Add backup url for Spam Dataset (#543)

* Add backup url for Spam Dataset

* import urllib

* fix url

appendix-E/01_main-chapter-code/appendix-E.ipynb

@@ -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",

ch06/01_main-chapter-code/ch06.ipynb

@@ -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) "
    ]
   },
   {

ch06/01_main-chapter-code/gpt_class_finetune.py

@@ -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})

ch06/02_bonus_additional-experiments/additional_experiments.py

@@ -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")

ch06/03_bonus_imdb-classification/train_bert_hf_spam.py

@@ -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":