{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/codespace/.python/current/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from datasets import load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading data: 100%|██████████| 1.74G/1.74G [00:27<00:00, 62.8MB/s]\n",
"Generating train split: 100%|██████████| 192363/192363 [00:31<00:00, 6170.02 examples/s]\n"
]
}
],
"source": [
"data = load_dataset(\"Mohamed-BC/Articles\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"app.py\tdemo.ipynb recommend.py requirements.txt user.py\n"
]
}
],
"source": [
"!ls"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"!mkdir -p data"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset URL: https://www.kaggle.com/datasets/fabiochiusano/medium-articles\n",
"License(s): CC0-1.0\n",
"Downloading medium-articles.zip to /workspaces/codespaces-blank\n",
" 99%|███████████████████████████████████████▊| 367M/369M [00:14<00:00, 42.9MB/s]\n",
"100%|████████████████████████████████████████| 369M/369M [00:14<00:00, 27.5MB/s]\n"
]
}
],
"source": [
"!kaggle datasets download -d fabiochiusano/medium-articles"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Archive: medium-articles.zip\n",
" inflating: data/medium_articles.csv \n"
]
}
],
"source": [
"!unzip medium-articles.zip -d data\n",
"!rm medium-articles.zip"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cloning into 'articles_embeddings'...\n",
"remote: Enumerating objects: 6, done.\u001b[K\n",
"remote: Counting objects: 100% (3/3), done.\u001b[K\n",
"remote: Compressing objects: 100% (3/3), done.\u001b[K\n",
"remote: Total 6 (delta 0), reused 0 (delta 0), pack-reused 3 (from 1)\u001b[K\n",
"Unpacking objects: 100% (6/6), 2.11 KiB | 1.06 MiB/s, done.\n"
]
}
],
"source": [
"!git clone https://huggingface.co/Mohamed-BC/articles_embeddings "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"!mv articles_embeddings/articles_embeddings.pkl data\n",
"!rm -rf articles_embeddings"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"emb = pd.read_pickle('data/articles_embeddings.pkl')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(192363,)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"emb.shape"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"from recommend import recommend"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/codespace/.python/current/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
" warnings.warn(\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
"\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
"\u001b[1;31mClick here for more info. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"query = \"How to train a model in PyTorch?\"\n",
"recommend(query=\"How to train a model in PyTorch?\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
" _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n",
" _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n",
" _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n",
"\n",
" To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n",
"Enter your token (input will not be visible): Traceback (most recent call last):\n",
" File \"/home/codespace/.python/current/bin/huggingface-cli\", line 8, in \n",
" sys.exit(main())\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/commands/huggingface_cli.py\", line 51, in main\n",
" service.run()\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/commands/user.py\", line 98, in run\n",
" login(token=self.args.token, add_to_git_credential=self.args.add_to_git_credential)\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/_login.py\", line 115, in login\n",
" interpreter_login(new_session=new_session, write_permission=write_permission)\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/_login.py\", line 191, in interpreter_login\n",
" token = getpass(\"Enter your token (input will not be visible): \")\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/getpass.py\", line 77, in unix_getpass\n",
" passwd = _raw_input(prompt, stream, input=input)\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/getpass.py\", line 146, in _raw_input\n",
" line = input.readline()\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/codecs.py\", line 319, in decode\n",
" def decode(self, input, final=False):\n",
"KeyboardInterrupt\n"
]
}
],
"source": [
"!huggingface-cli login"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[90mgit version 2.44.0\u001b[0m\n",
"\u001b[90mgit-lfs/3.5.1 (GitHub; linux amd64; go 1.21.8)\u001b[0m\n",
"\n",
"You are about to create \u001b[1mspaces/Mohamed-BC/articles_recommender_system\u001b[0m\n",
"Proceed? [Y/n] ^C\n",
"Traceback (most recent call last):\n",
" File \"/home/codespace/.python/current/bin/huggingface-cli\", line 8, in \n",
" sys.exit(main())\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/commands/huggingface_cli.py\", line 51, in main\n",
" service.run()\n",
" File \"/usr/local/python/3.10.13/lib/python3.10/site-packages/huggingface_hub/commands/user.py\", line 169, in run\n",
" choice = input(\"Proceed? [Y/n] \").lower()\n",
"KeyboardInterrupt\n"
]
}
],
"source": [
"!huggingface-cli repo create articles_recommender_system --type space"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.\n",
"articles_embeddings.pkl: 0%| | 0.00/666M [00:00