{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import gc\n",
    "sns.set_style(\"darkgrid\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "fpmms = pd.read_parquet('../data/all_fpmms.parquet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>title</th>\n",
       "      <th>market_creator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>No</td>\n",
       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
       "      <td>Will the first floating offshore wind research...</td>\n",
       "      <td>quickstart</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>No</td>\n",
       "      <td>0x0020d13c89140b47e10db54cbd53852b90bc1391</td>\n",
       "      <td>Will the Francis Scott Key Bridge in Baltimore...</td>\n",
       "      <td>quickstart</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>No</td>\n",
       "      <td>0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07</td>\n",
       "      <td>Will FC Saarbrucken reach the final of the Ger...</td>\n",
       "      <td>quickstart</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Yes</td>\n",
       "      <td>0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c</td>\n",
       "      <td>Will the pro-life activists convicted for 'con...</td>\n",
       "      <td>quickstart</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Yes</td>\n",
       "      <td>0x005e3f7a90585acbec807425a750fbba1d0c2b5c</td>\n",
       "      <td>Will Apple announce the release of a new M4 ch...</td>\n",
       "      <td>quickstart</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  currentAnswer                                          id  \\\n",
       "0            No  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5   \n",
       "1            No  0x0020d13c89140b47e10db54cbd53852b90bc1391   \n",
       "2            No  0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07   \n",
       "3           Yes  0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c   \n",
       "4           Yes  0x005e3f7a90585acbec807425a750fbba1d0c2b5c   \n",
       "\n",
       "                                               title market_creator  \n",
       "0  Will the first floating offshore wind research...     quickstart  \n",
       "1  Will the Francis Scott Key Bridge in Baltimore...     quickstart  \n",
       "2  Will FC Saarbrucken reach the final of the Ger...     quickstart  \n",
       "3  Will the pro-life activists convicted for 'con...     quickstart  \n",
       "4  Will Apple announce the release of a new M4 ch...     quickstart  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "currentAnswer\n",
       "No       2583\n",
       "Yes      1833\n",
       "no          1\n",
       "False       1\n",
       "IND         1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms.currentAnswer.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "market_creator\n",
       "quickstart    4252\n",
       "pearl          167\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms.market_creator.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4419 entries, 0 to 4418\n",
      "Data columns (total 4 columns):\n",
      " #   Column          Non-Null Count  Dtype \n",
      "---  ------          --------------  ----- \n",
      " 0   currentAnswer   4419 non-null   object\n",
      " 1   id              4419 non-null   object\n",
      " 2   title           4419 non-null   object\n",
      " 3   market_creator  4419 non-null   object\n",
      "dtypes: object(4)\n",
      "memory usage: 138.2+ KB\n"
     ]
    }
   ],
   "source": [
    "fpmms.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "currentAnswer\n",
       "No       2495\n",
       "Yes      1746\n",
       "no          1\n",
       "False       1\n",
       "IND         1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms.currentAnswer.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "currentAnswer\n",
       "No       2170\n",
       "Yes      1500\n",
       "no          1\n",
       "False       1\n",
       "IND         1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fpmms.currentAnswer.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3673 entries, 0 to 3672\n",
      "Data columns (total 3 columns):\n",
      " #   Column         Non-Null Count  Dtype \n",
      "---  ------         --------------  ----- \n",
      " 0   id             3673 non-null   object\n",
      " 1   currentAnswer  3673 non-null   object\n",
      " 2   title          3673 non-null   object\n",
      "dtypes: object(3)\n",
      "memory usage: 86.2+ KB\n"
     ]
    }
   ],
   "source": [
    "fpmms.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_trades = pd.read_parquet('../data/all_trades_profitability.parquet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "is_invalid\n",
       "False    23830\n",
       "True      3877\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_trades.is_invalid.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "24722"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask = (all_trades[\"is_invalid\"] & all_trades[\"redeemed\"])\n",
    "filtered_trades = all_trades[~mask]\n",
