{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/l_/g22b1g_n0gn4tmx9lkxqv5x00000gn/T/ipykernel_14130/269978020.py:6: DtypeWarning: Columns (7,10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  tools = pd.read_csv(\"../data/tools.csv\")\n"
     ]
    }
   ],
   "source": [
    "import pickle\n",
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Make t_map"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = pd.read_csv(\"../data/tools.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['request_id', 'request_block', 'prompt_request', 'tool', 'nonce',\n",
       "       'trader_address', 'deliver_block', 'error', 'error_message',\n",
       "       'prompt_response', 'mech_address', 'p_yes', 'p_no', 'confidence',\n",
       "       'info_utility', 'vote', 'win_probability', 'title', 'currentAnswer',\n",
       "       'request_time', 'request_month_year', 'request_month_year_week'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "t_map = tools[['request_block', 'request_time']].set_index('request_block').to_dict()['request_time']\n",
    "\n",
    "with open('../data/t_map.pkl', 'wb') as f:\n",
    "    pickle.dump(t_map, f)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('../data/t_map.pkl', 'rb') as f:\n",
    "    t_map = pickle.load(f)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Markets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['id', 'currentAnswer', 'title'], dtype='object')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms = pd.read_csv(\"../data/fpmms.csv\")\n",
    "fpmms.columns\n"
   ]
  },
  {
   "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>id</th>\n",
       "      <th>currentAnswer</th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0x0020d13c89140b47e10db54cbd53852b90bc1391</td>\n",
       "      <td>No</td>\n",
       "      <td>Will the Francis Scott Key Bridge in Baltimore...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07</td>\n",
       "      <td>No</td>\n",
       "      <td>Will FC Saarbrucken reach the final of the Ger...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Will the pro-life activists convicted for 'con...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0x0094fa304017d5c2b355790e2976f769ea600492</td>\n",
       "      <td>No</td>\n",
       "      <td>Will the Hisense U8K be considered a top-tier ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0x00b03e86def06f5afb3b5219df72df758c96ec87</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Will the ChatGPT app for Android exceed 1 mill...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3020</th>\n",
       "      <td>0xff866fd6092f8cc779fed6480e8a0a00740c4685</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Will Nvidia's market value exceed $2 trillion ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3021</th>\n",
       "      <td>0xff8fedb76e6659f9da2505b28e86ea3a7db282e7</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Will UFC face a boycott due to its $100M Bud L...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3022</th>\n",
       "      <td>0xff94627786768f5d94f7e5687de131b34c4b0c0d</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Will there be another volcanic eruption in Gri...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3023</th>\n",
       "      <td>0xffd0b522ff00ffaec575cc628d1bb4ea37346fd7</td>\n",
       "      <td>No</td>\n",
       "      <td>Will the manslaughter trial for James Crumbley...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3024</th>\n",
       "      <td>0xffd6f34459ff26040e9cf1d9e4d9aaa7026a9683</td>\n",
       "      <td>No</td>\n",
       "      <td>Will YouTube's subscribe button light up whene...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3025 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              id currentAnswer  \\\n",
       "0     0x0020d13c89140b47e10db54cbd53852b90bc1391            No   \n",
       "1     0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07            No   \n",
       "2     0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c           Yes   \n",
       "3     0x0094fa304017d5c2b355790e2976f769ea600492            No   \n",
       "4     0x00b03e86def06f5afb3b5219df72df758c96ec87           Yes   \n",
       "...                                          ...           ...   \n",
       "3020  0xff866fd6092f8cc779fed6480e8a0a00740c4685           Yes   \n",
       "3021  0xff8fedb76e6659f9da2505b28e86ea3a7db282e7           Yes   \n",
       "3022  0xff94627786768f5d94f7e5687de131b34c4b0c0d           Yes   \n",
       "3023  0xffd0b522ff00ffaec575cc628d1bb4ea37346fd7            No   \n",
       "3024  0xffd6f34459ff26040e9cf1d9e4d9aaa7026a9683            No   \n",
       "\n",
       "                                                  title  \n",
       "0     Will the Francis Scott Key Bridge in Baltimore...  \n",
       "1     Will FC Saarbrucken reach the final of the Ger...  \n",
       "2     Will the pro-life activists convicted for 'con...  \n",
       "3     Will the Hisense U8K be considered a top-tier ...  \n",
       "4     Will the ChatGPT app for Android exceed 1 mill...  \n",
       "...                                                 ...  \n",
       "3020  Will Nvidia's market value exceed $2 trillion ...  \n",
       "3021  Will UFC face a boycott due to its $100M Bud L...  \n",
       "3022  Will there be another volcanic eruption in Gri...  \n",
       "3023  Will the manslaughter trial for James Crumbley...  \n",
       "3024  Will YouTube's subscribe button light up whene...  \n",
       "\n",
       "[3025 rows x 3 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/l_/g22b1g_n0gn4tmx9lkxqv5x00000gn/T/ipykernel_14130/371090584.py:1: DtypeWarning: Columns (2) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  delivers = pd.read_csv(\"../data/delivers.csv\")\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(262750, 12)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "delivers = pd.read_csv(\"../data/delivers.csv\")\n",
    "delivers.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(244242, 6)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "requests = pd.read_csv(\"../data/requests.csv\")\n",
    "requests.columns\n",
    "\n",
    "requests.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(243228, 22)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools.shape\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/l_/g22b1g_n0gn4tmx9lkxqv5x00000gn/T/ipykernel_14130/4197935432.py:1: DtypeWarning: Columns (7,10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  tools = pd.read_csv(\"../data/tools.csv\")\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Index(['request_id', 'request_block', 'prompt_request', 'tool', 'nonce',\n",
       "       'trader_address', 'deliver_block', 'error', 'error_message',\n",
       "       'prompt_response', 'mech_address', 'p_yes', 'p_no', 'confidence',\n",
       "       'info_utility', 'vote', 'win_probability', 'title', 'currentAnswer',\n",
       "       'request_time', 'request_month_year', 'request_month_year_week'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools = pd.read_csv(\"../data/tools.csv\")\n",
    "tools.columns\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(244623, 22)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "autogen",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}