cleaning notebooks folder

notebooks/markets_analysis.ipynb

@@ -15,13 +15,75 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "fpmms = pd.read_parquet('../data/all_fpmms.parquet')"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "markets = pd.read_parquet('../data/fpmms.parquet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 4688 entries, 0 to 4687\n",
+      "Data columns (total 4 columns):\n",
+      " #   Column          Non-Null Count  Dtype \n",
+      "---  ------          --------------  ----- \n",
+      " 0   currentAnswer   4688 non-null   object\n",
+      " 1   id              4688 non-null   object\n",
+      " 2   title           4688 non-null   object\n",
+      " 3   market_creator  4688 non-null   object\n",
+      "dtypes: object(4)\n",
+      "memory usage: 146.6+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "markets.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "currentAnswer\n",
+       "No       2771\n",
+       "Yes      1914\n",
+       "no          1\n",
+       "False       1\n",
+       "IND         1\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "markets.currentAnswer.value_counts()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -1308,7 +1370,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

notebooks/tools_accuracy.ipynb

@@ -0,0 +1,1130 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import json\n",
+    "sns.set_style(\"darkgrid\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = pd.read_parquet('../data/tools.parquet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 133835 entries, 0 to 133834\n",
+      "Data columns (total 23 columns):\n",
+      " #   Column                   Non-Null Count   Dtype  \n",
+      "---  ------                   --------------   -----  \n",
+      " 0   request_id               133835 non-null  object \n",
+      " 1   request_block            133835 non-null  object \n",
+      " 2   prompt_request           133835 non-null  object \n",
+      " 3   tool                     133835 non-null  object \n",
+      " 4   nonce                    133835 non-null  object \n",
+      " 5   trader_address           133835 non-null  object \n",
+      " 6   deliver_block            133835 non-null  object \n",
+      " 7   error                    133835 non-null  int64  \n",
+      " 8   error_message            1873 non-null    object \n",
+      " 9   prompt_response          133664 non-null  object \n",
+      " 10  mech_address             133664 non-null  object \n",
+      " 11  p_yes                    131962 non-null  float64\n",
+      " 12  p_no                     131962 non-null  float64\n",
+      " 13  confidence               131962 non-null  float64\n",
+      " 14  info_utility             131962 non-null  float64\n",
+      " 15  vote                     104902 non-null  object \n",
+      " 16  win_probability          131962 non-null  float64\n",
+      " 17  title                    133835 non-null  object \n",
+      " 18  currentAnswer            107007 non-null  object \n",
+      " 19  request_time             133835 non-null  object \n",
+      " 20  request_month_year       133835 non-null  object \n",
+      " 21  request_month_year_week  133835 non-null  object \n",
+      " 22  market_creator           133835 non-null  object \n",
+      "dtypes: float64(5), int64(1), object(17)\n",
+      "memory usage: 23.5+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "tools.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pickle\n",
+    "t_map = pickle.load(open(\"../data/t_map.pkl\", \"rb\"))\n",
+    "type(t_map)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "475329"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(t_map)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "29624577\n"
+     ]
+    }
+   ],
+   "source": [
+    "for item in t_map:\n",
+    "    print(item)\n",
+    "    break"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2023-07-12 11:58:40'"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "min(t_map.values())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2023-08-24 16:04:50'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "t_map[29624577]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2024-09-04 07:32:15'"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "max(t_map.values())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "request_id         1155886186807766696223563218518399229072982679...\n",
+       "request_block                                               35356121\n",
+       "prompt_request     Please take over the role of a Data Scientist ...\n",
+       "tool                                   prediction-request-rag-claude\n",
+       "nonce                           2c4c8c5c-afcf-4e28-a09a-aa2bae3f5444\n",
+       "trader_address            0x22335c348afa4eae4cc6d2158c1ac259aaaecdfe\n",
+       "deliver_block                                               35356134\n",
+       "error                                                              0\n",
+       "error_message                                                   None\n",
+       "prompt_response    \\nYou will be evaluating the likelihood of an ...\n",
+       "mech_address              0x5e1d1eb61e1164d5a50b28c575da73a29595dff7\n",
+       "p_yes                                                            0.6\n",
+       "p_no                                                             0.4\n",
+       "confidence                                                       0.7\n",
+       "info_utility                                                     0.7\n",
+       "vote                                                             Yes\n",
+       "win_probability                                                  0.6\n",
+       "title              Will there be an increase in the wasp populati...\n",
+       "currentAnswer                                                    Yes\n",
+       "Name: 0, dtype: object"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools.iloc[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "vote\n",
+       "Yes    55881\n",
+       "No     51741\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools.vote.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 132150 entries, 0 to 132149\n",
+      "Data columns (total 22 columns):\n",
+      " #   Column                   Non-Null Count   Dtype  \n",
+      "---  ------                   --------------   -----  \n",
+      " 0   request_id               132150 non-null  object \n",
+      " 1   request_block            132150 non-null  int64  \n",
+      " 2   prompt_request           132150 non-null  object \n",
+      " 3   tool                     132150 non-null  object \n",
+      " 4   nonce                    132150 non-null  object \n",
+      " 5   trader_address           132150 non-null  object \n",
+      " 6   deliver_block            132150 non-null  int64  \n",
+      " 7   error                    132149 non-null  float64\n",
+      " 8   error_message            9702 non-null    object \n",
+      " 9   prompt_response          132060 non-null  object \n",
+      " 10  mech_address             132150 non-null  object \n",
