Prepare dataset

Author: ashwinprasadme

extras/fine_tuning/1.finetuning_data_prepare.ipynb

@@ -0,0 +1,70 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "# Paths to your pickle files\n",
+    "train_data_path_cg = 'finetuning_cg_gpt_v1.jsonl'\n",
+    "train_data_path_cs = 'finetuning_cs_gpt_v1.jsonl'\n",
+    "\n",
+    "# Load the jsonl files\n",
+    "train_data_cg = pd.read_json(train_data_path_cg, lines=True)\n",
+    "train_data_cs = pd.read_json(train_data_path_cs, lines=True)\n",
+    "\n",
+    "# rename column to text\n",
+    "train_data_cg.rename(columns={'messages': 'text'}, inplace=True)\n",
+    "train_data_cs.rename(columns={'messages': 'text'}, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Save to CSV in new directory\n",
+    "import os\n",
+    "\n",
+    "os.makedirs('data_cg', exist_ok=True)\n",
+    "os.makedirs('data_cs', exist_ok=True)\n",
+    "\n",
+    "train_data_cg.to_csv('data_cg/train.csv', index=False)\n",
+    "train_data_cs.to_csv('data_cs/train.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}