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

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",