File size: 11,230 Bytes
c710b24 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"execution": {
"iopub.execute_input": "2025-04-09T09:04:50.582374Z",
"iopub.status.busy": "2025-04-09T09:04:50.581446Z",
"iopub.status.idle": "2025-04-09T09:04:54.831276Z",
"shell.execute_reply": "2025-04-09T09:04:54.829937Z",
"shell.execute_reply.started": "2025-04-09T09:04:50.582330Z"
},
"id": "POBbLwluCMeK",
"outputId": "9589beb5-86c8-4b44-d9bd-cc3316c838c9"
},
"outputs": [],
"source": [
"%pip install kagglehub\n",
"%pip install sacremoses"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-04-09T09:04:54.834196Z",
"iopub.status.busy": "2025-04-09T09:04:54.833289Z",
"iopub.status.idle": "2025-04-09T09:04:58.835896Z",
"shell.execute_reply": "2025-04-09T09:04:58.834641Z",
"shell.execute_reply.started": "2025-04-09T09:04:54.834135Z"
},
"id": "BwJ36n6vZUB2",
"tags": []
},
"outputs": [],
"source": [
"from pathlib import Path\n",
"import os\n",
"from pathlib import Path\n",
"from transformers import pipeline\n",
"from tqdm import tqdm\n",
"import pandas as pd\n",
"import torch\n",
"import kagglehub\n",
"import signal"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-04-09T09:04:58.838507Z",
"iopub.status.busy": "2025-04-09T09:04:58.837160Z",
"iopub.status.idle": "2025-04-09T09:04:58.856737Z",
"shell.execute_reply": "2025-04-09T09:04:58.855801Z",
"shell.execute_reply.started": "2025-04-09T09:04:58.838466Z"
},
"id": "cOIT5Hu5FdT2"
},
"outputs": [],
"source": [
"class GracefulExiter:\n",
" # to catch keyboard interrupts\n",
" def __init__(self):\n",
" self.should_exit = False\n",
" signal.signal(signal.SIGINT, self.exit_gracefully)\n",
" signal.signal(signal.SIGTERM, self.exit_gracefully)\n",
"\n",
" def exit_gracefully(self, signum, frame):\n",
" print(\n",
" \"\\nReceived interrupt signal. Finishing current work and saving progress...\"\n",
" )\n",
" self.should_exit = True"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-04-09T09:04:58.859897Z",
"iopub.status.busy": "2025-04-09T09:04:58.858860Z",
"iopub.status.idle": "2025-04-09T09:04:58.886712Z",
"shell.execute_reply": "2025-04-09T09:04:58.885792Z",
"shell.execute_reply.started": "2025-04-09T09:04:58.859858Z"
},
"id": "Fg9c5cFZZyoG"
},
"outputs": [],
"source": [
"def get_dataset():\n",
" # Download latest version\n",
" path = kagglehub.dataset_download(\"Cornell-University/arxiv\")\n",
"\n",
" print(\"Path to dataset files:\", path)\n",
"\n",
" file_name = os.listdir(path)[0]\n",
" path_to_dataset = Path(path) / file_name\n",
" data = pd.read_json(path_to_dataset, lines=True)\n",
"\n",
" # leave only the first common category\n",
" data[\"categories\"] = [category.split()[0] for category in data[\"categories\"]]\n",
" data[\"categories\"] = [category.split(\".\")[0] for category in data[\"categories\"]]\n",
"\n",
" # sort data in a proper way\n",
" counts = data.groupby(by=\"categories\")[\"title\"].count().sort_index()\n",
" unique_categories = counts.index.to_list()\n",
"\n",
" groups_same_category = {\n",
" category: data[data[\"categories\"] == category] for category in unique_categories\n",
" }\n",
"\n",
" max_group_size = counts.max()\n",
"\n",
" new_df = []\n",
"\n",
" for i in range(max_group_size):\n",
" for category in unique_categories:\n",
" if i < len(groups_same_category[category]):\n",
" new_df.append(groups_same_category[category].iloc[i])\n",
"\n",
" result_df = pd.DataFrame(new_df).reset_index()\n",
" return result_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-04-09T09:04:58.889441Z",
"iopub.status.busy": "2025-04-09T09:04:58.887873Z",
"iopub.status.idle": "2025-04-09T09:04:58.910755Z",
"shell.execute_reply": "2025-04-09T09:04:58.909796Z",
"shell.execute_reply.started": "2025-04-09T09:04:58.889390Z"
},
"id": "RqdjPXAk1dyg",
"tags": []
},
"outputs": [],
"source": [
"def translate_dataset(\n",
" starting_from=0,\n",
" count=1000,\n",
" batch_size=16,\n",
" save_interval=64,\n",
" dataset=None,\n",
" use_google_drive=False,\n",
"):\n",
" # if dataset is given the function will use it\n",
" # else it will download dataset\n",
"\n",
" # for colab to save files in your google drive\n",
" # just in case colab ending the session before you could save all the files\n",
"\n",
" # if use_google_drive:\n",
