fixing update of tool accuracy file

data/tools_accuracy.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c334d2f2db204a97501adde354c61569b269514579781f894787e52829407d
-size 1014
+oid sha256:8103fd33f62fd3080293e6b7677dde31efe71a5a9719fbdcf960d7323726e2c2
+size 1010

notebooks/markets_analysis.ipynb

@@ -0,0 +1,1372 @@
+{
+ "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": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fpmms = pd.read_parquet('../data/fpmms.parquet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>currentAnswer</th>\n",
+       "      <th>title</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0x0020d13c89140b47e10db54cbd53852b90bc1391</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Will the Francis Scott Key Bridge in Baltimore...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Will FC Saarbrucken reach the final of the Ger...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Will the pro-life activists convicted for 'con...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0x005e3f7a90585acbec807425a750fbba1d0c2b5c</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Will Apple announce the release of a new M4 ch...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0x0094fa304017d5c2b355790e2976f769ea600492</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Will the Hisense U8K be considered a top-tier ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                           id currentAnswer  \\\n",
+       "0  0x0020d13c89140b47e10db54cbd53852b90bc1391            No   \n",
+       "1  0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07            No   \n",
+       "2  0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c           Yes   \n",
+       "3  0x005e3f7a90585acbec807425a750fbba1d0c2b5c           Yes   \n",
+       "4  0x0094fa304017d5c2b355790e2976f769ea600492            No   \n",
+       "\n",
+       "                                               title  \n",
+       "0  Will the Francis Scott Key Bridge in Baltimore...  \n",
+       "1  Will FC Saarbrucken reach the final of the Ger...  \n",
+       "2  Will the pro-life activists convicted for 'con...  \n",
+       "3  Will Apple announce the release of a new M4 ch...  \n",
+       "4  Will the Hisense U8K be considered a top-tier ...  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fpmms.head()"
+   ]
+  },
+  {
+   "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": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_trades = pd.read_parquet('../data/all_trades_profitability.parquet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "27707"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(all_trades)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "127674"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "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>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>0x005e3f7a90585acbec807425a750fbba1d0c2b5c0x03...</td>\n",
+       "      <td>2024-05-12 04:26:35+00:00</td>\n",
+       "      <td>Will Apple announce the release of a new M4 ch...</td>\n",
+       "      <td>CLOSED</td>\n",
+       "      <td>0.682360</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.013647</td>\n",
+       "      <td>0.889368</td>\n",
+       "      <td>0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "      <td>0.889368</td>\n",
+       "      <td>True</td>\n",
+       "      <td>0.889368</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.193360</td>\n",
+       "      <td>0.277813</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>0x017947579ab51313c31fe1cc562c0f1726ec09c90x03...</td>\n",
+       "      <td>2024-05-21 04:26:40+00:00</td>\n",
+       "      <td>Will Google's Pixel 9 lineup be officially rel...</td>\n",
+       "      <td>CLOSED</td>\n",
+       "      <td>0.732158</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.014643</td>\n",
+       "      <td>1.120798</td>\n",
+       "      <td>1</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "      <td>1.120798</td>\n",
+       "      <td>True</td>\n",
+       "      <td>1.120798</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.373997</td>\n",
+       "      <td>0.500799</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>0x0290d432108f22fdc91e6677b1436e7bc702bced0x03...</td>\n",
+       "      <td>2024-05-09 08:26:30+00:00</td>\n",
+       "      <td>Will the ICC take legal action against Israel ...</td>\n",
+       "      <td>CLOSED</td>\n",
+       "      <td>1.246551</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.024931</td>\n",
+       "      <td>2.505972</td>\n",
+       "      <td>0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "      <td>2.505972</td>\n",
+       "      <td>True</td>\n",
+       "      <td>2.505972</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.234490</td>\n",
+       "      <td>0.970906</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>0x02c244eef143b16254f3d6a444c2e44d35a175590x03...</td>\n",