+      " 11  p_yes                    122447 non-null  float64\n",
+      " 12  p_no                     122447 non-null  float64\n",
+      " 13  confidence               122447 non-null  float64\n",
+      " 14  info_utility             122447 non-null  float64\n",
+      " 15  vote                     102396 non-null  object \n",
+      " 16  win_probability          122447 non-null  float64\n",
+      " 17  title                    124256 non-null  object \n",
+      " 18  currentAnswer            85763 non-null   object \n",
+      " 19  request_time             132150 non-null  object \n",
+      " 20  request_month_year       132150 non-null  object \n",
+      " 21  request_month_year_week  132150 non-null  object \n",
+      "dtypes: float64(6), int64(2), object(14)\n",
+      "memory usage: 22.2+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "tools.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fpmms = pd.read_parquet('../data/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",
+       "    </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",
+       "    </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",
+       "    </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",
+       "    </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",
+       "    </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",
+       "    </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  \n",
+       "0  Will the first floating offshore wind research...  \n",
+       "1  Will the Francis Scott Key Bridge in Baltimore...  \n",
+       "2  Will FC Saarbrucken reach the final of the Ger...  \n",
+       "3  Will the pro-life activists convicted for 'con...  \n",
+       "4  Will Apple announce the release of a new M4 ch...  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fpmms.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4251"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(fpmms)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 18035 entries, 0 to 18034\n",
+      "Data columns (total 20 columns):\n",
+      " #   Column                  Non-Null Count  Dtype              \n",
+      "---  ------                  --------------  -----              \n",
+      " 0   trader_address          18035 non-null  object             \n",
+      " 1   market_creator          18035 non-null  object             \n",
+      " 2   trade_id                18035 non-null  object             \n",
+      " 3   creation_timestamp      18035 non-null  datetime64[ns, UTC]\n",
+      " 4   title                   18035 non-null  object             \n",
+      " 5   market_status           18035 non-null  object             \n",
+      " 6   collateral_amount       18035 non-null  float64            \n",
+      " 7   outcome_index           18035 non-null  object             \n",
+      " 8   trade_fee_amount        18035 non-null  float64            \n",
+      " 9   outcomes_tokens_traded  18035 non-null  float64            \n",
+      " 10  current_answer          18035 non-null  int64              \n",
+      " 11  is_invalid              18035 non-null  bool               \n",
+      " 12  winning_trade           18035 non-null  bool               \n",
+      " 13  earnings                18035 non-null  float64            \n",
+      " 14  redeemed                18035 non-null  bool               \n",
+      " 15  redeemed_amount         18035 non-null  float64            \n",
+      " 16  num_mech_calls          18035 non-null  int64              \n",
+      " 17  mech_fee_amount         18035 non-null  float64            \n",
+      " 18  net_earnings            18035 non-null  float64            \n",
+      " 19  roi                     18035 non-null  float64            \n",
+      "dtypes: bool(3), datetime64[ns, UTC](1), float64(8), int64(2), object(6)\n",
+      "memory usage: 2.4+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "prof = pd.read_parquet('../data/all_trades_profitability.parquet')\n",
+    "prof.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "market_creator\n",
+       "quickstart    16775\n",
+       "pearl          1260\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prof.market_creator.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trades = pd.read_parquet(\"../data/fpmmTrades.parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "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>request_id</th>\n",
+       "      <th>request_block</th>\n",
+       "      <th>prompt_request</th>\n",
+       "      <th>tool</th>\n",
+       "      <th>nonce</th>\n",
+       "      <th>trader_address</th>\n",
+       "      <th>deliver_block</th>\n",
+       "      <th>error</th>\n",
+       "      <th>error_message</th>\n",
+       "      <th>prompt_response</th>\n",
+       "      <th>mech_address</th>\n",
+       "      <th>p_yes</th>\n",
+       "      <th>p_no</th>\n",
+       "      <th>confidence</th>\n",
+       "      <th>info_utility</th>\n",
+       "      <th>vote</th>\n",
+       "      <th>win_probability</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [request_id, request_block, prompt_request, tool, nonce, trader_address, deliver_block, error, error_message, prompt_response, mech_address, p_yes, p_no, confidence, info_utility, vote, win_probability]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools.head()"
+   ]
+  },
+  {
+   "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>collateralAmount</th>\n",
+       "      <th>collateralAmountUSD</th>\n",
+       "      <th>collateralToken</th>\n",
+       "      <th>creationTimestamp</th>\n",
+       "      <th>trader_address</th>\n",
+       "      <th>feeAmount</th>\n",
+       "      <th>id</th>\n",
+       "      <th>oldOutcomeTokenMarginalPrice</th>\n",
+       "      <th>outcomeIndex</th>\n",
+       "      <th>outcomeTokenMarginalPrice</th>\n",
+       "      <th>...</th>\n",
+       "      <th>market_creator</th>\n",
+       "      <th>fpmm.answerFinalizedTimestamp</th>\n",
+       "      <th>fpmm.arbitrationOccurred</th>\n",
+       "      <th>fpmm.currentAnswer</th>\n",
+       "      <th>fpmm.id</th>\n",
+       "      <th>fpmm.isPendingArbitration</th>\n",
+       "      <th>fpmm.openingTimestamp</th>\n",
+       "      <th>fpmm.outcomes</th>\n",
+       "      <th>fpmm.title</th>\n",
+       "      <th>fpmm.condition.id</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>450426474650738688</td>\n",
+       "      <td>0.4504269694034145716308073094168006</td>\n",
+       "      <td>0xe91d153e0b41518a2ce8dd3d7944fa863463a97d</td>\n",
+       "      <td>1724553455</td>\n",
+       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
+       "      <td>9008529493014773</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x02...</td>\n",
+       "      <td>0.592785210609610270634125335572129</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.6171295391012242250994586583534301</td>\n",
+       "      <td>...</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>1725071760</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0x00000000000000000000000000000000000000000000...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1724976000</td>\n",
