unavailable. Using backup URL.\")\n",
" url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n", " url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path) " " download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path) "
] ]

3
ch06/01_main-chapter-code/gpt_class_finetune.py
View File

@ -280,7 +280,8 @@ if __name__ == "__main__":
download_and_unzip_spam_data( download_and_unzip_spam_data(
url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode
) )
except urllib.error.HTTPError: except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:
print(f"Primary URL failed: {e}. Trying backup URL...")
backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip" backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
download_and_unzip_spam_data( download_and_unzip_spam_data(
backup_url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode backup_url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode

3
ch06/02_bonus_additional-experiments/additional_experiments.py
View File

@ -605,7 +605,8 @@ if __name__ == "__main__":
if not all_exist: if not all_exist:
try: try:
download_and_unzip(url, zip_path, extract_to, new_file_path) download_and_unzip(url, zip_path, extract_to, new_file_path)
except urllib.error.HTTPError: except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:
print(f"Primary URL failed: {e}. Trying backup URL...")
backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip" backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
download_and_unzip(backup_url, zip_path, extract_to, new_file_path) download_and_unzip(backup_url, zip_path, extract_to, new_file_path)
create_dataset_csvs(new_file_path) create_dataset_csvs(new_file_path)

3
ch06/03_bonus_imdb-classification/train_bert_hf_spam.py
View File

@ -412,7 +412,8 @@ if __name__ == "__main__":
if not all_exist: if not all_exist:
try: try:
download_and_unzip(url, zip_path, extract_to, new_file_path) download_and_unzip(url, zip_path, extract_to, new_file_path)
except urllib.error.HTTPError: except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:
print(f"Primary URL failed: {e}. Trying backup URL...")
backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip" backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
download_and_unzip(backup_url, zip_path, extract_to, new_file_path) download_and_unzip(backup_url, zip_path, extract_to, new_file_path)
create_dataset_csvs(new_file_path) create_dataset_csvs(new_file_path)