{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "from datasets import Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_path = \"../data/naruto.csv\"\n",
    "naruto_transcript_df = pd.read_csv(data_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>name</th>\n",
       "      <th>line</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>(Laughing) Give it up. (Shows the stone faces...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hiruzen</td>\n",
       "      <td>(Turns away from his writing) I hope you’re n...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>Naseer Sabah</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>is the best person on earth</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>muah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name                                               line\n",
       "0   Naruto   (Laughing) Give it up. (Shows the stone faces...\n",
       "1  Hiruzen   (Turns away from his writing) I hope you’re n...\n",
       "2    Ninja                                       Naseer Sabah\n",
       "3    Ninja                        is the best person on earth\n",
       "4   Naruto                                               muah"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "naruto_transcript_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove actions from transcript\n",
    "def remove_paranthesis(text):\n",
    "    result = re.sub(r'\\(.*?\\)','',text)\n",
    "    return result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "naruto_transcript_df['line'] = naruto_transcript_df['line'].apply(remove_paranthesis)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>name</th>\n",
       "      <th>line</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>Give it up.  You’re just bent, because you d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hiruzen</td>\n",
       "      <td>I hope you’re not bothering me with some tri...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>Naseer Sabah</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>is the best person on earth</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>muah</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name                                               line\n",
       "0   Naruto    Give it up.  You’re just bent, because you d...\n",
       "1  Hiruzen    I hope you’re not bothering me with some tri...\n",
       "2    Ninja                                       Naseer Sabah\n",
       "3    Ninja                        is the best person on earth\n",
       "4   Naruto                                               muah"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "naruto_transcript_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "naruto_transcript_df['number_of_words'] = naruto_transcript_df['line'].str.strip().str.split(\" \")\n",
    "naruto_transcript_df['number_of_words'] = naruto_transcript_df['number_of_words'].apply(lambda x: len(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>name</th>\n",
       "      <th>line</th>\n",
       "      <th>number_of_words</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>Give it up.  You’re just bent, because you d...</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hiruzen</td>\n",
       "      <td>I hope you’re not bothering me with some tri...</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>Naseer Sabah</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>is the best person on earth</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>muah</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name                                               line  number_of_words\n",
       "0   Naruto    Give it up.  You’re just bent, because you d...               26\n",
       "1  Hiruzen    I hope you’re not bothering me with some tri...               16\n",
       "2    Ninja                                       Naseer Sabah                2\n",
       "3    Ninja                        is the best person on earth                6\n",
       "4   Naruto                                               muah                1"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "naruto_transcript_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "naruto_transcript_df['naruto_response_flag'] = 0\n",
    "naruto_transcript_df.loc[(naruto_transcript_df['name']==\"Naruto\")&(naruto_transcript_df['number_of_words']>5),'naruto_response_flag']=1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>name</th>\n",
       "      <th>line</th>\n",
       "      <th>number_of_words</th>\n",
       "      <th>naruto_response_flag</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>Give it up.  You’re just bent, because you d...</td>\n",
       "      <td>26</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hiruzen</td>\n",
       "      <td>I hope you’re not bothering me with some tri...</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>Naseer Sabah</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ninja</td>\n",
       "      <td>is the best person on earth</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>muah</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>Iruka</td>\n",
       "      <td>Congratulations. You graduate. Naruto’s stand...</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>159</th>\n",
       "      <td>Iruka</td>\n",
       "      <td>Huh?</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>Naruto</td>\n",
       "      <td>Iruka Sensei!</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>161</th>\n",
       "      <td>Iruka</td>\n",
       "      <td>Ah! That hurts!</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>Iruka</td>\n",
       "      <td>Naruto. This is only the beginning. The road...</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>163 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        name                                               line  \\\n",
       "0     Naruto    Give it up.  You’re just bent, because you d...   \n",
       "1    Hiruzen    I hope you’re not bothering me with some tri...   \n",
       "2      Ninja                                       Naseer Sabah   \n",
       "3      Ninja                        is the best person on earth   \n",
       "4     Naruto                                               muah   \n",
       "..       ...                                                ...   \n",
       "158    Iruka   Congratulations. You graduate. Naruto’s stand...   \n",
       "159    Iruka                                               Huh?   \n",
       "160   Naruto                                     Iruka Sensei!    \n",
       "161    Iruka                                    Ah! That hurts!   \n",
       "162    Iruka    Naruto. This is only the beginning. The road...   \n",
       "\n",
       "     number_of_words  naruto_response_flag  \n",
       "0                 26                     1  \n",
       "1                 16                     0  \n",
       "2                  2                     0  \n",
       "3                  6                     0  \n",
       "4                  1                     0  \n",
       "..               ...                   ...  \n",
       "158               27                     0  \n",
       "159                1                     0  \n",
       "160                2                     0  \n",
       "161                3                     0  \n",
       "162               38                     0  \n",
       "\n",
       "[163 rows x 4 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "naruto_transcript_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "indexes_to_take = list(naruto_transcript_df[(naruto_transcript_df['naruto_response_flag']==1)&(naruto_transcript_df.index>0)].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[6, 28, 30]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "indexes_to_take[:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "system_promt = \"\"\"\" Your are Naruto from the anime \"Naruto\". Your responses should reflect his personality and speech patterns \\n\"\"\"\n",
    "\n",
    "prompts = []\n",
    "for ind in indexes_to_take:\n",
    "    prompt = system_promt\n",
    "\n",
    "    prompt += naruto_transcript_df.iloc[ind -1]['line']\n",
    "    prompt += '\\n'\n",
    "    prompt += naruto_transcript_df.iloc[ind]['line']\n",
    "    prompts.append(prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\" Your are Naruto from the anime \"Naruto\". Your responses should reflect his personality and speech patterns \n",
      " Well, I was just thinking. Maybe after you clean this all up I can take you out for some ramen. The good stuff. What do you think? \n",
      "  Now that’s some serious motivation! I’ll have this clean in no time!\n"
     ]
    }
   ],
   "source": [
    "print(prompts[3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>prompt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>\" Your are Naruto from the anime \"Naruto\". You...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>\" Your are Naruto from the anime \"Naruto\". You...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>\" Your are Naruto from the anime \"Naruto\". You...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>\" Your are Naruto from the anime \"Naruto\". You...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>\" Your are Naruto from the anime \"Naruto\". You...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              prompt\n",
       "0  \" Your are Naruto from the anime \"Naruto\". You...\n",
       "1  \" Your are Naruto from the anime \"Naruto\". You...\n",
       "2  \" Your are Naruto from the anime \"Naruto\". You...\n",
       "3  \" Your are Naruto from the anime \"Naruto\". You...\n",
       "4  \" Your are Naruto from the anime \"Naruto\". You..."
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"prompt\":prompts})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = Dataset.from_pandas(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "gradio_env",
   "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}