signal_confirmation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n"
     ]
    }
   ],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "%matplotlib inline\n",
    "from pprint import pprint\n",
    "from IPython.display import display"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pylab as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "transformed OHLCV at frequency 1D\n",
      "reading cache of TXF in 1D OHLCV\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/cyyen/miniconda3/envs/stock_path_tracker/lib/python3.8/site-packages/pandas/core/groupby/groupby.py:980: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n",
      "of pandas will change to not sort by default.\n",
      "\n",
      "To accept the future behavior, pass 'sort=False'.\n",
      "\n",
      "To retain the current behavior and silence the warning, pass 'sort=True'.\n",
      "\n",
      "  result = concat(values, axis=self.axis, keys=keys)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Score: 0.5983086680761099\n",
      "Confusion Matrix:\n"
     ]
    },
    {
     "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>Negative</th>\n",
       "      <th>Positve</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>False</th>\n",
       "      <td>262</td>\n",
       "      <td>189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>True</th>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Negative  Positve\n",
       "False       262      189\n",
       "True          1       21"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Area Under Curve: 0.7677383592017739\n",
      "Recall score: 0.9545454545454546\n"
     ]
    }
   ],
   "source": [
    "from model_logistic_regression import y, X, idx, num_test\n",
    "from model_logistic_regression import scaler, model\n",
    "from turnpt_analysis import get_daily_TXF_OHLC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_scaled = scaler.transform(X)\n",
    "X_, y_, idx_ = X_scaled[-num_test:], y[-num_test:], idx[-num_test:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 0., 1., 1., 1., 1., 0., 0., 0., 1., 1., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 0., 0., 0., 1., 1., 1., 1., 0., 0., 1., 0., 1., 1., 0., 1.,\n",
       "       1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 0., 0., 0., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 0., 0., 1., 1., 1., 1., 0., 0., 0., 1., 1., 1., 0., 0., 0.,\n",
       "       0., 1., 0., 1., 0., 0., 1., 1., 0., 0., 0., 0., 0., 0., 0., 1., 1.,\n",
       "       1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 0., 1., 1., 1., 0.,\n",
       "       1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1.,\n",
       "       0., 0., 0., 1., 1., 0., 0., 0., 1., 0., 1., 1., 1., 1., 1., 1., 0.,\n",
       "       0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1.,\n",
       "       0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 0., 0., 0.,\n",
       "       0., 0., 0., 1., 1., 1., 1., 1., 0., 1., 1., 1., 1., 0., 1., 1., 0.,\n",
       "       0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "       1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 0., 1., 1., 0.,\n",
       "       1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 0., 0., 0., 0., 1., 0., 1., 0., 1., 1., 1., 0., 1., 1., 0.,\n",
       "       0., 1., 1., 0., 0., 0., 0., 0., 0., 1., 1., 0., 1., 1., 1., 1., 1.,\n",
       "       1., 0., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 0., 0.,\n",
       "       1., 1., 1., 0., 1., 1., 1., 0., 0., 0., 0., 0., 1., 1., 1., 0., 1.,\n",
       "       1., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 1., 1., 1., 1., 0., 0.,\n",
       "       0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1.,\n",
       "       1., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 1., 0.,\n",
       "       0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
       "       0., 1., 1., 0., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 0., 1., 0., 0., 0., 0., 1., 1., 0., 1., 0., 0., 0., 0., 0., 0.,\n",
       "       0., 1., 1., 1., 1., 1., 0., 0., 1., 1., 1., 0., 1., 1., 1., 1., 1.,\n",
       "       1., 0., 0., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0.])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "signal = model.predict(X_)\n",
    "signal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_position(df, holding_days=5):\n",
    "    df['exit'] = 0\n",
    "    df['exit_at'] = np.nan\n",
    "    df['exit_at'] = np.where((df.enter == 1) & (df.p0 > df.p5), 'p5', df.exit_at)# NOTE: order is important\n",
    "    df['exit_at'] = np.where((df.enter == 1) & (df.p0 > df.p4), 'p4', df.exit_at)\n",
    "    df['exit_at'] = np.where((df.enter == 1) & (df.p0 > df.p3), 'p3', df.exit_at)\n",
    "    df['exit_at'] = np.where((df.enter == 1) & (df.p0 > df.p2), 'p2', df.exit_at)\n",
    "    df['exit_at'] = np.where((df.enter == 1) & (df.p0 > df.p1), 'p1', 'p_holding')\n",
    "    assert df.exit_at.isna().sum() == 0\n",
    "    \n",