+       "      <td>[Yes, No]</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>610163214546941400</td>\n",
+       "      <td>0.6101636232215150135654007337015298</td>\n",
+       "      <td>0xe91d153e0b41518a2ce8dd3d7944fa863463a97d</td>\n",
+       "      <td>1724811940</td>\n",
+       "      <td>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>12203264290938828</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x03...</td>\n",
+       "      <td>0.842992636523755061934822129394812</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.8523396372892128845826889719620915</td>\n",
+       "      <td>...</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>1725071760</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0x00000000000000000000000000000000000000000000...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1724976000</td>\n",
+       "      <td>[Yes, No]</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>789065092332460672</td>\n",
+       "      <td>0.7890644120527324071908793822796086</td>\n",
+       "      <td>0xe91d153e0b41518a2ce8dd3d7944fa863463a97d</td>\n",
+       "      <td>1724815755</td>\n",
+       "      <td>0x09e9d42a029e8b0c2df3871709a762117a681d92</td>\n",
+       "      <td>15781301846649213</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x09...</td>\n",
+       "      <td>0.7983775743712442891104598770339028</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.8152123711444691659642000374025623</td>\n",
+       "      <td>...</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>1725071760</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0x00000000000000000000000000000000000000000000...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1724976000</td>\n",
+       "      <td>[Yes, No]</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1000000000000000000</td>\n",
+       "      <td>1.000000605383660329048491794939126</td>\n",
+       "      <td>0xe91d153e0b41518a2ce8dd3d7944fa863463a97d</td>\n",
+       "      <td>1724546620</td>\n",
+       "      <td>0x09e9d42a029e8b0c2df3871709a762117a681d92</td>\n",
+       "      <td>20000000000000000</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x09...</td>\n",
+       "      <td>0.5110745907733438805447072252622708</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.5746805204222762335911904727318937</td>\n",
+       "      <td>...</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>1725071760</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0x00000000000000000000000000000000000000000000...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1724976000</td>\n",
+       "      <td>[Yes, No]</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>100000000000000000</td>\n",
+       "      <td>0.1000004271262862419547394646567906</td>\n",
+       "      <td>0xe91d153e0b41518a2ce8dd3d7944fa863463a97d</td>\n",
+       "      <td>1724771260</td>\n",
+       "      <td>0x0d049dcaece0ecb6fc81a460da7bcc2a4785d6e5</td>\n",
+       "      <td>2000000000000000</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x0d...</td>\n",
+       "      <td>0.2713968218662319388988681987389408</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.2804586217805511523845593360379658</td>\n",
+       "      <td>...</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>1725071760</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0x00000000000000000000000000000000000000000000...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>False</td>\n",
+       "      <td>1724976000</td>\n",
+       "      <td>[Yes, No]</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 24 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      collateralAmount                   collateralAmountUSD  \\\n",
+       "0   450426474650738688  0.4504269694034145716308073094168006   \n",
+       "1   610163214546941400  0.6101636232215150135654007337015298   \n",
+       "2   789065092332460672  0.7890644120527324071908793822796086   \n",
+       "3  1000000000000000000   1.000000605383660329048491794939126   \n",
+       "4   100000000000000000  0.1000004271262862419547394646567906   \n",
+       "\n",
+       "                              collateralToken creationTimestamp  \\\n",
+       "0  0xe91d153e0b41518a2ce8dd3d7944fa863463a97d        1724553455   \n",
+       "1  0xe91d153e0b41518a2ce8dd3d7944fa863463a97d        1724811940   \n",
+       "2  0xe91d153e0b41518a2ce8dd3d7944fa863463a97d        1724815755   \n",
+       "3  0xe91d153e0b41518a2ce8dd3d7944fa863463a97d        1724546620   \n",
+       "4  0xe91d153e0b41518a2ce8dd3d7944fa863463a97d        1724771260   \n",
+       "\n",
+       "                               trader_address          feeAmount  \\\n",
+       "0  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   9008529493014773   \n",
+       "1  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736  12203264290938828   \n",
+       "2  0x09e9d42a029e8b0c2df3871709a762117a681d92  15781301846649213   \n",
+       "3  0x09e9d42a029e8b0c2df3871709a762117a681d92  20000000000000000   \n",
+       "4  0x0d049dcaece0ecb6fc81a460da7bcc2a4785d6e5   2000000000000000   \n",
+       "\n",
+       "                                                  id  \\\n",
+       "0  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x02...   \n",
+       "1  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x03...   \n",
+       "2  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x09...   \n",
+       "3  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x09...   \n",
+       "4  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f50x0d...   \n",
+       "\n",
+       "           oldOutcomeTokenMarginalPrice outcomeIndex  \\\n",
+       "0   0.592785210609610270634125335572129            1   \n",
+       "1   0.842992636523755061934822129394812            1   \n",
+       "2  0.7983775743712442891104598770339028            1   \n",
+       "3  0.5110745907733438805447072252622708            1   \n",
+       "4  0.2713968218662319388988681987389408            0   \n",
+       "\n",
+       "              outcomeTokenMarginalPrice  ... market_creator  \\\n",
+       "0  0.6171295391012242250994586583534301  ...     quickstart   \n",
+       "1  0.8523396372892128845826889719620915  ...     quickstart   \n",
+       "2  0.8152123711444691659642000374025623  ...     quickstart   \n",
+       "3  0.5746805204222762335911904727318937  ...     quickstart   \n",
+       "4  0.2804586217805511523845593360379658  ...     quickstart   \n",
+       "\n",
+       "  fpmm.answerFinalizedTimestamp fpmm.arbitrationOccurred  \\\n",
+       "0                    1725071760                    False   \n",
+       "1                    1725071760                    False   \n",
+       "2                    1725071760                    False   \n",
+       "3                    1725071760                    False   \n",
+       "4                    1725071760                    False   \n",
+       "\n",
+       "                                  fpmm.currentAnswer  \\\n",
+       "0  0x00000000000000000000000000000000000000000000...   \n",
+       "1  0x00000000000000000000000000000000000000000000...   \n",
