{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/cyberosa/.pyenv/versions/hf_dashboards/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import gradio as gr\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "div_data = pd.read_parquet(\"../data/closed_markets_div.parquet\")"
   ]
  },
  {
   "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>currentAnswer</th>\n",
       "      <th>id</th>\n",
       "      <th>openingTimestamp</th>\n",
       "      <th>market_creator</th>\n",
       "      <th>opening_datetime</th>\n",
       "      <th>first_outcome_prob</th>\n",
       "      <th>second_outcome_prob</th>\n",
       "      <th>kl_divergence</th>\n",
       "      <th>off_by_perc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>315</th>\n",
       "      <td>no</td>\n",
       "      <td>0x29462bf8c8f24772cd6da03878a4aee5c5813474</td>\n",
       "      <td>1724976000</td>\n",
       "      <td>pearl</td>\n",
       "      <td>2024-08-30 02:00:00</td>\n",
       "      <td>0.9416</td>\n",
       "      <td>0.0584</td>\n",
       "      <td>2.840439</td>\n",
       "      <td>94.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>323</th>\n",
       "      <td>yes</td>\n",
       "      <td>0x0ad9d4edb0a401ec9a5b4f2ccf7942d28c29d4e3</td>\n",
       "      <td>1724976000</td>\n",
       "      <td>quickstart</td>\n",
       "      <td>2024-08-30 02:00:00</td>\n",
       "      <td>0.0499</td>\n",
       "      <td>0.9501</td>\n",
       "      <td>2.997734</td>\n",
       "      <td>95.01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    currentAnswer                                          id  \\\n",
       "315            no  0x29462bf8c8f24772cd6da03878a4aee5c5813474   \n",
       "323           yes  0x0ad9d4edb0a401ec9a5b4f2ccf7942d28c29d4e3   \n",
       "\n",
       "    openingTimestamp market_creator    opening_datetime  first_outcome_prob  \\\n",
       "315       1724976000          pearl 2024-08-30 02:00:00              0.9416   \n",
       "323       1724976000     quickstart 2024-08-30 02:00:00              0.0499   \n",
       "\n",
       "     second_outcome_prob  kl_divergence  off_by_perc  \n",
       "315               0.0584       2.840439        94.16  \n",
       "323               0.9501       2.997734        95.01  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "div_data.loc[div_data[\"off_by_perc\"]>=90]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>currentAnswer</th>\n",
       "      <th>id</th>\n",
       "      <th>openingTimestamp</th>\n",
       "      <th>market_creator</th>\n",
       "      <th>opening_datetime</th>\n",
       "      <th>first_outcome_prob</th>\n",
       "      <th>second_outcome_prob</th>\n",
       "      <th>kl_divergence</th>\n",
       "      <th>off_by_perc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>no</td>\n",
       "      <td>0x927beda324bfd4514a7b64ab5594451fdaf4796e</td>\n",
       "      <td>1722816000</td>\n",
       "      <td>quickstart</td>\n",
       "      <td>2024-08-05 02:00:00</td>\n",
       "      <td>0.8792</td>\n",
       "      <td>0.1208</td>\n",
       "      <td>2.113619</td>\n",
       "      <td>87.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>yes</td>\n",
       "      <td>0x90bb15982f2b5a5f044ad8ff49fe20daddfb8ca7</td>\n",
       "      <td>1724803200</td>\n",
       "      <td>quickstart</td>\n",
       "      <td>2024-08-28 02:00:00</td>\n",
       "      <td>0.1166</td>\n",
       "      <td>0.8834</td>\n",
       "      <td>2.149006</td>\n",
       "      <td>88.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>315</th>\n",
       "      <td>no</td>\n",
       "      <td>0x29462bf8c8f24772cd6da03878a4aee5c5813474</td>\n",
       "      <td>1724976000</td>\n",
       "      <td>pearl</td>\n",
