File size: 5,646 Bytes
c9036ae b3db2b8 470e696 b3db2b8 24469e0 c9036ae |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# !pip install datasets\n",
"# !huggingface-cli login"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# from datasets import load_dataset\n",
"# load_dataset(\"balochiml/balochi-language-data\", data_dir=\"data\", cache_dir=\"../data\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Generate the processed data without English characters"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4294"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"\n",
"def get_txt_file_paths(directory):\n",
" txt_file_paths = []\n",
" for root, dirs, files in os.walk(directory):\n",
" for file in files:\n",
" if file.endswith(\".txt\"):\n",
" file_path = os.path.join(root, file)\n",
" txt_file_paths.append(file_path)\n",
" return txt_file_paths\n",
"\n",
"# Replace \"directory_path\" with the actual path of the directory you want to search\n",
"directory_path = \"../data/raw_text\"\n",
"txt_paths = get_txt_file_paths(directory_path)\n",
"\n",
"len(txt_paths)\n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"\n",
"def clean_text(file_path):\n",
" # Open the file and read it into memory\n",
" with open(file_path, 'r', encoding='utf-8') as file:\n",
" text = file.read()\n",
"\n",
" # Remove English-language characters and numbers\n",
" text = re.sub(r'[a-zA-Z0-9]', '', text)\n",
"\n",
" # Remove any excess whitespace\n",
" text = re.sub(r'[^\\S\\n]+', ' ', text)\n",
"\n",
" return text"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"for path in txt_paths:\n",
" cleaned_text = clean_text(path)\n",
"\n",
" # write the cleaned text to a new file with an incremented filename\n",
" # write the files all into the '../data/processed_text' directory\n",
" with open(f'../data/processed_text/{path.split(\"/\")[-1]}', 'w', encoding='utf-8') as file:\n",
" file.write(cleaned_text)\n"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"from tokenizers import Tokenizer\n",
"from tokenizers.models import BPE\n",
"\n",
"tokenizer = Tokenizer(BPE(unk_token=\"[UNK]\"))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"from tokenizers.trainers import BpeTrainer\n",
"\n",
"# trainer = BpeTrainer(vocab_size=25000, min_frequency=2)\n",
"trainer = BpeTrainer(\n",
" min_frequency=2,\n",
" vocab_size=100000,\n",
" special_tokens=[\"[UNK]\", \"[CLS]\", \"[SEP]\", \"[PAD]\", \"[MASK]\"],\n",
" show_progress=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4294"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get a list of all the txt files in\n",
"# '/Users/strickvl/balochi/balochi-tokenizer/data/processed_text'\n",
"\n",
"processed_files = get_txt_file_paths(\"../data/processed_text\")\n",
"assert len(processed_files) == len(txt_paths)\n",
"len(processed_files)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\n"
]
}
],
"source": [
"tokenizer.train(processed_files, trainer)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<tokenizers.models.BPE at 0x140d828f0>"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.model"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"100000"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.get_vocab_size()"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"tokenizer.save(\"../models/balochi-tokenizer.json\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "balochi",
"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": "3.10.11"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|