{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the data\n",
    "with open('data/pun_anno/pun_het.json') as f:\n",
    "    data_het = json.load(f)\n",
    "\n",
    "with open('data/pun_anno/pun_hom.json') as f:\n",
    "    data_hom = json.load(f)\n",
    "\n",
    "with open('data/pun_annotated.json') as f:\n",
    "    data_anno = json.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a DataFrame\n",
    "df_anno = pd.DataFrame(data_anno)\n",
    "\n",
    "df_het = pd.DataFrame(data_het)\n",
    "# df switch columns to rows\n",
    "df_het = df_het.T\n",
    "\n",
    "df_hom = pd.DataFrame(data_hom)\n",
    "# df switch columns to rows\n",
    "df_hom = df_hom.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0        hom_362\n",
      "1        het_837\n",
      "2        het_635\n",
      "3        hom_657\n",
      "4       het_1275\n",
      "          ...   \n",
      "1894    hom_2076\n",
      "1895    hom_1437\n",
      "1896    het_1530\n",
      "1897     het_100\n",
      "1898     hom_364\n",
      "Name: ID, Length: 1899, dtype: object\n",
      "Index(['het_991', 'het_990', 'het_987', 'het_982', 'het_980', 'het_978',\n",
      "       'het_973', 'het_958', 'het_956', 'het_955',\n",
      "       ...\n",
      "       'het_1739', 'het_1741', 'het_1747', 'het_1748', 'het_1753', 'het_1757',\n",
      "       'het_1758', 'het_1759', 'het_1764', 'het_1770'],\n",
      "      dtype='object', length=1146)\n",
      "Index(['hom_998', 'hom_996', 'hom_994', 'hom_993', 'hom_992', 'hom_990',\n",
      "       'hom_99', 'hom_985', 'hom_984', 'hom_981',\n",
      "       ...\n",
      "       'hom_2221', 'hom_2223', 'hom_2225', 'hom_2226', 'hom_2230', 'hom_2232',\n",
      "       'hom_2234', 'hom_2243', 'hom_2246', 'hom_2247'],\n",
      "      dtype='object', length=1443)\n"
     ]
    }
   ],
   "source": [
    "# print index for each df\n",
    "print(df_anno['ID'])\n",
    "print(df_het.index)\n",
    "print(df_hom.index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(655, 8) (1146, 11) (1899, 8)\n",
      "(825, 8) (1443, 11) (1899, 8)\n"
     ]
    }
   ],
   "source": [
    "# find matches from df_anno['ID'] to df_het.index\n",
    "df_het_match = df_anno[df_anno['ID'].isin(df_het.index)]\n",
    "print(df_het_match.shape, df_het.shape, df_anno.shape)\n",
    "\n",
    "# find matches from df_anno['ID'] to df_hom.index\n",
    "df_hom_match = df_anno[df_anno['ID'].isin(df_hom.index)]\n",
    "print(df_hom_match.shape, df_hom.shape, df_anno.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0        hom_362\n",
      "3        hom_657\n",
      "6       hom_1510\n",
      "7        hom_955\n",
      "8       hom_1505\n",
      "          ...   \n",
      "1893     hom_151\n",
      "1894    hom_2076\n",
      "1895    hom_1437\n",
      "1896    het_1530\n",
      "1898     hom_364\n",
      "Name: ID, Length: 1244, dtype: object\n",
      "Index(['het_955', 'het_907', 'het_905', 'het_786', 'het_783', 'het_777',\n",
      "       'het_639', 'het_573', 'het_466', 'het_435',\n",
      "       ...\n",
      "       'het_1739', 'het_1741', 'het_1747', 'het_1748', 'het_1753', 'het_1757',\n",
      "       'het_1758', 'het_1759', 'het_1764', 'het_1770'],\n",
      "      dtype='object', length=491)\n"
     ]
    }
   ],
   "source": [
    "# print not matched IDs and index\n",
    "print(df_anno[~df_anno['ID'].isin(df_het.index)]['ID'])\n",
    "print(df_het.index[~df_het.index.isin(df_anno['ID'])])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# merge df_anno and df_het where ID matches with index\n",
    "df_het_merge = pd.merge(df_anno, df_het, left_on='ID', right_index=True)\n",
    "# score_avg \n",
    "df_het_merge['score_avg'] = df_het_merge['Funniness (1-5)'].apply(lambda x: np.mean(x))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}