jstrong
/
data-pipelines

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1min 8s, sys: 7.72 s, total: 1min 16s\n",
      "Wall time: 1min 16s\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 92331988 entries, 0 to 92331987\n",
      "Data columns (total 7 columns):\n",
      "time           int64\n",
      "amount         float64\n",
      "exch           object\n",
      "price          float64\n",
      "server_time    int64\n",
      "side           object\n",
      "ticker         object\n",
      "dtypes: float64(2), int64(2), object(3)\n",
      "memory usage: 4.8+ GB\n"
     ]
    }
   ],
   "source": [
    "%time df = pd.read_csv('/xfs/sample.csv')\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>time</th>\n",
       "      <th>amount</th>\n",
       "      <th>exch</th>\n",
       "      <th>price</th>\n",
       "      <th>server_time</th>\n",
       "      <th>side</th>\n",
       "      <th>ticker</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1561939200002479372</td>\n",
       "      <td>1.4894</td>\n",
       "      <td>bnce</td>\n",
       "      <td>292.7000</td>\n",
       "      <td>1561939199919000064</td>\n",
       "      <td>NaN</td>\n",
       "      <td>eth_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1561939200011035644</td>\n",
       "      <td>0.0833</td>\n",
       "      <td>btfx</td>\n",
       "      <td>10809.0000</td>\n",
       "      <td>1561939199927000064</td>\n",
       "      <td>bid</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1561939200011055712</td>\n",
       "      <td>0.8333</td>\n",
       "      <td>btfx</td>\n",
       "      <td>10809.0000</td>\n",
       "      <td>1561939199927000064</td>\n",
       "      <td>bid</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1561939200019037617</td>\n",
       "      <td>0.0831</td>\n",
       "      <td>bnce</td>\n",
       "      <td>10854.1000</td>\n",
       "      <td>1561939199935000064</td>\n",
       "      <td>NaN</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1561939200026450471</td>\n",
       "      <td>0.1250</td>\n",
       "      <td>okex</td>\n",
       "      <td>123.2100</td>\n",
       "      <td>1561939200026450432</td>\n",
       "      <td>ask</td>\n",
       "      <td>ltc_usd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  time  amount  exch      price          server_time side  \\\n",
       "0  1561939200002479372  1.4894  bnce   292.7000  1561939199919000064  NaN   \n",
       "1  1561939200011035644  0.0833  btfx 10809.0000  1561939199927000064  bid   \n",
       "2  1561939200011055712  0.8333  btfx 10809.0000  1561939199927000064  bid   \n",
       "3  1561939200019037617  0.0831  bnce 10854.1000  1561939199935000064  NaN   \n",
       "4  1561939200026450471  0.1250  okex   123.2100  1561939200026450432  ask   \n",
       "\n",
       "    ticker  \n",
       "0  eth_usd  \n",
       "1  btc_usd  \n",
       "2  btc_usd  \n",
       "3  btc_usd  \n",
       "4  ltc_usd  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(True, True, True)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SECOND = int(1e9)\n",
    "\n",
    "example_time = 1567295920000000000\n",
    "\n",
    "last_5min = (df['time'] > example_time - SECOND * 60 * 5) & (df['time'] <= example_time)\n",
    "last_15min = (df['time'] > example_time - SECOND * 60 * 15) & (df['time'] <= example_time)\n",
    "last_60min = (df['time'] > example_time - SECOND * 60 * 60) & (df['time'] <= example_time)\n",
    "of_btc_usd = df['ticker'] == 'btc_usd'\n",
    "of_gdax = df['exch'] == 'gdax'\n",
    "of_bmex = df['exch'] == 'bmex'\n",
    "\n",
    "g5 = last_5min & of_btc_usd & of_gdax\n",
    "b5 = last_5min & of_btc_usd & of_bmex\n",
    "g15 = last_15min & of_btc_usd & of_gdax\n",
    "b15 = last_15min & of_btc_usd & of_bmex\n",
    "g60 = last_60min & of_btc_usd & of_gdax\n",