+       "      <td>2024-05-04 04:24:20+00:00</td>\n",
+       "      <td>Will Trent Staggs win the Senatorial race to r...</td>\n",
+       "      <td>CLOSED</td>\n",
+       "      <td>1.219659</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.024393</td>\n",
+       "      <td>2.948666</td>\n",
+       "      <td>1</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>True</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>-1.244052</td>\n",
+       "      <td>-1.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736</td>\n",
+       "      <td>0x0518764fb0684f3156c200ae78d4214d19d8b9530x03...</td>\n",
+       "      <td>2024-05-19 04:22:50+00:00</td>\n",
+       "      <td>Will OpenAI release another model update by 20...</td>\n",
+       "      <td>CLOSED</td>\n",
+       "      <td>1.203097</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.024062</td>\n",
+       "      <td>3.143667</td>\n",
+       "      <td>0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>True</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>-1.227159</td>\n",
+       "      <td>-1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                               trader_address  \\\n",
+       "0  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736   \n",
+       "1  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736   \n",
+       "2  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736   \n",
+       "3  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736   \n",
+       "4  0x034c4ad84f7ac6638bf19300d5bbe7d9b981e736   \n",
+       "\n",
+       "                                            trade_id  \\\n",
+       "0  0x005e3f7a90585acbec807425a750fbba1d0c2b5c0x03...   \n",
+       "1  0x017947579ab51313c31fe1cc562c0f1726ec09c90x03...   \n",
+       "2  0x0290d432108f22fdc91e6677b1436e7bc702bced0x03...   \n",
+       "3  0x02c244eef143b16254f3d6a444c2e44d35a175590x03...   \n",
+       "4  0x0518764fb0684f3156c200ae78d4214d19d8b9530x03...   \n",
+       "\n",
+       "         creation_timestamp  \\\n",
+       "0 2024-05-12 04:26:35+00:00   \n",
+       "1 2024-05-21 04:26:40+00:00   \n",
+       "2 2024-05-09 08:26:30+00:00   \n",
+       "3 2024-05-04 04:24:20+00:00   \n",
+       "4 2024-05-19 04:22:50+00:00   \n",
+       "\n",
+       "                                               title market_status  \\\n",
+       "0  Will Apple announce the release of a new M4 ch...        CLOSED   \n",
+       "1  Will Google's Pixel 9 lineup be officially rel...        CLOSED   \n",
+       "2  Will the ICC take legal action against Israel ...        CLOSED   \n",
+       "3  Will Trent Staggs win the Senatorial race to r...        CLOSED   \n",
+       "4  Will OpenAI release another model update by 20...        CLOSED   \n",
+       "\n",
+       "   collateral_amount outcome_index  trade_fee_amount  outcomes_tokens_traded  \\\n",
+       "0           0.682360             0          0.013647                0.889368   \n",
+       "1           0.732158             1          0.014643                1.120798   \n",
+       "2           1.246551             0          0.024931                2.505972   \n",
+       "3           1.219659             0          0.024393                2.948666   \n",
+       "4           1.203097             1          0.024062                3.143667   \n",
+       "\n",
+       "   current_answer  is_invalid  winning_trade  earnings  redeemed  \\\n",
+       "0               0       False           True  0.889368      True   \n",
+       "1               1       False           True  1.120798      True   \n",
+       "2               0       False           True  2.505972      True   \n",
+       "3               1       False          False  0.000000      True   \n",
+       "4               0       False          False  0.000000      True   \n",
+       "\n",
+       "   redeemed_amount  num_mech_calls  mech_fee_amount  net_earnings       roi  \n",
+       "0         0.889368               0              0.0      0.193360  0.277813  \n",
+       "1         1.120798               0              0.0      0.373997  0.500799  \n",
+       "2         2.505972               0              0.0      1.234490  0.970906  \n",
+       "3         0.000000               0              0.0     -1.244052 -1.000000  \n",
+       "4         0.000000               0              0.0     -1.227159 -1.000000  "
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_trades.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "winning_trade\n",
+       "False    14574\n",
+       "True     13133\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_trades.winning_trade.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_trades[\"creation_timestamp\"] = pd.to_datetime(all_trades[\"creation_timestamp\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "current_answer\n",
+       " 1    13016\n",
+       " 0    10814\n",
+       "-1     3877\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_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
+}

