Adding filter for invalid markets for trades stats

notebooks/markets_analysis.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -167,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -176,301 +176,137 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "27707"
+       "is_invalid\n",
+       "False    23830\n",
+       "True      3877\n",
+       "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "len(all_trades)"
+    "all_trades.is_invalid.value_counts()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "127674"
+       "24722"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "len(tools)"
+    "mask = (all_trades[\"is_invalid\"] & all_trades[\"redeemed\"])\n",
+    "filtered_trades = all_trades[~mask]\n",
+    "len(filtered_trades)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "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  "
+       "27707"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "all_trades.head()"
+    "len(all_trades)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "24722"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(filtered_trades)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "winning_trade\n",
-       "False    14574\n",
        "True     13133\n",
+       "False    11589\n",
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "all_trades.winning_trade.value_counts()"
+    "filtered_trades.winning_trade.value_counts()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/gp/02mb1d514ng739czlxw1lhh00000gn/T/ipykernel_82376/982645160.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  filtered_trades[\"creation_timestamp\"] = pd.to_datetime(filtered_trades[\"creation_timestamp\"])\n"
+     ]
+    }
+   ],
    "source": [
-    "all_trades[\"creation_timestamp\"] = pd.to_datetime(all_trades[\"creation_timestamp\"])"
+    "filtered_trades[\"creation_timestamp\"] = pd.to_datetime(filtered_trades[\"creation_timestamp\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -479,17 +315,17 @@
        "current_answer\n",
        " 1    13016\n",
        " 0    10814\n",
-       "-1     3877\n",
+       "-1      892\n",
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "all_trades.current_answer.value_counts()"
+    "filtered_trades.current_answer.value_counts()"
    ]
   },
   {

scripts/profitability.py

@@ -617,6 +617,10 @@ def run_profitability_analysis(rpc):
     print("Analysing trades...")
     all_trades_df = analyse_all_traders(fpmmTrades, tools)
 
+    # filter invalid markets. Condition: "redeemed" and "is_invalid" are True
+    invalid_market_mask = all_trades_df["is_invalid"] & all_trades_df["redeemed"]
+    all_trades_df = all_trades_df[~invalid_market_mask]
+
     # summarize profitability df
     print("Summarising trades...")
     summary_df = summary_analyse(all_trades_df)