    "    df['prc_exit'] = np.nan\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p5', df.p5, df.prc_exit)\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p4', df.p4, df.prc_exit)\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p3', df.p3, df.prc_exit)\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p2', df.p2, df.prc_exit)\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p1', df.p1, df.prc_exit)\n",
    "    df['prc_exit'] = np.where(df.exit_at == 'p_holding', df.p0.shift(-holding_days), df.prc_exit)\n",
    "    \n",
    "    days_enter = df.query('enter == 1').index\n",
    "    nrows = df.shape[0]\n",
    "    for idx_row in range(nrows):\n",
    "        dt, row = df.index[idx_row], df.iloc[idx_row]\n",
    "        if dt in days_enter:\n",
    "            if row.exit_at == 'p_holding':\n",
    "                idx_exit = idx_row+holding_days\n",
    "            elif row.exit_at == 'p1':\n",
    "                idx_exit = idx_row+1\n",
    "            elif row.exit_at == 'p2':\n",
    "                idx_exit = idx_row+2\n",
    "            elif row.exit_at == 'p3':\n",
    "                idx_exit = idx_row+3\n",
    "            elif row.exit_at == 'p4':\n",
    "                idx_exit = idx_row+4\n",
    "                \n",
    "            elif row.exit_at == 'p5':\n",
    "                idx_exit = idx_row+5\n",
    "    \n",
    "            else:\n",
    "                raise ValueError(f'There is no such exit_at code: {row.exit_at}')\n",
    "                \n",
    "            \n",
    "            if idx_exit <= nrows-1:\n",
    "                dt_exit = df.index[idx_exit]\n",
    "                df.loc[dt_exit, 'exit'] += 1\n",
    "\n",
    "    buy = df.enter.cumsum()\n",
    "    sell = df.exit.cumsum()\n",
    "    df['position'] = buy - sell\n",
    "    return df\n",
    "\n",
    "\n",
    "def get_df_action(dt_includes, signal, holding_days):\n",
    "    df = (\n",
    "        get_daily_TXF_OHLC().\n",
    "        set_index('tx_datetime').loc[:, ['close']].\n",
    "        query('index in @idx_').\n",
    "        assign(signal = signal, \n",
    "               signal_true = y_).\n",
    "        assign(p0 = lambda x: x.close,\n",
    "               p_1 = lambda x: x.close.shift(1), p_2 = lambda x: x.close.shift(2), p_3 = lambda x: x.close.shift(3), p_4 = lambda x: x.close.shift(4), p_5 = lambda x: x.close.shift(5),\n",
    "               p1 = lambda x: x.close.shift(-1), p2 = lambda x: x.close.shift(-2), p3 = lambda x: x.close.shift(-3), p4 = lambda x: x.close.shift(-4), p5 = lambda x: x.close.shift(-5),).\n",
    "        dropna().\n",
    "        assign(enter = lambda x: np.where(x[['p0', 'p_1', 'p_2', 'p_3', 'p_4', 'p_5']].idxmin(axis=1) == 'p0', x.signal, 0)).\n",
    "        pipe(get_position, holding_days = holding_days).\n",
    "        assign(action = lambda x: x.position.diff().fillna(x.iloc[0].position))\n",
    "    )\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "transformed OHLCV at frequency 1D\n",
      "reading cache of TXF in 1D OHLCV\n"
     ]
    },
    {
     "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>signal_true</th>\n",
       "      <th>signal</th>\n",
       "      <th>enter</th>\n",
       "      <th>exit_at</th>\n",
       "      <th>position</th>\n",
       "      <th>action</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tx_datetime</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-03-03</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-06</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-07</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-08</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-09</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-10</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-13</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-14</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-15</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-16</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-17</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-20</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-21</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-22</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-03-23</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>p_holding</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             signal_true  signal  enter    exit_at  position  action\n",
       "tx_datetime                                                         \n",
       "2017-03-03           0.0     1.0    1.0  p_holding       1.0     1.0\n",
       "2017-03-06           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-07           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-08           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-09           0.0     1.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-10           1.0     1.0    1.0  p_holding       1.0     0.0\n",
