jstrong
/
data-pipelines

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "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>1531094401700852527</td>\n",
       "      <td>0.0801</td>\n",
       "      <td>bits</td>\n",
       "      <td>6706.6001</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1531094401780298519</td>\n",
       "      <td>0.0284</td>\n",
       "      <td>bits</td>\n",
       "      <td>6706.6099</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1531094402305708472</td>\n",
       "      <td>0.0050</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6707.0000</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1531094403455657797</td>\n",
       "      <td>0.0050</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6706.7002</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1531094403592663872</td>\n",
       "      <td>0.0658</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6705.8999</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  time  amount  exch     price  server_time side   ticker\n",
       "0  1531094401700852527  0.0801  bits 6706.6001            0   na  btc_usd\n",
       "1  1531094401780298519  0.0284  bits 6706.6099            0   na  btc_usd\n",
       "2  1531094402305708472  0.0050  btfx 6707.0000            0   na  btc_usd\n",
       "3  1531094403455657797  0.0050  btfx 6706.7002            0   na  btc_usd\n",
       "4  1531094403592663872  0.0658  btfx 6705.8999            0   na  btc_usd"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('/xfs/trades.csv', nrows=1024 * 1024)\n",
    "df.head()"
   ]
  },
  {
   "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",
       "    <tr>\n",
       "      <th>time</th>\n",
       "      <th></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",
       "      <td>2018-07-09 00:00:01.700852527+00:00</td>\n",
       "      <td>1531094401700852527</td>\n",
       "      <td>0.0801</td>\n",
       "      <td>bits</td>\n",
       "      <td>6706.6001</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2018-07-09 00:00:01.780298519+00:00</td>\n",
       "      <td>1531094401780298519</td>\n",
       "      <td>0.0284</td>\n",
       "      <td>bits</td>\n",
       "      <td>6706.6099</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2018-07-09 00:00:02.305708472+00:00</td>\n",
       "      <td>1531094402305708472</td>\n",
       "      <td>0.0050</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6707.0000</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2018-07-09 00:00:03.455657797+00:00</td>\n",
       "      <td>1531094403455657797</td>\n",
       "      <td>0.0050</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6706.7002</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2018-07-09 00:00:03.592663872+00:00</td>\n",
       "      <td>1531094403592663872</td>\n",
       "      <td>0.0658</td>\n",
       "      <td>btfx</td>\n",
       "      <td>6705.8999</td>\n",
       "      <td>0</td>\n",
       "      <td>na</td>\n",
       "      <td>btc_usd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    time  amount  exch  \\\n",
       "time                                                                     \n",
       "2018-07-09 00:00:01.700852527+00:00  1531094401700852527  0.0801  bits   \n",
       "2018-07-09 00:00:01.780298519+00:00  1531094401780298519  0.0284  bits   \n",
       "2018-07-09 00:00:02.305708472+00:00  1531094402305708472  0.0050  btfx   \n",
       "2018-07-09 00:00:03.455657797+00:00  1531094403455657797  0.0050  btfx   \n",
       "2018-07-09 00:00:03.592663872+00:00  1531094403592663872  0.0658  btfx   \n",
       "\n",
       "                                        price  server_time side   ticker  \n",
       "time                                                                      \n",
       "2018-07-09 00:00:01.700852527+00:00 6706.6001            0   na  btc_usd  \n",
       "2018-07-09 00:00:01.780298519+00:00 6706.6099            0   na  btc_usd  \n",
       "2018-07-09 00:00:02.305708472+00:00 6707.0000            0   na  btc_usd  \n",
       "2018-07-09 00:00:03.455657797+00:00 6706.7002            0   na  btc_usd  \n",
       "2018-07-09 00:00:03.592663872+00:00 6705.8999            0   na  btc_usd  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.index = pd.to_datetime(df['time'], utc=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Timestamp('2018-07-09 00:00:01.700852527+0000', tz='UTC'),\n",
       " Timestamp('2018-07-11 19:27:34.453569864+0000', tz='UTC'),\n",
       " Timedelta('2 days 19:27:32.752717'))"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.index[0], df.index[-1], df.index[-1] - df.index[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.000578250137079"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start = \"2018-07-10T04:00:00Z\" # <- randomly selected start/end \n",
    "end   = \"2018-07-10T05:00:00Z\" #    important point is, 1h span\n",
    "\n",
    "target_hr = (df.index >= start) & (df.index < end)\n",
    "assert target_hr.sum() > 0\n",
    "\n",
    "of_btcusd = df['ticker'] == 'btc_usd'\n",
    "assert of_btcusd.sum() > 0\n",
    "\n",
    "of_bmex = df['exch'] == 'bmex'\n",
    "of_gdax = df['exch'] == 'gdax'\n",
    "\n",
    "assert of_bmex.sum() > 0\n",
    "assert of_gdax.sum() > 0\n",
    "\n",
    "bmex_hr = df.loc[target_hr & of_bmex & of_btcusd, ['price', 'amount']]\n",
    "gdax_hr = df.loc[target_hr & of_gdax & of_btcusd, ['price', 'amount']]\n",
    "\n",
    "bmex_size_wt_price = (\n",
    "    (bmex_hr['price'] * bmex_hr['amount']).sum()\n",
    "    / bmex_hr['amount'].sum()\n",
    ")\n",
    "\n",
    "gdax_size_wt_price = (\n",
    "    (gdax_hr['price'] * gdax_hr['amount']).sum()\n",
    "    / gdax_hr['amount'].sum()\n",
    ")\n",
    "\n",
    "ratio = bmex_size_wt_price / gdax_size_wt_price # <- final answer (for start,end hr at least)\n",
    "ratio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((2714, 2), (1305, 2))"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bmex_hr.shape, gdax_hr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6642.42451802828, 6638.585754905495)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bmex_size_wt_price, gdax_size_wt_price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}