    "b60 = last_60min & of_btc_usd & of_bmex\n",
    "\n",
    "ratio_5min = ((df.loc[b5, 'price'] * df.loc[b5, 'amount']).sum() / df.loc[b5, 'amount'].sum()) / ((df.loc[g5, 'price'] * df.loc[g5, 'amount']).sum() / df.loc[g5, 'amount'].sum())\n",
    "ratio_15min = ((df.loc[b15, 'price'] * df.loc[b15, 'amount']).sum() / df.loc[b15, 'amount'].sum()) / ((df.loc[g15, 'price'] * df.loc[g15, 'amount']).sum() / df.loc[g15, 'amount'].sum())\n",
    "ratio_60min = ((df.loc[b60, 'price'] * df.loc[b60, 'amount']).sum() / df.loc[b60, 'amount'].sum()) / ((df.loc[g60, 'price'] * df.loc[g60, 'amount']).sum() / df.loc[g60, 'amount'].sum())\n",
    "\n",
    "abs(ratio_5min - 1.000474060563638) < 1e-6, abs(ratio_15min - 1.0005019306061411) < 1e-6, abs(ratio_60min - 1.0002338013889658) < 1e-6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>time</th>\n",
       "      <th>last</th>\n",
       "      <th>bmex_5min</th>\n",
       "      <th>gdax_5min</th>\n",
       "      <th>n_bmex_p5</th>\n",
       "      <th>n_gdax_p5</th>\n",
       "      <th>r5</th>\n",
       "      <th>r15</th>\n",
       "      <th>r60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1561939210000000000</td>\n",
       "      <td>10758.5800</td>\n",
       "      <td>10760.7205</td>\n",
       "      <td>10760.4593</td>\n",
       "      <td>22</td>\n",
       "      <td>28</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>1.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1561939220000000000</td>\n",
       "      <td>10770.0000</td>\n",
       "      <td>10763.6811</td>\n",
       "      <td>10761.2528</td>\n",
       "      <td>230</td>\n",
       "      <td>75</td>\n",
       "      <td>1.0002</td>\n",
       "      <td>1.0002</td>\n",
       "      <td>1.0002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1561939230000000000</td>\n",
       "      <td>10758.0100</td>\n",
       "      <td>10761.8843</td>\n",
       "      <td>10760.1596</td>\n",
       "      <td>418</td>\n",
       "      <td>120</td>\n",
       "      <td>1.0002</td>\n",
       "      <td>1.0002</td>\n",
       "      <td>1.0002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1561939240000000000</td>\n",
       "      <td>10752.5000</td>\n",
       "      <td>10757.6829</td>\n",
       "      <td>10760.3630</td>\n",
       "      <td>507</td>\n",
       "      <td>147</td>\n",
       "      <td>0.9998</td>\n",
       "      <td>0.9998</td>\n",
       "      <td>0.9998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1561939250000000000</td>\n",
       "      <td>10772.6900</td>\n",
       "      <td>10757.5702</td>\n",
       "      <td>10763.0840</td>\n",
       "      <td>537</td>\n",
       "      <td>191</td>\n",
       "      <td>0.9995</td>\n",
       "      <td>0.9995</td>\n",
       "      <td>0.9995</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  time       last  bmex_5min  gdax_5min  n_bmex_p5  n_gdax_p5  \\\n",
       "0  1561939210000000000 10758.5800 10760.7205 10760.4593         22         28   \n",
       "1  1561939220000000000 10770.0000 10763.6811 10761.2528        230         75   \n",
       "2  1561939230000000000 10758.0100 10761.8843 10760.1596        418        120   \n",
       "3  1561939240000000000 10752.5000 10757.6829 10760.3630        507        147   \n",
       "4  1561939250000000000 10772.6900 10757.5702 10763.0840        537        191   \n",
       "\n",
       "      r5    r15    r60  \n",
       "0 1.0000 1.0000 1.0000  \n",
       "1 1.0002 1.0002 1.0002  \n",
       "2 1.0002 1.0002 1.0002  \n",
       "3 0.9998 0.9998 0.9998  \n",
       "4 0.9995 0.9995 0.9995  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ref = pd.read_csv('../var/hard.csv')\n",