    "len(filtered_trades)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "27707"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(all_trades)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "24722"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(filtered_trades)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "winning_trade\n",
       "True     13133\n",
       "False    11589\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_trades.winning_trade.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/gp/02mb1d514ng739czlxw1lhh00000gn/T/ipykernel_82376/982645160.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  filtered_trades[\"creation_timestamp\"] = pd.to_datetime(filtered_trades[\"creation_timestamp\"])\n"
     ]
    }
   ],
   "source": [
    "filtered_trades[\"creation_timestamp\"] = pd.to_datetime(filtered_trades[\"creation_timestamp\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "current_answer\n",
       " 1    13016\n",
       " 0    10814\n",
       "-1      892\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_trades.current_answer.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "203"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(list(all_trades.trader_address.unique()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "27707"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(all_trades)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/gp/02mb1d514ng739czlxw1lhh00000gn/T/ipykernel_70112/183699308.py:1: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n",
      "  all_trades['month_year'] = all_trades['creation_timestamp'].dt.to_period('M').astype(str)\n",
      "/var/folders/gp/02mb1d514ng739czlxw1lhh00000gn/T/ipykernel_70112/183699308.py:2: UserWarning: Converting to PeriodArray/Index representation will drop timezone information.\n",
      "  all_trades['month_year_week'] = all_trades['creation_timestamp'].dt.to_period('W').astype(str)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "winning_trade\n",
       "0    14574\n",
       "1    13133\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_trades['month_year'] = all_trades['creation_timestamp'].dt.to_period('M').astype(str)\n",
    "all_trades['month_year_week'] = all_trades['creation_timestamp'].dt.to_period('W').astype(str)\n",
    "all_trades['winning_trade'] = all_trades['winning_trade'].astype(int)\n",
    "all_trades.winning_trade.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>month_year_week</th>\n",
       "      <th>winning_trade</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-04-22/2024-04-28</td>\n",
       "      <td>60.465116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-04-29/2024-05-05</td>\n",
       "      <td>53.887043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-05-06/2024-05-12</td>\n",
       "      <td>49.626201</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-05-13/2024-05-19</td>\n",
       "      <td>47.931617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-05-20/2024-05-26</td>\n",
       "      <td>46.209810</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2024-05-27/2024-06-02</td>\n",
       "      <td>41.855369</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2024-06-03/2024-06-09</td>\n",
       "      <td>43.714888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2024-06-10/2024-06-16</td>\n",
       "      <td>46.697039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2024-06-17/2024-06-23</td>\n",
       "      <td>52.762120</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         month_year_week  winning_trade\n",
       "0  2024-04-22/2024-04-28      60.465116\n",
       "1  2024-04-29/2024-05-05      53.887043\n",
       "2  2024-05-06/2024-05-12      49.626201\n",
       "3  2024-05-13/2024-05-19      47.931617\n",
       "4  2024-05-20/2024-05-26      46.209810\n",
       "5  2024-05-27/2024-06-02      41.855369\n",
       "6  2024-06-03/2024-06-09      43.714888\n",
       "7  2024-06-10/2024-06-16      46.697039\n",
       "8  2024-06-17/2024-06-23      52.762120"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "winning_trades = all_trades.groupby(['month_year_week'])['winning_trade'].sum() / all_trades.groupby(['month_year_week'])['winning_trade'].count() * 100\n",
    "# winning_trades is a series, give it a dataframe\n",
    "winning_trades = winning_trades.reset_index()\n",
    "winning_trades.columns = winning_trades.columns.astype(str)\n",
    "winning_trades.columns = ['month_year_week', 'winning_trade']\n",
    "winning_trades"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>month_year_week</th>\n",
       "      <th>winning_trade</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2024-06-03/2024-06-09</td>\n",
       "      <td>43.714888</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         month_year_week  winning_trade\n",
       "6  2024-06-03/2024-06-09      43.714888"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "that_week = winning_trades[winning_trades[\"month_year_week\"]==\"2024-06-03/2024-06-09\"]\n",
    "that_week"
   ]
  },
  {
   "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>month_year_week</th>\n",
       "      <th>sum</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-04-22/2024-04-28</td>\n",
       "      <td>26</td>\n",
       "      <td>43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-04-29/2024-05-05</td>\n",
       "      <td>1622</td>\n",