" # from google.colab import drive\n",
" # drive.mount('/content/drive')\n",
" # target_folder = Path(\"/content/drive/MyDrive/arxiv_translations\")\n",
" # else:\n",
" # target_folder = Path(\"russian_dataset\")\n",
" # target_folder.mkdir(exist_ok=True)\n",
"\n",
" target_folder = Path(\"dataset_parts\")\n",
" target_folder.mkdir(exist_ok=True)\n",
"\n",
" # to catch keyboard interrupts\n",
" exiter = GracefulExiter()\n",
"\n",
" result_df = dataset.copy()\n",
"\n",
" # download the model\n",
" translator = pipeline(\n",
" \"translation_en_to_ru\",\n",
" model=\"Helsinki-NLP/opus-mt-en-ru\",\n",
" device=\"cuda\" if torch.cuda.is_available() else \"cpu\",\n",
" torch_dtype=\"auto\",\n",
" )\n",
"\n",
" def clean_text(text, max_length=512):\n",
" if pd.isna(text) or text.strip() == \"\":\n",
" return \"[EMPTY]\"\n",
" if len(text) > max_length:\n",
" text = text[:max_length]\n",
" return str(text).strip()\n",
"\n",
" def translate_batch(texts, batch_size=batch_size, max_length=512):\n",
" results = []\n",
" texts = [clean_text(text, max_length) for text in texts]\n",
" try:\n",
" for out in tqdm(\n",
" translator(texts, max_length=max_length, batch_size=batch_size),\n",
" total=len(texts),\n",
" desc=\"Translating...\",\n",
" ):\n",
" results.append(out)\n",
" except Exception as e:\n",
" print(f\"Error: {e}\")\n",
" return results\n",
"\n",
" # take the necessary interval\n",
" part_df = result_df.iloc[starting_from : starting_from + count]\n",
"\n",
" russian_data = pd.DataFrame(columns=[\"authors\", \"title\", \"abstract\", \"categories\"])\n",
"\n",
" previous_temp_file = None\n",
"\n",
" for chunk_start in range(0, count, save_interval):\n",
" if exiter.should_exit:\n",
" break\n",
"\n",
" chunk_end = min(chunk_start + save_interval, count)\n",
" print(f\"Processing records {chunk_start} to {chunk_end}...\")\n",
"\n",
" chunk_df = part_df.iloc[chunk_start:chunk_end]\n",
"\n",
" translated_chunk = {\n",
" \"authors\": translate_batch(chunk_df[\"authors\"].tolist()),\n",
" \"title\": translate_batch(chunk_df[\"title\"].tolist()),\n",
" \"abstract\": translate_batch(chunk_df[\"abstract\"].tolist()),\n",
" \"categories\": chunk_df[\"categories\"].tolist(),\n",
" }\n",
" if exiter.should_exit:\n",
" print(\"Interrupt detected. Saving partial results...\")\n",
" break\n",
" chunk_df_translated = pd.DataFrame(translated_chunk)\n",
" russian_data = pd.concat([russian_data, chunk_df_translated], ignore_index=True)\n",
"\n",
" # save temperory results\n",
" temp_filename = (\n",
" target_folder / f\"{starting_from}_{starting_from + chunk_end}_temp.csv\"\n",
" )\n",
" russian_data.to_csv(temp_filename, index=False)\n",
" print(f\"Saved temporary results to {temp_filename}\")\n",
"\n",
" # removing previous temporary file\n",
" if previous_temp_file is not None and previous_temp_file.exists():\n",
" previous_temp_file.unlink()\n",
" print(f\"Removed previous temporary file: {previous_temp_file}\")\n",
"\n",
" previous_temp_file = temp_filename\n",
"\n",
" if exiter.should_exit:\n",
" # keyboard interrupt\n",
" final_filename = (\n",
" target_folder\n",
" / f\"{starting_from}_{starting_from + len(russian_data)}_partial.csv\"\n",
" )\n",
" print(f\"\\nProcess interrupted. Saving partial results to {final_filename}\")\n",
" else:\n",
" final_filename = target_folder / f\"{starting_from}_{count}_final.csv\"\n",
" print(f\"\\nProcessing completed. Saving final results to {final_filename}\")\n",
"\n",
" russian_data.to_csv(final_filename, index=False)\n",
"\n",
" # remove temperorary files\n",
" if not exiter.should_exit:\n",
" for temp_file in target_folder.glob(\"*_temp.csv\"):\n",
" temp_file.unlink()\n",
" print(\"Temporary files removed.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-04-09T09:04:58.913113Z",
"iopub.status.busy": "2025-04-09T09:04:58.911808Z"
}
},
"outputs": [],
"source": [
"df = get_dataset()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mlO-3KoY8uT6",
"outputId": "bb555bc7-6ad4-43ef-d096-06ef01b07525",
"tags": []
},
"outputs": [],
"source": [
"translate_dataset(\n",
" starting_from=0, count=50_000, dataset=df, batch_size=128, save_interval=512\n",
")"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "DataSphere Kernel",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|