    "ref.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1567295750000000000, 1567295760000000000, 1567295770000000000, 1567295780000000000, 1567295790000000000, 1567295800000000000, 1567295810000000000, 1567295820000000000, 1567295830000000000,\n",
       "       1567295840000000000, 1567295850000000000, 1567295860000000000, 1567295870000000000, 1567295880000000000, 1567295890000000000, 1567295900000000000, 1567295910000000000, 1567295920000000000,\n",
       "       1567295930000000000, 1567295940000000000, 1567295950000000000, 1567295960000000000, 1567295970000000000, 1567295980000000000, 1567295990000000000])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ref['time'].tail(25).values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "finished in 487.8sec\n"
     ]
    }
   ],
   "source": [
    "import time\n",
    "\n",
    "start = time.time()\n",
    "rows = []\n",
    "\n",
    "for example_time in ref['time'].tail(25).values:\n",
    "    last_5min = (df['time'] > example_time - SECOND * 60 * 5) & (df['time'] <= example_time)\n",
    "    last_15min = (df['time'] > example_time - SECOND * 60 * 15) & (df['time'] <= example_time)\n",
    "    last_60min = (df['time'] > example_time - SECOND * 60 * 60) & (df['time'] <= example_time)\n",
    "    of_btc_usd = df['ticker'] == 'btc_usd'\n",
    "    of_gdax = df['exch'] == 'gdax'\n",
    "    of_bmex = df['exch'] == 'bmex'\n",
    "\n",
    "    g5 = last_5min & of_btc_usd & of_gdax\n",
    "    b5 = last_5min & of_btc_usd & of_bmex\n",
    "    g15 = last_15min & of_btc_usd & of_gdax\n",
    "    b15 = last_15min & of_btc_usd & of_bmex\n",
    "    g60 = last_60min & of_btc_usd & of_gdax\n",
    "    b60 = last_60min & of_btc_usd & of_bmex\n",
    "\n",
    "    ratio_5min = ((df.loc[b5, 'price'] * df.loc[b5, 'amount']).sum() / df.loc[b5, 'amount'].sum()) / ((df.loc[g5, 'price'] * df.loc[g5, 'amount']).sum() / df.loc[g5, 'amount'].sum())\n",
    "    ratio_15min = ((df.loc[b15, 'price'] * df.loc[b15, 'amount']).sum() / df.loc[b15, 'amount'].sum()) / ((df.loc[g15, 'price'] * df.loc[g15, 'amount']).sum() / df.loc[g15, 'amount'].sum())\n",
    "    ratio_60min = ((df.loc[b60, 'price'] * df.loc[b60, 'amount']).sum() / df.loc[b60, 'amount'].sum()) / ((df.loc[g60, 'price'] * df.loc[g60, 'amount']).sum() / df.loc[g60, 'amount'].sum())\n",
    "    rows.append(dict(example_time=example_time, r5=ratio_5min, r15=ratio_15min, r60=ratio_60min))\n",
    "    \n",
    "took = time.time() - start\n",
    "print('finished in {:.1f}sec'.format(took))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.342554545733013"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hypothetical_full_took = (took / 25) * 5401808\n",
    "hypothetical_full_took / 60 / 60 / 24 / 365"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.1016643329480867"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "92331988 / 908204336"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "19.513984975814818"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "took / 25"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('105,410,800.2', 105410800.15423629)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'{:,.1f}'.format(hypothetical_full_took), hypothetical_full_took"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "r5_delta     0.000000000002368\n",
       "r15_delta    0.000000000010704\n",
       "r60_delta    0.000000000005513\n",
       "dtype: object"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(pd.DataFrame(rows).join(ref.set_index('time'), on='example_time', rsuffix='_rust')\n",
    " .assign(r5_delta=lambda df: abs(df['r5'] - df['r5_rust']))\n",
    " .assign(r15_delta=lambda df: abs(df['r15'] - df['r15_rust']))\n",
    " .assign(r60_delta=lambda df: abs(df['r60'] - df['r60_rust']))\n",
    ")[['r5_delta','r15_delta','r60_delta']].max(axis=0).map(lambda x: '{:.15f}'.format(x))"
   ]
  }
 ],
 "metadata": {
  "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}