       "      <td>3010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-05-06/2024-05-12</td>\n",
       "      <td>2788</td>\n",
       "      <td>5618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-05-13/2024-05-19</td>\n",
       "      <td>2271</td>\n",
       "      <td>4738</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-05-20/2024-05-26</td>\n",
       "      <td>1969</td>\n",
       "      <td>4261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2024-05-27/2024-06-02</td>\n",
       "      <td>1719</td>\n",
       "      <td>4107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2024-06-03/2024-06-09</td>\n",
       "      <td>1245</td>\n",
       "      <td>2848</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2024-06-10/2024-06-16</td>\n",
       "      <td>1025</td>\n",
       "      <td>2195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2024-06-17/2024-06-23</td>\n",
       "      <td>468</td>\n",
       "      <td>887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         month_year_week   sum  count\n",
       "0  2024-04-22/2024-04-28    26     43\n",
       "1  2024-04-29/2024-05-05  1622   3010\n",
       "2  2024-05-06/2024-05-12  2788   5618\n",
       "3  2024-05-13/2024-05-19  2271   4738\n",
       "4  2024-05-20/2024-05-26  1969   4261\n",
       "5  2024-05-27/2024-06-02  1719   4107\n",
       "6  2024-06-03/2024-06-09  1245   2848\n",
       "7  2024-06-10/2024-06-16  1025   2195\n",
       "8  2024-06-17/2024-06-23   468    887"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "winning_trades2 = all_trades.groupby(['month_year_week'])['winning_trade'].agg([\"sum\",\"count\"]).reset_index()\n",
    "winning_trades2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>month_year_week</th>\n",
       "      <th>sum</th>\n",
       "      <th>count</th>\n",
       "      <th>winning_trade</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2024-06-03/2024-06-09</td>\n",
       "      <td>1245</td>\n",
       "      <td>2848</td>\n",
       "      <td>43.714888</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         month_year_week   sum  count  winning_trade\n",
       "6  2024-06-03/2024-06-09  1245   2848      43.714888"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "that_week = winning_trades2[winning_trades2[\"month_year_week\"]==\"2024-06-03/2024-06-09\"]\n",
    "that_week"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "INC_TOOLS = [\n",
    "    \"prediction-online\",\n",
    "    \"prediction-offline\",\n",
    "    \"claude-prediction-online\",\n",
    "    \"claude-prediction-offline\",\n",
    "    \"prediction-offline-sme\",\n",
    "    \"prediction-online-sme\",\n",
    "    \"prediction-request-rag\",\n",
    "    \"prediction-request-reasoning\",\n",
    "    \"prediction-url-cot-claude\",\n",
    "    \"prediction-request-rag-claude\",\n",
    "    \"prediction-request-reasoning-claude\",\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = pd.read_parquet('../data/tools.parquet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 127674 entries, 0 to 127673\n",
      "Data columns (total 22 columns):\n",
      " #   Column                   Non-Null Count   Dtype  \n",
      "---  ------                   --------------   -----  \n",
      " 0   request_id               127674 non-null  object \n",
      " 1   request_block            127674 non-null  int64  \n",
      " 2   prompt_request           127674 non-null  object \n",
      " 3   tool                     127674 non-null  object \n",
      " 4   nonce                    127674 non-null  object \n",
      " 5   trader_address           127674 non-null  object \n",
      " 6   deliver_block            127674 non-null  int64  \n",
      " 7   error                    127668 non-null  float64\n",
      " 8   error_message            19534 non-null   object \n",
      " 9   prompt_response          120607 non-null  object \n",
      " 10  mech_address             127674 non-null  object \n",
      " 11  p_yes                    108134 non-null  float64\n",
      " 12  p_no                     108134 non-null  float64\n",
      " 13  confidence               108134 non-null  float64\n",
      " 14  info_utility             108134 non-null  float64\n",
      " 15  vote                     94137 non-null   object \n",
      " 16  win_probability          108134 non-null  float64\n",
      " 17  title                    118074 non-null  object \n",
      " 18  currentAnswer            88330 non-null   object \n",
      " 19  request_time             127674 non-null  object \n",
      " 20  request_month_year       127674 non-null  object \n",
      " 21  request_month_year_week  127674 non-null  object \n",
      "dtypes: float64(6), int64(2), object(14)\n",
      "memory usage: 21.4+ MB\n"
     ]
    }
   ],
   "source": [
    "tools.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "currentAnswer\n",
       "No     51140\n",
       "Yes    37190\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools.currentAnswer.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "127674"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(tools)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools_inc = tools[tools['tool'].isin(INC_TOOLS)]\n",
