jstrong
/
data-pipelines
1
0
Fork 0
Code Issues 0 Pull Requests 0 Releases 2 Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
26 Commits
1 Branch
318KB
Tree: d196fc4710
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd196fc4710'
${ noResults }
data-pipelines/notebooks/verifying-hard-query-output...

515 lines
16KB
Raw Blame History 

  1. {

  2.  "cells": [

  3.   {

  4.    "cell_type": "code",

  5.    "execution_count": 1,

  6.    "metadata": {},

  7.    "outputs": [

  8.     {

  9.      "name": "stdout",

  10.      "output_type": "stream",

  11.      "text": [

  12.       "CPU times: user 1min 8s, sys: 7.72 s, total: 1min 16s\n",

  13.       "Wall time: 1min 16s\n",

  14.       "<class 'pandas.core.frame.DataFrame'>\n",

  15.       "RangeIndex: 92331988 entries, 0 to 92331987\n",

  16.       "Data columns (total 7 columns):\n",

  17.       "time           int64\n",

  18.       "amount         float64\n",

  19.       "exch           object\n",

  20.       "price          float64\n",

  21.       "server_time    int64\n",

  22.       "side           object\n",

  23.       "ticker         object\n",

  24.       "dtypes: float64(2), int64(2), object(3)\n",

  25.       "memory usage: 4.8+ GB\n"

  26.      ]

  27.     }

  28.    ],

  29.    "source": [

  30.     "%time df = pd.read_csv('/xfs/sample.csv')\n",

  31.     "df.info()"

  32.    ]

