yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-30 19:41:51 +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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
appendix-E/01_main-chapter-code/appendix-E.ipynb
View File

@ -48,12 +48,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"matplotlib version: 3.7.2\n",
"numpy version: 1.25.2\n",
"tiktoken version: 0.5.1\n",
"torch version: 2.2.2\n",
"tensorflow version: 2.15.0\n",
"pandas version: 2.0.3\n"
"matplotlib version: 3.10.0\n",
"numpy version: 2.0.2\n",
"tiktoken version: 0.9.0\n",
"torch version: 2.6.0\n",
"tensorflow version: 2.18.0\n",
"pandas version: 2.2.3\n"
]
}
],
@ -190,6 +190,7 @@
}
],
"source": [
"import urllib\n",
"from pathlib import Path\n",
"import pandas as pd\n",
"from previous_chapters import (\n",
@ -204,7 +205,13 @@
"extracted_path = \"sms_spam_collection\"\n",
"data_file_path = Path(extracted_path) / \"SMSSpamCollection.tsv\"\n",
"\n",
"download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"try:\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"except urllib.error.HTTPError:\n",
" print(\"UCI Machine Learning Repository (https://archive.ics.uci.edu)\"\n",
" \" temporary unavailable. Using backup URL.\")\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",
"\n",
"df = pd.read_csv(data_file_path, sep=\"\\t\", header=None, names=[\"Label\", \"Text\"])\n",
"balanced_df = create_balanced_dataset(df)\n",

14
ch06/01_main-chapter-code/ch06.ipynb
View File

@ -50,7 +50,7 @@
"text": [
"matplotlib version: 3.10.0\n",
"numpy version: 2.0.2\n",
"tiktoken version: 0.8.0\n",
"tiktoken version: 0.9.0\n",
"torch version: 2.6.0\n",
"tensorflow version: 2.18.0\n",
"pandas version: 2.2.3\n"
@ -167,7 +167,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"id": "def7c09b-af9c-4216-90ce-5e67aed1065c",
"metadata": {
"colab": {
@ -181,7 +181,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"sms_spam_collection/SMSSpamCollection.tsv already exists. Skipping download and extraction.\n"
"File downloaded and saved as sms_spam_collection/SMSSpamCollection.tsv\n"
]
}
],
@ -215,7 +215,13 @@
" os.rename(original_file_path, data_file_path)\n",
" print(f\"File downloaded and saved as {data_file_path}\")\n",
"\n",
"download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)"
"try:\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"except urllib.error.HTTPError:\n",
" print(\"UCI Machine Learning Repository (https://archive.ics.uci.edu)\"\n",
" \" temporary unavailable. Using backup URL.\")\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) "
]
},
{

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})

6
ch06/02_bonus_additional-experiments/additional_experiments.py
View File

@ -603,7 +603,11 @@ if __name__ == "__main__":
all_exist = all((base_path / file_name).exists() for file_name in file_names)
if not all_exist:
download_and_unzip(url, zip_path, extract_to, new_file_path)
try:
download_and_unzip(url, zip_path, extract_to, new_file_path)
except urllib.error.HTTPError:
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)
create_dataset_csvs(new_file_path)
tokenizer = tiktoken.get_encoding("gpt2")

6
ch06/03_bonus_imdb-classification/train_bert_hf_spam.py
View File

@ -410,7 +410,11 @@ if __name__ == "__main__":
all_exist = all((base_path / file_name).exists() for file_name in file_names)
if not all_exist:
download_and_unzip(url, zip_path, extract_to, new_file_path)
try:
download_and_unzip(url, zip_path, extract_to, new_file_path)
except urllib.error.HTTPError:
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)
create_dataset_csvs(new_file_path)
if args.use_attention_mask.lower() == "true":