+       "2  0x00000000000000000000000000000000000000000000...   \n",
+       "3  0x00000000000000000000000000000000000000000000...   \n",
+       "4  0x00000000000000000000000000000000000000000000...   \n",
+       "\n",
+       "                                      fpmm.id fpmm.isPendingArbitration  \\\n",
+       "0  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5                     False   \n",
+       "1  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5                     False   \n",
+       "2  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5                     False   \n",
+       "3  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5                     False   \n",
+       "4  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5                     False   \n",
+       "\n",
+       "   fpmm.openingTimestamp fpmm.outcomes  \\\n",
+       "0             1724976000     [Yes, No]   \n",
+       "1             1724976000     [Yes, No]   \n",
+       "2             1724976000     [Yes, No]   \n",
+       "3             1724976000     [Yes, No]   \n",
+       "4             1724976000     [Yes, No]   \n",
+       "\n",
+       "                                          fpmm.title  \\\n",
+       "0  Will the first floating offshore wind research...   \n",
+       "1  Will the first floating offshore wind research...   \n",
+       "2  Will the first floating offshore wind research...   \n",
+       "3  Will the first floating offshore wind research...   \n",
+       "4  Will the first floating offshore wind research...   \n",
+       "\n",
+       "                                   fpmm.condition.id  \n",
+       "0  0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...  \n",
+       "1  0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...  \n",
+       "2  0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...  \n",
+       "3  0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...  \n",
+       "4  0x0e940f12f30e928e4879c52d065d9da739a3d3f020d1...  \n",
+       "\n",
+       "[5 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trades.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 23455 entries, 0 to 23454\n",
+      "Data columns (total 24 columns):\n",
+      " #   Column                         Non-Null Count  Dtype \n",
+      "---  ------                         --------------  ----- \n",
+      " 0   collateralAmount               23455 non-null  object\n",
+      " 1   collateralAmountUSD            23455 non-null  object\n",
+      " 2   collateralToken                23455 non-null  object\n",
+      " 3   creationTimestamp              23455 non-null  object\n",
+      " 4   trader_address                 23455 non-null  object\n",
+      " 5   feeAmount                      23455 non-null  object\n",
+      " 6   id                             23455 non-null  object\n",
+      " 7   oldOutcomeTokenMarginalPrice   23455 non-null  object\n",
+      " 8   outcomeIndex                   23455 non-null  object\n",
+      " 9   outcomeTokenMarginalPrice      23455 non-null  object\n",
+      " 10  outcomeTokensTraded            23455 non-null  object\n",
+      " 11  title                          23455 non-null  object\n",
+      " 12  transactionHash                23455 non-null  object\n",
+      " 13  type                           23455 non-null  object\n",
+      " 14  market_creator                 23455 non-null  object\n",
+      " 15  fpmm.answerFinalizedTimestamp  21489 non-null  object\n",
+      " 16  fpmm.arbitrationOccurred       23455 non-null  bool  \n",
+      " 17  fpmm.currentAnswer             21489 non-null  object\n",
+      " 18  fpmm.id                        23455 non-null  object\n",
+      " 19  fpmm.isPendingArbitration      23455 non-null  bool  \n",
+      " 20  fpmm.openingTimestamp          23455 non-null  object\n",
+      " 21  fpmm.outcomes                  23455 non-null  object\n",
+      " 22  fpmm.title                     23455 non-null  object\n",
+      " 23  fpmm.condition.id              23455 non-null  object\n",
+      "dtypes: bool(2), object(22)\n",
+      "memory usage: 4.0+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "trades.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "market_creator\n",
+       "quickstart    21852\n",
+       "pearl          1603\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trades.market_creator.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fpmms_trades = pd.read_parquet('../data/fpmmTrades.parquet')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Adding market creator info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ERROR getting the market creator of 0xae7b042059b179dcac3169657fac111d7925f8dd\n",
+      "ERROR getting the market creator of 0x347e4ef0ff34cf39d1c7e08bc07c68c41a4836d6\n",
+      "ERROR getting the market creator of 0x8e03d3a7a3dfd930f73577ba4204deadf12b33f3\n",
+      "ERROR getting the market creator of 0x2a0b461417fa0ae8bbeb28ed265fbe3944772435\n",
+      "ERROR getting the market creator of 0x8069ea45a18910fa493a6a736438971b0e59ec9b\n",
+      "ERROR getting the market creator of 0xdf91eac2a8573646c7e8e95c740877fe3d38f11f\n",
+      "ERROR getting the market creator of 0x87f0fcfe810502555f8d1439793155cbfa2eb583\n",
+      "ERROR getting the market creator of 0x7bcf0f480e52da1597d7437d5b4a4644b1e7ec23\n",
+      "ERROR getting the market creator of 0xcfef6a50bd9439d1e1a15fcfe99068a57e533d95\n",
+      "ERROR getting the market creator of 0xaeb8c31302361d42ec806faf406ef0c30b6eba5f\n",
+      "ERROR getting the market creator of 0x9db7e7a0c82a229a7f3bb15046ff0c3a778b7291\n",
+      "ERROR getting the market creator of 0x85c31bbeaab5468d97900e69d87a459aba997fa5\n",
+      "ERROR getting the market creator of 0x36660fec571bb4d5849a433f9ec64622416f1dbb\n",
+      "ERROR getting the market creator of 0x5ebe6dcb1ac4470bb71c89cf1e6b9abc48b637ba\n",
+      "ERROR getting the market creator of 0xa0acfecc55465870c9baa7c954a0e81165fb112c\n",
+      "ERROR getting the market creator of 0xd6d6951a8fa033f91a2227d75fb1eebc139e2e57\n",
+      "ERROR getting the market creator of 0x651d04044b780e68f3f952796fb7c06fb0928ad2\n",
+      "ERROR getting the market creator of 0xe271378e094db9d64e34c6c14a7492bcccd11dfb\n",
+      "ERROR getting the market creator of 0x37c241945001f6c26c886c8d551cc2e6cf34c214\n",
+      "ERROR getting the market creator of 0x20b9e32b17360310c633e5676f28430bd723f4bd\n",
+      "ERROR getting the market creator of 0x06d873e7465a6680f5487905d7b5daf7f2c6e299\n",
+      "ERROR getting the market creator of 0xd28b5e2f2ce950705354cd2ceaf4eab9d23db52b\n",
+      "ERROR getting the market creator of 0x4d70e1ac779094e9790c8b74954d15729371e6bc\n",
+      "ERROR getting the market creator of 0x81489c0eab196fb88704f08ef34b8a9ed7137c91\n",
+      "ERROR getting the market creator of 0x223c99787f25179d51a9934a426b6d1b252bb4bd\n",
+      "ERROR getting the market creator of 0xd61b2c4f70645c830bd5af76426d6b22af63c152\n",
+      "ERROR getting the market creator of 0xe66e931f7b065361f56e41d61f599adab3b167c2\n",
+      "ERROR getting the market creator of 0x5ccf21332df9af6195a5b1ba78d15562db915a35\n",