scripts/tools.py

@@ -529,14 +529,15 @@ def update_tools_accuracy(
     existing_tools = list(tools_acc["tool"].values)
     for tool in tools_to_update:
         if tool in existing_tools:
-            new_accuracy = acc_info[acc_info["tool"] == tool, "tool_accuracy"]
-            new_volume = acc_info[acc_info["tool"] == tool, "total_requests"]
-            new_min_timeline = acc_info[acc_info["tool"] == tool, "min"]
-            new_max_timeline = acc_info[acc_info["tool"] == tool, "max"]
-            tools_acc[tools_acc["tool"] == tool, "tool_accuracy"] = new_accuracy
-            tools_acc[tools_acc["tool"] == tool, "total_requests"] = new_volume
-            tools_acc[tools_acc["tool"] == tool, "min"] = new_min_timeline
-            tools_acc[tools_acc["tool"] == tool, "max"] = new_max_timeline
+            new_accuracy = acc_info[acc_info["tool"] == tool]["tool_accuracy"].values[0]
+            new_volume = acc_info[acc_info["tool"] == tool]["total_requests"].values[0]
+            new_min_timeline = acc_info[acc_info["tool"] == tool]["min"].values[0]
+            new_max_timeline = acc_info[acc_info["tool"] == tool]["max"].values[0]
+            tools_acc.loc[tools_acc["tool"] == tool, "tool_accuracy"] = new_accuracy
+            tools_acc.loc[tools_acc["tool"] == tool, "total_requests"] = new_volume
+            tools_acc.loc[tools_acc["tool"] == tool, "min"] = new_min_timeline
+            tools_acc.loc[tools_acc["tool"] == tool, "max"] = new_max_timeline
+    print(tools_acc)
     return tools_acc
 
 

tabs/tool_win.py

@@ -3,46 +3,59 @@ import gradio as gr
 from typing import List
 
 
-HEIGHT=600
-WIDTH=1000
+HEIGHT = 600
+WIDTH = 1000
 
 
 def get_tool_winning_rate(tools_df: pd.DataFrame, inc_tools: List[str]) -> pd.DataFrame:
     """Gets the tool winning rate data for the given tools and calculates the winning percentage."""
-    tools_inc = tools_df[tools_df['tool'].isin(inc_tools)]
+    tools_inc = tools_df[tools_df["tool"].isin(inc_tools)]
     # tools_inc['error'] = tools_inc.apply(set_error, axis=1)
-    tools_non_error = tools_inc[tools_inc['error'] != 1]
-    tools_non_error.loc[:, 'currentAnswer'] = tools_non_error['currentAnswer'].replace({'no': 'No', 'yes': 'Yes'})
-    tools_non_error = tools_non_error[tools_non_error['currentAnswer'].isin(['Yes', 'No'])]
-    tools_non_error = tools_non_error[tools_non_error['vote'].isin(['Yes', 'No'])]
-    tools_non_error['win'] = (tools_non_error['currentAnswer'] == tools_non_error['vote']).astype(int)
+    tools_non_error = tools_inc[tools_inc["error"] != 1]
+    tools_non_error.loc[:, "currentAnswer"] = tools_non_error["currentAnswer"].replace(
+        {"no": "No", "yes": "Yes"}
+    )
+    tools_non_error = tools_non_error[
+        tools_non_error["currentAnswer"].isin(["Yes", "No"])
+    ]
+    tools_non_error = tools_non_error[tools_non_error["vote"].isin(["Yes", "No"])]
+    tools_non_error["win"] = (
+        tools_non_error["currentAnswer"] == tools_non_error["vote"]
+    ).astype(int)
     tools_non_error.columns = tools_non_error.columns.astype(str)
-    wins = tools_non_error.groupby(['tool', 'request_month_year_week', 'win']).size().unstack().fillna(0)
-    wins['win_perc'] = (wins[1] / (wins[0] + wins[1])) * 100
+    wins = (
+        tools_non_error.groupby(["tool", "request_month_year_week", "win"])
+        .size()
+        .unstack()
+        .fillna(0)
+    )
+    wins["win_perc"] = (wins[1] / (wins[0] + wins[1])) * 100
     wins.reset_index(inplace=True)
-    wins['total_request'] = wins[0] + wins[1]
+    wins["total_request"] = wins[0] + wins[1]
     wins.columns = wins.columns.astype(str)
     # Convert request_month_year_week to string and explicitly set type for Altair
-    wins['request_month_year_week'] = wins['request_month_year_week'].astype(str)
+    wins["request_month_year_week"] = wins["request_month_year_week"].astype(str)
     return wins
 