       "      <td>2024-08-30 02:00:00</td>\n",
       "      <td>0.9416</td>\n",
       "      <td>0.0584</td>\n",
       "      <td>2.840439</td>\n",
       "      <td>94.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>323</th>\n",
       "      <td>yes</td>\n",
       "      <td>0x0ad9d4edb0a401ec9a5b4f2ccf7942d28c29d4e3</td>\n",
       "      <td>1724976000</td>\n",
       "      <td>quickstart</td>\n",
       "      <td>2024-08-30 02:00:00</td>\n",
       "      <td>0.0499</td>\n",
       "      <td>0.9501</td>\n",
       "      <td>2.997734</td>\n",
       "      <td>95.01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    currentAnswer                                          id  \\\n",
       "52             no  0x927beda324bfd4514a7b64ab5594451fdaf4796e   \n",
       "293           yes  0x90bb15982f2b5a5f044ad8ff49fe20daddfb8ca7   \n",
       "315            no  0x29462bf8c8f24772cd6da03878a4aee5c5813474   \n",
       "323           yes  0x0ad9d4edb0a401ec9a5b4f2ccf7942d28c29d4e3   \n",
       "\n",
       "    openingTimestamp market_creator    opening_datetime  first_outcome_prob  \\\n",
       "52        1722816000     quickstart 2024-08-05 02:00:00              0.8792   \n",
       "293       1724803200     quickstart 2024-08-28 02:00:00              0.1166   \n",
       "315       1724976000          pearl 2024-08-30 02:00:00              0.9416   \n",
       "323       1724976000     quickstart 2024-08-30 02:00:00              0.0499   \n",
       "\n",
       "     second_outcome_prob  kl_divergence  off_by_perc  \n",
       "52                0.1208       2.113619        87.92  \n",
       "293               0.8834       2.149006        88.34  \n",
       "315               0.0584       2.840439        94.16  \n",
       "323               0.9501       2.997734        95.01  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "div_data.loc[div_data[\"kl_divergence\"]>=2.0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_markets = closed_markets.copy(deep=True)\n",
    "    all_markets[\"market_creator\"] = \"all\"\n",
    "\n",
    "    # merging both dataframes\n",
    "    final_markets = pd.concat([div_data, all_markets], ignore_index=True)\n",
    "    final_markets = final_markets.sort_values(by=\"opening_datetime\", ascending=True)\n",
    "\n",
    "    # Create the main figure and axis\n",
    "    fig, ax1 = plt.subplots(figsize=(10, 6))\n",
    "\n",
    "    # Create the boxplot using seaborn\n",
    "    sns.boxplot(\n",
    "        data=closed_markets,\n",
    "        x=\"month_year_week\",\n",
    "        y=\"kl_divergence\",\n",
    "        ax=ax1,\n",
    "        hue=\"market_creator\",\n",
    "        order=[\"pearl\", \"quickstart\", \"all\"],\n",
    "    )\n",
    "\n",
    "    # Set labels and title for the main axis\n",
    "    ax1.set_xlabel(\"Week\")\n",
    "    ax1.set_ylabel(\"KL Divergence\")\n",
    "    ax1.set_title(\"KL Divergence Boxplot with Off-by Percentage\")\n",
    "\n",
    "    # Create a secondary y-axis\n",
    "    ax2 = ax1.twinx()\n",
    "\n",
    "    # Plot the off_by_perc values on the secondary y-axis\n",
    "    for i, week in enumerate(closed_markets[\"month_year_week\"].unique()):\n",
    "        off_by_perc = closed_markets[closed_markets[\"month_year_week\"] == week][\n",
    "            \"off_by_perc\"\n",
    "        ]\n",
    "        ax2.scatter([i] * len(off_by_perc), off_by_perc, color=\"red\", alpha=0.01)\n",
    "\n",
    "    # Set label for the secondary y-axis\n",
    "    ax2.set_ylabel(\"Off-by Percentage\")\n",
    "\n",
    "    # Adjust the layout and display the plot\n",
    "    plt.tight_layout()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "hf_dashboards",
   "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}