+      "ERROR getting the market creator of 0xf8e68d9f66d2534df36c23db6770467da1c1ff1b\n",
+      "ERROR getting the market creator of 0x2b9274ddf2213d8a6b2930a5b82801165df55017\n",
+      "ERROR getting the market creator of 0xf9349c5ea0b5559abd8dfa6cdd4e4d5d913e1e61\n",
+      "ERROR getting the market creator of 0xad8aa6f927bb6a38af8121418f1b64d4ed8be99c\n",
+      "ERROR getting the market creator of 0x3dcc00904249d796a89943de15c85ac11afc5d66\n",
+      "ERROR getting the market creator of 0x10ece1553b5017414388fe78f64720814d7f8799\n",
+      "ERROR getting the market creator of 0x0930bcc328a695419d596dae380dec7fb43cd715\n",
+      "ERROR getting the market creator of 0x956d8bbc930372482a361dec7e4707b15d8b02f4\n",
+      "ERROR getting the market creator of 0x14da1cc12b382142ac3e2422162f122a0a31ec45\n",
+      "ERROR getting the market creator of 0x28dd86a2c82ce02970eff7f4ea9ebde97750adc8\n",
+      "ERROR getting the market creator of 0xb997d5e2fddf39b8a197715c7b200df612d74360\n",
+      "ERROR getting the market creator of 0x2064ceecb78a382f4988d41f881abef89b6e785c\n",
+      "ERROR getting the market creator of 0xe715cc8f264ab48f75bb1b5c11d7dbaf949d73c5\n",
+      "ERROR getting the market creator of 0x5fc7213135962250147030c5dd30b84a80f2ad1e\n",
+      "ERROR getting the market creator of 0x10ccffdc8e801ab4fda98371723cda4e30e6d672\n",
+      "ERROR getting the market creator of 0x6e5d93fdcc14db02a58ace636c2dcff8db36039d\n",
+      "ERROR getting the market creator of 0xf792f6a308525b72b5d47f12798668c140f5968e\n",
+      "ERROR getting the market creator of 0x00897abcbbefe4f558956b7a9d1b7819677e4d90\n",
+      "ERROR getting the market creator of 0x29448445959cc5045c03b7f316fa3332cc2b37b7\n",
+      "ERROR getting the market creator of 0xdb8c2038cd17645216125f323048dcd4c9845826\n",
+      "ERROR getting the market creator of 0x32969cce1791f13dc5d500b9e701ffb931baae03\n",
+      "ERROR getting the market creator of 0x84aeb93d348c6da1ea4b0016c207aefc26edaa44\n",
+      "ERROR getting the market creator of 0xdda87f7ec43aab7080e9ac23ae1550e5bc89d6cc\n",
+      "ERROR getting the market creator of 0xafd80421ce35298d3698ca0f4008477a169c9ea2\n",
+      "ERROR getting the market creator of 0xffc47cb1ecd41daae58e39fd4193d6fe9a6f5d2e\n",
+      "ERROR getting the market creator of 0x351d430d229740f986ee240612c932c66188dd09\n",
+      "ERROR getting the market creator of 0xd72455c8d5398a2b3b822bbc7cc0de638ea35519\n",
+      "ERROR getting the market creator of 0x2c83cf4bb92e55e35b6e4af6eca6c0a85fb73650\n",
+      "ERROR getting the market creator of 0xf2baf410b7d42d7572fb2f39cf216ffae8d4cafe\n",
+      "ERROR getting the market creator of 0xb42a955a0e06b3e6bdf229c9abfd2fdad20688a7\n",
+      "ERROR getting the market creator of 0x35021fcc0d15c4e87fc1c7fb527f389829dde3d9\n",
+      "ERROR getting the market creator of 0xaa19120a9976c75dc569ab2cfcc087cd224db4e2\n",
+      "ERROR getting the market creator of 0x6e79766698f58a25d2548b76601de9535c5080d3\n",
+      "ERROR getting the market creator of 0x6915dcb7601802ea4a2dd840c44b6ed4473b5ce2\n",
+      "ERROR getting the market creator of 0x6957f7ac4a0a09f237a901749e518a678d1a614a\n",
+      "ERROR getting the market creator of 0x785a9d3329955ffd7cd24ca7a89ce2da21ac62da\n",
+      "ERROR getting the market creator of 0x1e738f7e82102e2f56fef62df473d3f1f1dc53b1\n",
+      "ERROR getting the market creator of 0x8e23b89649f22a6e8084b34a1a5de28d9ddf5a88\n",
+      "ERROR getting the market creator of 0x31c6b19cae793ba90ee9c70263af773c27df2774\n",
+      "ERROR getting the market creator of 0x3a2d7bf095988f30daf308b5484cd74903d82c22\n",
+      "ERROR getting the market creator of 0xde10d01d4315cf64d9feeb79e9a593d78da8a50b\n",
+      "ERROR getting the market creator of 0xa57b7f04bb813b5a6ded7cc92c5bd56586d8f7d4\n",
+      "ERROR getting the market creator of 0x97609769fddc72ea9f45f62cef1f7a9658dd1efe\n",
+      "ERROR getting the market creator of 0x7ddbfbebbec1635315f9217cbf9de8afd272c8de\n",
+      "ERROR getting the market creator of 0x37cdc93194dc7f46f3cc377cf4350f56455a4f85\n",
+      "ERROR getting the market creator of 0x75c10935141d740b71e1763aa6a3139643754655\n",
+      "ERROR getting the market creator of 0x0f98789650877b1928960490a5a19769ac1c84b3\n",
+      "ERROR getting the market creator of 0x9f87c202db8b3270406a3084817909a9d4afc6ea\n",
+      "ERROR getting the market creator of 0x8cfb5af2b0287b34a423755d0481478f0a8f1356\n",
+      "ERROR getting the market creator of 0x09244905029648aca18830291bb62634b04d9a46\n",
+      "ERROR getting the market creator of 0x4e9a5580ce24dd06ed8d6b1d75a7ccce7abf7361\n",
+      "ERROR getting the market creator of 0x8bbeb8a3e1f6fdc9e95aa0d7e80ebc6dc1468b7a\n",
+      "ERROR getting the market creator of 0xcb279a4ebb3f0d78cb15817e942cc7aea01b8545\n",
+      "ERROR getting the market creator of 0xb36fa15e34dd50b8199c57305573dc48d1271b50\n",
+      "ERROR getting the market creator of 0x2198981fc1d8b3c61e7df9a50cf240708c057dfa\n",
+      "ERROR getting the market creator of 0x37bab68f9ae4f9c7ce915d9e1f3404e7cd1794cc\n",
+      "ERROR getting the market creator of 0x97f59586921ebdcfc07694ba8376f59871db11f9\n",
+      "ERROR getting the market creator of 0xc79bf3f6370e8a8002a3093c379752f395a3c291\n",
+      "ERROR getting the market creator of 0x178021f40d4e1ed270f2d2125f9f80d3e78a1836\n",
+      "ERROR getting the market creator of 0xcca6ccde20a551caec29d6c1318f4f2ec7e6063c\n"
+     ]
+    }
+   ],
+   "source": [
+    "tools[\"market_creator\"] = \"\"\n",
+    "# traverse the list of traders\n",
+    "traders_list = list(tools.trader_address.unique())\n",
+    "for trader_address in traders_list:\n",
+    "    market_creator = \"\"\n",
+    "    try:\n",
+    "        trades = fpmms_trades[fpmms_trades[\"trader_address\"] == trader_address]\n",
+    "        market_creator = trades.iloc[0][\"market_creator\"]  # first value is enough\n",
+    "    except Exception:\n",
+    "        print(f\"ERROR getting the market creator of {trader_address}\")\n",
+    "    tools_of_the_trader = tools[tools[\"trader_address\"] == trader_address]\n",
+    "    # update\n",
+    "    tools.loc[tools[\"trader_address\"] == trader_address, \"market_creator\"] = market_creator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "market_creator\n",
+       "quickstart    121106\n",
+       "pearl          12729\n",
+       "                5182\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools.market_creator.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "139017"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.03727601660228605"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "5182/139017"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = tools.loc[tools[\"market_creator\"] != \"\"]\n",
+    "tools.to_parquet(\"../data/tools.parquet\", index=False)"
+   ]
+  }
+ ],
+ "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
+}

notebooks/weekly_analysis.ipynb

@@ -40,7 +40,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "currentAnswer\n",
+       "No     66982\n",