       "2017-03-13           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-14           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-15           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-16           0.0     0.0    0.0  p_holding       1.0     0.0\n",
       "2017-03-17           0.0     0.0    0.0  p_holding       0.0    -1.0\n",
       "2017-03-20           0.0     0.0    0.0  p_holding       0.0     0.0\n",
       "2017-03-21           0.0     0.0    0.0  p_holding       0.0     0.0\n",
       "2017-03-22           0.0     0.0    0.0  p_holding       0.0     0.0\n",
       "2017-03-23           0.0     0.0    0.0  p_holding       0.0     0.0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>signal_true</th>\n",
       "      <th>signal</th>\n",
       "      <th>signal_enter</th>\n",
       "      <th>signal_t1</th>\n",
       "      <th>signal_t2</th>\n",
       "      <th>signal_t3</th>\n",
       "      <th>signal_t4</th>\n",
       "      <th>signal_t5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>signal_true</th>\n",
       "      <td>1.00</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal</th>\n",
       "      <td>0.28</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.62</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_enter</th>\n",
       "      <td>0.42</td>\n",
       "      <td>0.62</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.71</td>\n",
       "      <td>0.71</td>\n",
       "      <td>0.71</td>\n",
       "      <td>0.71</td>\n",
       "      <td>0.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_t1</th>\n",
       "      <td>0.61</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.71</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_t2</th>\n",
       "      <td>0.61</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.71</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_t3</th>\n",
       "      <td>0.61</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.71</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_t4</th>\n",
       "      <td>0.61</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.71</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>signal_t5</th>\n",
       "      <td>0.61</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.71</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              signal_true  signal  signal_enter  signal_t1  signal_t2  \\\n",
       "signal_true          1.00    0.28          0.42       0.61       0.61   \n",
       "signal               0.28    1.00          0.62       0.44       0.44   \n",
       "signal_enter         0.42    0.62          1.00       0.71       0.71   \n",
       "signal_t1            0.61    0.44          0.71       1.00       1.00   \n",
       "signal_t2            0.61    0.44          0.71       1.00       1.00   \n",
       "signal_t3            0.61    0.44          0.71       1.00       1.00   \n",
       "signal_t4            0.61    0.44          0.71       1.00       1.00   \n",
       "signal_t5            0.61    0.44          0.71       1.00       1.00   \n",
       "\n",
       "              signal_t3  signal_t4  signal_t5  \n",
       "signal_true        0.61       0.61       0.61  \n",
       "signal             0.44       0.44       0.44  \n",
       "signal_enter       0.71       0.71       0.71  \n",
       "signal_t1          1.00       1.00       1.00  \n",
       "signal_t2          1.00       1.00       1.00  \n",
       "signal_t3          1.00       1.00       1.00  \n",
       "signal_t4          1.00       1.00       1.00  \n",
       "signal_t5          1.00       1.00       1.00  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "if __name__ == '__main__':\n",
    "    holding_days = 5\n",
    "    df_action = get_df_action(idx_, signal, holding_days)\n",
    "    display(df_action.head(15).loc[:, ['signal_true', 'signal', 'enter', 'exit_at', 'position', 'action']])\n",
    "    \n",
    "    # correlation\n",
    "    df_signal_confirmed = (\n",
    "        df_action.\n",
    "        assign(signal_enter = lambda x: x.enter == 1,\n",
    "               signal_t1 = lambda x: ((x.enter == 1) & (~x.exit_at.isin(['p1']))).astype(int),\n",
    "               signal_t2 = lambda x: ((x.enter == 1) & (~x.exit_at.isin(['p1', 'p2']))).astype(int),\n",
    "               signal_t3 = lambda x: ((x.enter == 1) & (~x.exit_at.isin(['p1', 'p2', 'p3']))).astype(int),\n",
    "               signal_t4 = lambda x: ((x.enter == 1) & (~x.exit_at.isin(['p1', 'p2', 'p3', 'p4']))).astype(int),\n",
    "               signal_t5 = lambda x: ((x.enter == 1) & (~x.exit_at.isin(['p1', 'p2', 'p3', 'p4', 'p5']))).astype(int)).\n",
    "        loc[:, ['signal_true', 'signal', 'signal_enter', 'signal_t1', 'signal_t2', 'signal_t3', 'signal_t4', 'signal_t5']]\n",
    "    )\n",
    "    display(round(df_signal_confirmed.corr(), 2))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "jupytext": {
   "formats": "ipynb,py:percent"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}