File size: 2,638 Bytes
097ab1f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import selfies as sf\n",
"from tokenizers import Tokenizer\n",
"from tokenizers.models import WordLevel\n",
"from tokenizers.pre_tokenizers import Split\n",
"from tokenizers.processors import TemplateProcessing\n",
"from tokenizers.trainers import WordLevelTrainer\n",
"from tqdm import tqdm"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open(\"./train.txt\") as f:\n",
" smiles = [line.strip() for line in f]\n",
"\n",
"selfies = []\n",
"for smile in tqdm(smiles):\n",
" try:\n",
" selfies.append(sf.encoder(smile))\n",
" except:\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = Tokenizer(WordLevel(unk_token=\"<UNK>\"))\n",
"\n",
"tokenizer.pre_tokenizer = Split(\n",
" pattern=\"]\", \n",
" behavior=\"merged_with_previous\"\n",
")\n",
"\n",
"trainer = WordLevelTrainer(\n",
" special_tokens=[\"<CLS>\", \"<EOS>\", \"<PAD>\", \"<UNK>\"]\n",
")\n",
"\n",
"tokenizer.train_from_iterator(selfies, trainer=trainer)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tokenizer.post_processor = TemplateProcessing(\n",
" single=\"<CLS> $A <EOS>\",\n",
" special_tokens=[\n",
" (\"<CLS>\", tokenizer.token_to_id(\"<CLS>\")),\n",
" (\"<EOS>\", tokenizer.token_to_id(\"<EOS>\")),\n",
" ],\n",
")\n",
"\n",
"tokenizer.enable_padding(\n",
" direction=\"right\",\n",
" pad_id=tokenizer.token_to_id(\"<PAD>\"),\n",
" pad_token=\"<PAD>\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tokenizer.save(\"./tokenizer.json\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "ddpm",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|