+       "Yes    42810\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools.currentAnswer.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -60,230 +83,102 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_trades.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
    "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>trader_address</th>\n",
-       "      <th>trade_id</th>\n",
-       "      <th>creation_timestamp</th>\n",
-       "      <th>title</th>\n",
-       "      <th>market_status</th>\n",
-       "      <th>collateral_amount</th>\n",
-       "      <th>outcome_index</th>\n",
-       "      <th>trade_fee_amount</th>\n",
-       "      <th>outcomes_tokens_traded</th>\n",
-       "      <th>current_answer</th>\n",
-       "      <th>is_invalid</th>\n",
-       "      <th>winning_trade</th>\n",
-       "      <th>earnings</th>\n",
-       "      <th>redeemed</th>\n",
-       "      <th>redeemed_amount</th>\n",
-       "      <th>num_mech_calls</th>\n",
-       "      <th>mech_fee_amount</th>\n",
-       "      <th>net_earnings</th>\n",
-       "      <th>roi</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
-       "      <td>0x017947579ab51313c31fe1cc562c0f1726ec09c90x02...</td>\n",
-       "      <td>2024-05-19 01:26:30+00:00</td>\n",
-       "      <td>Will Google's Pixel 9 lineup be officially rel...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.638</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.013</td>\n",
-       "      <td>1.206</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.206</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.206</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>0.556</td>\n",
-       "      <td>0.854</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
-       "      <td>0x027f6bc849e273477f4a63085192714084917fcc0x02...</td>\n",
-       "      <td>2024-06-12 01:16:55+00:00</td>\n",
-       "      <td>Will the 2D-animated Paramount Plus show 'Tale...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>1.000</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.020</td>\n",
-       "      <td>1.840</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.840</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.840</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.030</td>\n",
-       "      <td>0.790</td>\n",
-       "      <td>0.752</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
-       "      <td>0x027f6bc849e273477f4a63085192714084917fcc0x02...</td>\n",
-       "      <td>2024-06-12 15:08:00+00:00</td>\n",
-       "      <td>Will the 2D-animated Paramount Plus show 'Tale...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.800</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.016</td>\n",
-       "      <td>1.518</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.518</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.518</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.030</td>\n",
-       "      <td>0.672</td>\n",
-       "      <td>0.795</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
-       "      <td>0x027f6bc849e273477f4a63085192714084917fcc0x02...</td>\n",
-       "      <td>2024-06-13 07:22:55+00:00</td>\n",
-       "      <td>Will the 2D-animated Paramount Plus show 'Tale...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.456</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.009</td>\n",
-       "      <td>1.003</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>True</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.030</td>\n",
-       "      <td>-0.495</td>\n",
-       "      <td>-1.000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0x022b36c50b85b8ae7addfb8a35d76c59d5814834</td>\n",
-       "      <td>0x027f6bc849e273477f4a63085192714084917fcc0x02...</td>\n",
-       "      <td>2024-06-14 03:01:20+00:00</td>\n",
-       "      <td>Will the 2D-animated Paramount Plus show 'Tale...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.704</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.014</td>\n",
-       "      <td>1.198</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>True</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.030</td>\n",
-       "      <td>-0.748</td>\n",
-       "      <td>-1.000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
       "text/plain": [
-       "                               trader_address  \\\n",
-       "0  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   \n",
-       "1  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   \n",
-       "2  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   \n",
-       "3  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   \n",
-       "4  0x022b36c50b85b8ae7addfb8a35d76c59d5814834   \n",
-       "\n",
-       "                                            trade_id  \\\n",
-       "0  0x017947579ab51313c31fe1cc562c0f1726ec09c90x02...   \n",
-       "1  0x027f6bc849e273477f4a63085192714084917fcc0x02...   \n",
-       "2  0x027f6bc849e273477f4a63085192714084917fcc0x02...   \n",
-       "3  0x027f6bc849e273477f4a63085192714084917fcc0x02...   \n",
-       "4  0x027f6bc849e273477f4a63085192714084917fcc0x02...   \n",
-       "\n",
-       "         creation_timestamp  \\\n",
-       "0 2024-05-19 01:26:30+00:00   \n",
-       "1 2024-06-12 01:16:55+00:00   \n",
-       "2 2024-06-12 15:08:00+00:00   \n",
-       "3 2024-06-13 07:22:55+00:00   \n",
-       "4 2024-06-14 03:01:20+00:00   \n",
-       "\n",
-       "                                               title market_status  \\\n",
-       "0  Will Google's Pixel 9 lineup be officially rel...        CLOSED   \n",
-       "1  Will the 2D-animated Paramount Plus show 'Tale...        CLOSED   \n",
-       "2  Will the 2D-animated Paramount Plus show 'Tale...        CLOSED   \n",
-       "3  Will the 2D-animated Paramount Plus show 'Tale...        CLOSED   \n",
-       "4  Will the 2D-animated Paramount Plus show 'Tale...        CLOSED   \n",
-       "\n",
-       "   collateral_amount outcome_index  trade_fee_amount  outcomes_tokens_traded  \\\n",
-       "0              0.638             1             0.013                   1.206   \n",
-       "1              1.000             1             0.020                   1.840   \n",
-       "2              0.800             1             0.016                   1.518   \n",
-       "3              0.456             0             0.009                   1.003   \n",
-       "4              0.704             0             0.014                   1.198   \n",
-       "\n",
-       "   current_answer  is_invalid  winning_trade  earnings  redeemed  \\\n",
-       "0               1       False           True     1.206      True   \n",
-       "1               1       False           True     1.840      True   \n",
-       "2               1       False           True     1.518      True   \n",
-       "3               1       False          False     0.000      True   \n",
-       "4               1       False          False     0.000      True   \n",
-       "\n",
-       "   redeemed_amount  num_mech_calls  mech_fee_amount  net_earnings    roi  \n",
-       "0            1.206               0            0.000         0.556  0.854  \n",
-       "1            1.840               3            0.030         0.790  0.752  \n",