 
 def get_overall_winning_rate(wins_df: pd.DataFrame) -> pd.DataFrame:
     """Gets the overall winning rate data for the given tools and calculates the winning percentage."""
-    overall_wins = wins_df.groupby('request_month_year_week').agg({
-        "0": 'sum',
-        "1": 'sum',
-        "win_perc": 'mean',
-        "total_request": 'sum'
-    }).rename(columns={"0": 'losses', "1": 'wins'}).reset_index()
+    overall_wins = (
+        wins_df.groupby("request_month_year_week")
+        .agg({"0": "sum", "1": "sum", "win_perc": "mean", "total_request": "sum"})
+        .rename(columns={"0": "losses", "1": "wins"})
+        .reset_index()
+    )
     return overall_wins
 
 
-def plot_tool_winnings_overall(wins_df: pd.DataFrame, winning_selector: str = "win_perc") -> gr.BarPlot:
+def plot_tool_winnings_overall(
+    wins_df: pd.DataFrame, winning_selector: str = "win_perc"
+) -> gr.BarPlot:
     """Plots the overall winning rate data for the given tools and calculates the winning percentage."""
     return gr.BarPlot(
-        title="Winning Rate", 
-        x_title="Date", 
+        title="Winning Rate",
+        x_title="Date",
         y_title=winning_selector,
         show_label=True,
         interactive=True,
@@ -52,23 +65,23 @@ def plot_tool_winnings_overall(wins_df: pd.DataFrame, winning_selector: str = "w
         x="request_month_year_week",
         y=winning_selector,
         height=HEIGHT,
-        width=WIDTH
+        width=WIDTH,
     )
 
 
 def plot_tool_winnings_by_tool(wins_df: pd.DataFrame, tool: str) -> gr.BarPlot:
     """Plots the winning rate data for the given tool."""
     return gr.BarPlot(
-                title="Winning Rate", 
-                x_title="Week", 
-                y_title="Winning Rate", 
-                x="request_month_year_week", 
-                y="win_perc",
-                value=wins_df[wins_df['tool'] == tool],
-                show_label=True,
-                interactive=True,
-                show_actions_button=True,
-                tooltip=["request_month_year_week", "win_perc"],
-                height=HEIGHT,
-                width=WIDTH
-            )
+        title="Winning Rate",
+        x_title="Week",
+        y_title="Winning Rate",
+        x="request_month_year_week",
+        y="win_perc",
+        value=wins_df[wins_df["tool"] == tool],
+        show_label=True,
+        interactive=True,
+        show_actions_button=True,
+        tooltip=["request_month_year_week", "win_perc"],
+        height=HEIGHT,
+        width=WIDTH,
+    )