Upload data_conv.ipynb

data_conv.ipynb

@@ -0,0 +1,63 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "c9140a01-4f24-4dc2-8d8f-686f38dd5385",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = '/root/autodl-tmp/labeled-recipes/data/train-00000-of-00001-5dd0d415a357ff24.parquet'\n",
+    "output_file_name = '/root/autodl-tmp/data/train.jsonl'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "24d9b3a4-81e1-44c4-a25b-38c2bda4fdac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Read the Parquet file into a DataFrame\n",
+    "df = pd.read_parquet(path, engine='pyarrow')\n",
+    "\n",
+    "# Convert the DataFrame to JSONL and save it to a file\n",
+    "with open(output_file_name, 'w') as f:\n",
+    "    for index, row in df.iterrows():\n",
+    "        json_row = row.to_json()\n",
+    "        f.write(json_row + '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4c72fcf-a59b-4a6e-be45-f2f66e28bf4a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}