adding notebook for ChatDoctor data

notebooks/ChatDoctor-data.ipynb

@@ -0,0 +1,205 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Access token is needed for reading this data (contact Lavita's admin: [email protected])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datasets import load_dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Reading data from Lavita's Hugging Face\n",
+    "data_hf_name = \"lavita/ChatDoctor-HealthCareMagic-100k\"\n",
+    "dataset = load_dataset(data_hf_name)\n",
+    "\n",
+    "# Converting data to pandas DataFrame\n",
+    "df = dataset['train'].to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>instruction</th>\n",
+       "      <th>input</th>\n",
+       "      <th>output</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>I woke up this morning feeling the whole room ...</td>\n",
+       "      <td>Hi, Thank you for posting your query. The most...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>My baby has been pooing 5-6 times a day for a ...</td>\n",
+       "      <td>Hi... Thank you for consulting in Chat Doctor....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>Hello, My husband is taking Oxycodone due to a...</td>\n",
+       "      <td>Hello, and I hope I can help you today.First, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>lump under left nipple and stomach pain (male)...</td>\n",
+       "      <td>HI. You have two different problems. The lump ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>I have a 5 month old baby who is very congeste...</td>\n",
+       "      <td>Thank you for using Chat Doctor. I would sugge...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>I am F 38 in good shape work out (do triathlon...</td>\n",
+       "      <td>Hi, From history it seems that you might be ha...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>sir, MY uncle has ILD-Interstitial Lung diseas...</td>\n",
+       "      <td>Thanks for your question on Chat Doctor. I can...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>my husband was working on a project in the hou...</td>\n",
+       "      <td>Hello. It could be a blood collection due to m...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>hi my nine year old son had a cough and flu sy...</td>\n",
+       "      <td>Hi, If the symptoms persist that long this sug...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>If you are a doctor, please answer the medical...</td>\n",
+       "      <td>gyno problemsfor the past few months, I have b...</td>\n",
+       "      <td>Dear Friend. Welcome to Chat Doctor. I am Chat...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                         instruction  \\\n",
+       "0  If you are a doctor, please answer the medical...   \n",
+       "1  If you are a doctor, please answer the medical...   \n",
+       "2  If you are a doctor, please answer the medical...   \n",
+       "3  If you are a doctor, please answer the medical...   \n",
+       "4  If you are a doctor, please answer the medical...   \n",
+       "5  If you are a doctor, please answer the medical...   \n",
+       "6  If you are a doctor, please answer the medical...   \n",
+       "7  If you are a doctor, please answer the medical...   \n",
+       "8  If you are a doctor, please answer the medical...   \n",
+       "9  If you are a doctor, please answer the medical...   \n",
+       "\n",
+       "                                               input  \\\n",
+       "0  I woke up this morning feeling the whole room ...   \n",
+       "1  My baby has been pooing 5-6 times a day for a ...   \n",
+       "2  Hello, My husband is taking Oxycodone due to a...   \n",
+       "3  lump under left nipple and stomach pain (male)...   \n",
+       "4  I have a 5 month old baby who is very congeste...   \n",
+       "5  I am F 38 in good shape work out (do triathlon...   \n",
+       "6  sir, MY uncle has ILD-Interstitial Lung diseas...   \n",
+       "7  my husband was working on a project in the hou...   \n",
+       "8  hi my nine year old son had a cough and flu sy...   \n",
+       "9  gyno problemsfor the past few months, I have b...   \n",
+       "\n",
+       "                                              output  \n",
+       "0  Hi, Thank you for posting your query. The most...  \n",
+       "1  Hi... Thank you for consulting in Chat Doctor....  \n",
+       "2  Hello, and I hope I can help you today.First, ...  \n",
+       "3  HI. You have two different problems. The lump ...  \n",
+       "4  Thank you for using Chat Doctor. I would sugge...  \n",
+       "5  Hi, From history it seems that you might be ha...  \n",
+       "6  Thanks for your question on Chat Doctor. I can...  \n",
+       "7  Hello. It could be a blood collection due to m...  \n",
+       "8  Hi, If the symptoms persist that long this sug...  \n",
+       "9  Dear Friend. Welcome to Chat Doctor. I am Chat...  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "qa-env",
+   "language": "python",
+   "name": "qa-env"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}