yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-31 20:08:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix data download if UCI is temporarily down (#592)

Browse Source
This commit is contained in:
Sebastian Raschka 2025-03-31 16:25:53 -05:00 committed by GitHub
parent 0bdcce4e40
commit d75f74bd0c
1 changed files with 8 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
ch06/01_main-chapter-code/gpt_class_finetune.py
View File

@ -21,34 +21,15 @@ from gpt_download import download_and_load_gpt2
from previous_chapters import GPTModel, load_weights_into_gpt from previous_chapters import GPTModel, load_weights_into_gpt
def download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path, test_mode=False): def download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path):
if data_file_path.exists(): if data_file_path.exists():
print(f"{data_file_path} already exists. Skipping download and extraction.") print(f"{data_file_path} already exists. Skipping download and extraction.")
return return
if test_mode: # Try multiple times since CI sometimes has connectivity issues # Downloading the file
max_retries = 5 with urllib.request.urlopen(url) as response:
delay = 5 # delay between retries in seconds with open(zip_path, "wb") as out_file:
for attempt in range(max_retries): out_file.write(response.read())
try:
# Downloading the file
with urllib.request.urlopen(url, timeout=10) as response:
with open(zip_path, "wb") as out_file:
out_file.write(response.read())
break # if download is successful, break out of the loop
except urllib.error.URLError as e:
print(f"Attempt {attempt + 1} failed: {e}")
if attempt < max_retries - 1:
time.sleep(delay) # wait before retrying
else:
print("Failed to download file after several attempts.")
return # exit if all retries fail
else: # Code as it appears in the chapter
# Downloading the file
with urllib.request.urlopen(url) as response:
with open(zip_path, "wb") as out_file:
out_file.write(response.read())
# Unzipping the file # Unzipping the file
with zipfile.ZipFile(zip_path, "r") as zip_ref: with zipfile.ZipFile(zip_path, "r") as zip_ref:
@ -277,15 +258,11 @@ if __name__ == "__main__":
data_file_path = Path(extracted_path) / "SMSSpamCollection.tsv" data_file_path = Path(extracted_path) / "SMSSpamCollection.tsv"
try: try:
download_and_unzip_spam_data( download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)
url, zip_path, extracted_path, data_file_path, test_mode=args.test_mode
)
except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e: except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:
print(f"Primary URL failed: {e}. Trying backup URL...") print(f"Primary URL failed: {e}. Trying backup URL...")
backup_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip" url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
download_and_unzip_spam_data( download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)
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"]) df = pd.read_csv(data_file_path, sep="\t", header=None, names=["Label", "Text"])
balanced_df = create_balanced_dataset(df) balanced_df = create_balanced_dataset(df)