    "tools_non_error = tools_inc[tools_inc['error'] != 1]\n",
    "tools_non_error.loc[:, 'currentAnswer'] = tools_non_error['currentAnswer'].replace({'no': 'No', 'yes': 'Yes'})\n",
    "tools_non_error = tools_non_error[tools_non_error['currentAnswer'].isin(['Yes', 'No'])]\n",
    "tools_non_error = tools_non_error[tools_non_error['vote'].isin(['Yes', 'No'])]\n",
    "tools_non_error['win'] = (tools_non_error['currentAnswer'] == tools_non_error['vote']).astype(int)\n",
    "tools_non_error.columns = tools_non_error.columns.astype(str)\n",
    "wins = tools_non_error.groupby(['tool', 'request_month_year_week', 'win']).size().unstack().fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "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>win</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tool</th>\n",
       "      <th>request_month_year_week</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">claude-prediction-offline</th>\n",
       "      <th>2024-04-22/2024-04-28</th>\n",
       "      <td>14.0</td>\n",
       "      <td>23.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-29/2024-05-05</th>\n",
       "      <td>34.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-06/2024-05-12</th>\n",
       "      <td>22.0</td>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-13/2024-05-19</th>\n",
       "      <td>40.0</td>\n",
       "      <td>52.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-20/2024-05-26</th>\n",
       "      <td>18.0</td>\n",
       "      <td>52.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">prediction-url-cot-claude</th>\n",
       "      <th>2024-05-06/2024-05-12</th>\n",
       "      <td>67.0</td>\n",
       "      <td>91.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-13/2024-05-19</th>\n",
       "      <td>28.0</td>\n",
       "      <td>43.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-20/2024-05-26</th>\n",
       "      <td>64.0</td>\n",
       "      <td>145.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-27/2024-06-02</th>\n",
       "      <td>81.0</td>\n",
       "      <td>112.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-06-03/2024-06-09</th>\n",
       "      <td>7.0</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>91 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "win                                                   0      1\n",
       "tool                      request_month_year_week             \n",
       "claude-prediction-offline 2024-04-22/2024-04-28    14.0   23.0\n",
       "                          2024-04-29/2024-05-05    34.0   99.0\n",
       "                          2024-05-06/2024-05-12    22.0   34.0\n",
       "                          2024-05-13/2024-05-19    40.0   52.0\n",
       "                          2024-05-20/2024-05-26    18.0   52.0\n",
       "...                                                 ...    ...\n",
       "prediction-url-cot-claude 2024-05-06/2024-05-12    67.0   91.0\n",
       "                          2024-05-13/2024-05-19    28.0   43.0\n",
       "                          2024-05-20/2024-05-26    64.0  145.0\n",
       "                          2024-05-27/2024-06-02    81.0  112.0\n",
       "                          2024-06-03/2024-06-09     7.0   41.0\n",
       "\n",
       "[91 rows x 2 columns]"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "186"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_traders = list(tools.trader_address.unique())\n",
    "len(selected_traders)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "182"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(list(tools_non_error.trader_address.unique()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10817"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(tools)-len(tools_inc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "11778"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools_week = tools_non_error[tools_non_error[\"request_month_year_week\"]==\"2024-06-03/2024-06-09\"]\n",
    "len(tools_week)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_trades = all_trades.loc[all_trades[\"trader_address\"].isin(selected_traders)]\n",
    "len(filtered_trades)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_addresses = list(all_trades.trader_address.unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "for a in all_addresses:\n",
    "    if a in selected_traders:\n",
    "        print(\"found\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "for a in selected_traders:\n",
    "    if a in all_addresses:\n",
    "        print(\"found\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_tools = tools[tools[\"trader_address\"].isin(all_addresses)]\n",
    "len(filtered_tools)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    27707.000000\n",
       "mean         3.912224\n",
       "std          4.622220\n",
       "min          0.000000\n",
       "25%          1.000000\n",
       "50%          2.000000\n",
       "75%          5.000000\n",
       "max         66.000000\n",
       "Name: num_mech_calls, dtype: float64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_trades.num_mech_calls.describe()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "market_creator",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}