-       "2            1.518               3            0.030         0.672  0.795  \n",
-       "3            0.000               3            0.030        -0.495 -1.000  \n",
-       "4            0.000               3            0.030        -0.748 -1.000  "
+       "count    8210.000000\n",
+       "mean        0.129631\n",
+       "std        22.449193\n",
+       "min        -1.000000\n",
+       "25%        -1.000000\n",
+       "50%         0.117954\n",
+       "75%         0.541716\n",
+       "max      2032.090177\n",
+       "Name: roi, dtype: float64"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "all_trades.head()"
+    "all_trades.roi.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2032.0901766222644"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "max(all_trades.roi)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count    8.210000e+03\n",
+       "mean     1.269746e-02\n",
+       "std      1.381237e-02\n",
+       "min      2.000000e-07\n",
+       "25%      3.200000e-03\n",
+       "50%      1.014609e-02\n",
+       "75%      2.000000e-02\n",
+       "max      4.400000e-01\n",
+       "Name: trade_fee_amount, dtype: float64"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_trades.trade_fee_amount.describe()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 16,
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "to_investigate = all_trades.loc[all_trades[\"roi\"]==max(all_trades.roi)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -307,6 +202,7 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>trader_address</th>\n",
+       "      <th>market_creator</th>\n",
        "      <th>trade_id</th>\n",
        "      <th>creation_timestamp</th>\n",
        "      <th>title</th>\n",
@@ -329,184 +225,186 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>18936</th>\n",
-       "      <td>0xc8929dd39bb5f685435ab16345929a47caacc46b</td>\n",
-       "      <td>0xd068383c5d6d1466d10db660f33524c2725f8fb60xc8...</td>\n",
-       "      <td>2024-05-22 19:05:00+00:00</td>\n",
-       "      <td>Will Elon Musk's Neuralink successfully test i...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.100</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.002</td>\n",
-       "      <td>0.200</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>True</td>\n",
-       "      <td>0.200</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>2</td>\n",
-       "      <td>0.020</td>\n",
-       "      <td>0.078</td>\n",
-       "      <td>0.640</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18937</th>\n",
-       "      <td>0xc8929dd39bb5f685435ab16345929a47caacc46b</td>\n",
-       "      <td>0xec5578e95c71ddbad6aabf8517dcd35cf53da4970xc8...</td>\n",
-       "      <td>2024-05-22 17:57:35+00:00</td>\n",
-       "      <td>Will Kevin Spacey return to acting by 25 May 2...</td>\n",
+       "      <th>928</th>\n",
+       "      <td>0x3666da333dadd05083fef9ff6ddee588d26e4307</td>\n",
+       "      <td>quickstart</td>\n",
+       "      <td>0x11cf6ec9649097127238ffb789b0703da448d9fa0x36...</td>\n",
+       "      <td>2024-09-15 02:02:05+00:00</td>\n",
+       "      <td>Will Apple launch the iPhone 16 by 15 Septembe...</td>\n",
        "      <td>CLOSED</td>\n",
-       "      <td>0.160</td>\n",
+       "      <td>0.00001</td>\n",
        "      <td>0</td>\n",
-       "      <td>0.003</td>\n",
-       "      <td>0.309</td>\n",
+       "      <td>2.000000e-07</td>\n",
+       "      <td>0.020738</td>\n",
        "      <td>0</td>\n",
        "      <td>False</td>\n",
        "      <td>True</td>\n",
-       "      <td>0.309</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>2</td>\n",
-       "      <td>0.020</td>\n",
-       "      <td>0.126</td>\n",
-       "      <td>0.686</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18938</th>\n",
-       "      <td>0xc8929dd39bb5f685435ab16345929a47caacc46b</td>\n",
-       "      <td>0xf2c74ef39065ee2e239bf8551aedddd6b2d6add70xc8...</td>\n",
-       "      <td>2024-05-22 20:00:05+00:00</td>\n",
-       "      <td>Will Donald Trump testify in the hush money ca...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.100</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.002</td>\n",
-       "      <td>0.200</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
+       "      <td>0.020738</td>\n",
        "      <td>True</td>\n",
-       "      <td>0.200</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.030</td>\n",
-       "      <td>0.068</td>\n",
-       "      <td>0.518</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18939</th>\n",
-       "      <td>0xc8929dd39bb5f685435ab16345929a47caacc46b</td>\n",
-       "      <td>0xfdf1a762eaae0a4472599f26aeafeae043b37d360xc8...</td>\n",
-       "      <td>2024-05-22 19:42:35+00:00</td>\n",
-       "      <td>Will a new Marvel Cinematic Universe (MCU) mov...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>0.100</td>\n",
+       "      <td>0.020738</td>\n",
        "      <td>0</td>\n",
-       "      <td>0.002</td>\n",
-       "      <td>0.211</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>2</td>\n",
-       "      <td>0.020</td>\n",
-       "      <td>-0.122</td>\n",
-       "      <td>-1.000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18940</th>\n",
-       "      <td>0x7b2e78d4dfaaba045a167a70da285e30e8fca196</td>\n",
-       "      <td>0xaf8fa4b8e04bbbee6903fede1d27b3aad25b468e0x7b...</td>\n",
-       "      <td>2024-07-05 09:10:40+00:00</td>\n",
-       "      <td>Will Vice President Kamala Harris be the Democ...</td>\n",
-       "      <td>CLOSED</td>\n",
-       "      <td>1.000</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.020</td>\n",
-       "      <td>1.717</td>\n",
-       "      <td>1</td>\n",
-       "      <td>False</td>\n",
-       "      <td>True</td>\n",
-       "      <td>1.717</td>\n",
-       "      <td>False</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>0.697</td>\n",
-       "      <td>0.684</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.020727</td>\n",
+       "      <td>2032.090177</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "                                   trader_address  \\\n",
-       "18936  0xc8929dd39bb5f685435ab16345929a47caacc46b   \n",
-       "18937  0xc8929dd39bb5f685435ab16345929a47caacc46b   \n",
-       "18938  0xc8929dd39bb5f685435ab16345929a47caacc46b   \n",
-       "18939  0xc8929dd39bb5f685435ab16345929a47caacc46b   \n",
-       "18940  0x7b2e78d4dfaaba045a167a70da285e30e8fca196   \n",
+       "                                 trader_address market_creator  \\\n",
+       "928  0x3666da333dadd05083fef9ff6ddee588d26e4307     quickstart   \n",
        "\n",
-       "                                                trade_id  \\\n",
-       "18936  0xd068383c5d6d1466d10db660f33524c2725f8fb60xc8...   \n",
-       "18937  0xec5578e95c71ddbad6aabf8517dcd35cf53da4970xc8...   \n",
-       "18938  0xf2c74ef39065ee2e239bf8551aedddd6b2d6add70xc8...   \n",
-       "18939  0xfdf1a762eaae0a4472599f26aeafeae043b37d360xc8...   \n",
-       "18940  0xaf8fa4b8e04bbbee6903fede1d27b3aad25b468e0x7b...   \n",
+       "                                              trade_id  \\\n",
+       "928  0x11cf6ec9649097127238ffb789b0703da448d9fa0x36...   \n",
        "\n",
-       "             creation_timestamp  \\\n",
-       "18936 2024-05-22 19:05:00+00:00   \n",
-       "18937 2024-05-22 17:57:35+00:00   \n",
-       "18938 2024-05-22 20:00:05+00:00   \n",
-       "18939 2024-05-22 19:42:35+00:00   \n",
-       "18940 2024-07-05 09:10:40+00:00   \n",
+       "           creation_timestamp  \\\n",
+       "928 2024-09-15 02:02:05+00:00   \n",
        "\n",
-       "                                                   title market_status  \\\n",
-       "18936  Will Elon Musk's Neuralink successfully test i...        CLOSED   \n",
-       "18937  Will Kevin Spacey return to acting by 25 May 2...        CLOSED   \n",
-       "18938  Will Donald Trump testify in the hush money ca...        CLOSED   \n",
-       "18939  Will a new Marvel Cinematic Universe (MCU) mov...        CLOSED   \n",
-       "18940  Will Vice President Kamala Harris be the Democ...        CLOSED   \n",
+       "                                                 title market_status  \\\n",
+       "928  Will Apple launch the iPhone 16 by 15 Septembe...        CLOSED   \n",
        "\n",
-       "       collateral_amount outcome_index  trade_fee_amount  \\\n",
-       "18936              0.100             1             0.002   \n",
-       "18937              0.160             0             0.003   \n",
-       "18938              0.100             1             0.002   \n",
-       "18939              0.100             0             0.002   \n",
-       "18940              1.000             1             0.020   \n",
+       "     collateral_amount outcome_index  trade_fee_amount  \\\n",
+       "928            0.00001             0      2.000000e-07   \n",
        "\n",
-       "       outcomes_tokens_traded  current_answer  is_invalid  winning_trade  \\\n",
-       "18936                   0.200               1       False           True   \n",
-       "18937                   0.309               0       False           True   \n",
-       "18938                   0.200               1       False           True   \n",
-       "18939                   0.211               1       False          False   \n",
-       "18940                   1.717               1       False           True   \n",
+       "     outcomes_tokens_traded  current_answer  is_invalid  winning_trade  \\\n",
+       "928                0.020738               0       False           True   \n",
        "\n",
-       "       earnings  redeemed  redeemed_amount  num_mech_calls  mech_fee_amount  \\\n",
-       "18936     0.200     False            0.000               2            0.020   \n",
-       "18937     0.309     False            0.000               2            0.020   \n",
-       "18938     0.200     False            0.000               3            0.030   \n",
-       "18939     0.000     False            0.000               2            0.020   \n",
-       "18940     1.717     False            0.000               0            0.000   \n",
+       "     earnings  redeemed  redeemed_amount  num_mech_calls  mech_fee_amount  \\\n",
+       "928  0.020738      True         0.020738               0              0.0   \n",
        "\n",
-       "       net_earnings    roi  \n",
-       "18936         0.078  0.640  \n",
-       "18937         0.126  0.686  \n",
-       "18938         0.068  0.518  \n",
-       "18939        -0.122 -1.000  \n",
-       "18940         0.697  0.684  "
+       "     net_earnings          roi  \n",
+       "928      0.020727  2032.090177  "
       ]
      },
-     "execution_count": 16,
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "to_investigate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "928    0.036337\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(to_investigate.net_earnings -(to_investigate.trade_fee_amount + 2*0.01)) / (to_investigate.collateral_amount + to_investigate.trade_fee_amount + 2*0.01)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trades_no_mech = all_trades.loc[all_trades[\"num_mech_calls\"]==0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Index: 1649 entries, 61 to 8201\n",
+      "Data columns (total 20 columns):\n",
+      " #   Column                  Non-Null Count  Dtype              \n",
+      "---  ------                  --------------  -----              \n",
+      " 0   trader_address          1649 non-null   object             \n",
+      " 1   market_creator          1649 non-null   object             \n",
+      " 2   trade_id                1649 non-null   object             \n",
+      " 3   creation_timestamp      1649 non-null   datetime64[ns, UTC]\n",
+      " 4   title                   1649 non-null   object             \n",
+      " 5   market_status           1649 non-null   object             \n",
+      " 6   collateral_amount       1649 non-null   float64            \n",
+      " 7   outcome_index           1649 non-null   object             \n",
+      " 8   trade_fee_amount        1649 non-null   float64            \n",
+      " 9   outcomes_tokens_traded  1649 non-null   float64            \n",
+      " 10  current_answer          1649 non-null   int64              \n",
+      " 11  is_invalid              1649 non-null   bool               \n",
+      " 12  winning_trade           1649 non-null   bool               \n",
+      " 13  earnings                1649 non-null   float64            \n",
+      " 14  redeemed                1649 non-null   bool               \n",
+      " 15  redeemed_amount         1649 non-null   float64            \n",
+      " 16  num_mech_calls          1649 non-null   int64              \n",
+      " 17  mech_fee_amount         1649 non-null   float64            \n",
+      " 18  net_earnings            1649 non-null   float64            \n",
+      " 19  roi                     1649 non-null   float64            \n",
+      "dtypes: bool(3), datetime64[ns, UTC](1), float64(8), int64(2), object(6)\n",
+      "memory usage: 236.7+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "trades_no_mech.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.20085261875761268"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(trades_no_mech)/len(all_trades)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count    1649.000000\n",
+       "mean        1.378776\n",
+       "std        50.053860\n",
+       "min        -1.000000\n",
+       "25%        -1.000000\n",
+       "50%         0.199740\n",
+       "75%         0.673038\n",
+       "max      2032.090177\n",
+       "Name: roi, dtype: float64"
+      ]
+     },
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "all_trades.tail()"
+    "trades_no_mech.roi.describe()"
    ]
   },
   {

tabs/tool_accuracy.py

@@ -127,7 +127,9 @@ def plot_tools_weighted_accuracy_graph(tools_accuracy_info: pd.DataFrame):
     return gr.Plot(value=plot.get_figure())
 
 
-def plot_tools_weighted_accuracy_rotated_graph(tools_accuracy_info: pd.DataFrame):
+def plot_tools_weighted_accuracy_rotated_graph(
+    tools_accuracy_info: pd.DataFrame,
+) -> gr.Plot:
     tools_accuracy_info = tools_accuracy_info.sort_values(
         by="weighted_accuracy", ascending=False
     )