  33.   },

  34.   {

  35.    "cell_type": "code",

  36.    "execution_count": 2,

  37.    "metadata": {},

  38.    "outputs": [

  39.     {

  40.      "data": {

  41.       "text/html": [

  42.        "<div>\n",

  43.        "<style scoped>\n",

  44.        "    .dataframe tbody tr th:only-of-type {\n",

  45.        "        vertical-align: middle;\n",

  46.        "    }\n",

  47.        "\n",

  48.        "    .dataframe tbody tr th {\n",

  49.        "        vertical-align: top;\n",

  50.        "    }\n",

  51.        "\n",

  52.        "    .dataframe thead th {\n",

  53.        "        text-align: right;\n",

  54.        "    }\n",

  55.        "</style>\n",

  56.        "<table border=\"1\" class=\"dataframe\">\n",

  57.        "  <thead>\n",

  58.        "    <tr style=\"text-align: right;\">\n",

  59.        "      <th></th>\n",

  60.        "      <th>time</th>\n",

  61.        "      <th>amount</th>\n",

  62.        "      <th>exch</th>\n",

  63.        "      <th>price</th>\n",

  64.        "      <th>server_time</th>\n",

  65.        "      <th>side</th>\n",

  66.        "      <th>ticker</th>\n",

  67.        "    </tr>\n",

  68.        "  </thead>\n",

  69.        "  <tbody>\n",

  70.        "    <tr>\n",

  71.        "      <td>0</td>\n",

  72.        "      <td>1561939200002479372</td>\n",

  73.        "      <td>1.4894</td>\n",

  74.        "      <td>bnce</td>\n",

  75.        "      <td>292.7000</td>\n",

  76.        "      <td>1561939199919000064</td>\n",

  77.        "      <td>NaN</td>\n",

  78.        "      <td>eth_usd</td>\n",

  79.        "    </tr>\n",

  80.        "    <tr>\n",

  81.        "      <td>1</td>\n",

  82.        "      <td>1561939200011035644</td>\n",

  83.        "      <td>0.0833</td>\n",

  84.        "      <td>btfx</td>\n",

  85.        "      <td>10809.0000</td>\n",

  86.        "      <td>1561939199927000064</td>\n",

  87.        "      <td>bid</td>\n",

  88.        "      <td>btc_usd</td>\n",

  89.        "    </tr>\n",

  90.        "    <tr>\n",

  91.        "      <td>2</td>\n",

  92.        "      <td>1561939200011055712</td>\n",

  93.        "      <td>0.8333</td>\n",

  94.        "      <td>btfx</td>\n",

  95.        "      <td>10809.0000</td>\n",

  96.        "      <td>1561939199927000064</td>\n",

  97.        "      <td>bid</td>\n",

  98.        "      <td>btc_usd</td>\n",

  99.        "    </tr>\n",

  100.        "    <tr>\n",

  101.        "      <td>3</td>\n",

  102.        "      <td>1561939200019037617</td>\n",

  103.        "      <td>0.0831</td>\n",

  104.        "      <td>bnce</td>\n",

  105.        "      <td>10854.1000</td>\n",

  106.        "      <td>1561939199935000064</td>\n",

  107.        "      <td>NaN</td>\n",

  108.        "      <td>btc_usd</td>\n",

  109.        "    </tr>\n",

  110.        "    <tr>\n",

  111.        "      <td>4</td>\n",

  112.        "      <td>1561939200026450471</td>\n",

  113.        "      <td>0.1250</td>\n",

  114.        "      <td>okex</td>\n",

  115.        "      <td>123.2100</td>\n",

  116.        "      <td>1561939200026450432</td>\n",

  117.        "      <td>ask</td>\n",

  118.        "      <td>ltc_usd</td>\n",

  119.        "    </tr>\n",

  120.        "  </tbody>\n",

  121.        "</table>\n",

  122.        "</div>"

  123.       ],

  124.       "text/plain": [

  125.        "                  time  amount  exch      price          server_time side  \\\n",

  126.        "0  1561939200002479372  1.4894  bnce   292.7000  1561939199919000064  NaN   \n",

  127.        "1  1561939200011035644  0.0833  btfx 10809.0000  1561939199927000064  bid   \n",

  128.        "2  1561939200011055712  0.8333  btfx 10809.0000  1561939199927000064  bid   \n",

  129.        "3  1561939200019037617  0.0831  bnce 10854.1000  1561939199935000064  NaN   \n",

  130.        "4  1561939200026450471  0.1250  okex   123.2100  1561939200026450432  ask   \n",

  131.        "\n",

  132.        "    ticker  \n",

  133.        "0  eth_usd  \n",

  134.        "1  btc_usd  \n",

  135.        "2  btc_usd  \n",

  136.        "3  btc_usd  \n",

  137.        "4  ltc_usd  "

  138.       ]

  139.      },

  140.      "execution_count": 2,

  141.      "metadata": {},

  142.      "output_type": "execute_result"

  143.     }

  144.    ],

  145.    "source": [

  146.     "df.head()"

  147.    ]

  148.   },

  149.   {

  150.    "cell_type": "code",

  151.    "execution_count": 7,

  152.    "metadata": {},

  153.    "outputs": [

  154.     {

  155.      "data": {

  156.       "text/plain": [

  157.        "(True, True, True)"

  158.       ]

  159.      },

  160.      "execution_count": 7,

  161.      "metadata": {},

  162.      "output_type": "execute_result"

  163.     }

  164.    ],

  165.    "source": [

  166.     "SECOND = int(1e9)\n",

  167.     "\n",

  168.     "example_time = 1567295920000000000\n",

  169.     "\n",

  170.     "last_5min = (df['time'] > example_time - SECOND * 60 * 5) & (df['time'] <= example_time)\n",

  171.     "last_15min = (df['time'] > example_time - SECOND * 60 * 15) & (df['time'] <= example_time)\n",

  172.     "last_60min = (df['time'] > example_time - SECOND * 60 * 60) & (df['time'] <= example_time)\n",

  173.     "of_btc_usd = df['ticker'] == 'btc_usd'\n",

  174.     "of_gdax = df['exch'] == 'gdax'\n",

  175.     "of_bmex = df['exch'] == 'bmex'\n",

  176.     "\n",

  177.     "g5 = last_5min & of_btc_usd & of_gdax\n",

  178.     "b5 = last_5min & of_btc_usd & of_bmex\n",

  179.     "g15 = last_15min & of_btc_usd & of_gdax\n",

  180.     "b15 = last_15min & of_btc_usd & of_bmex\n",

  181.     "g60 = last_60min & of_btc_usd & of_gdax\n",

  182.     "b60 = last_60min & of_btc_usd & of_bmex\n",

  183.     "\n",

  184.     "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",

  185.     "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",

  186.     "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",

  187.     "\n",

  188.     "abs(ratio_5min - 1.000474060563638) < 1e-6, abs(ratio_15min - 1.0005019306061411) < 1e-6, abs(ratio_60min - 1.0002338013889658) < 1e-6"

  189.    ]

  190.   },

  191.   {

  192.    "cell_type": "code",

  193.    "execution_count": 8,

  194.    "metadata": {},

  195.    "outputs": [

  196.     {

  197.      "data": {

  198.       "text/html": [

  199.        "<div>\n",

  200.        "<style scoped>\n",

  201.        "    .dataframe tbody tr th:only-of-type {\n",

  202.        "        vertical-align: middle;\n",

  203.        "    }\n",

  204.        "\n",

  205.        "    .dataframe tbody tr th {\n",

  206.        "        vertical-align: top;\n",

  207.        "    }\n",

  208.        "\n",

  209.        "    .dataframe thead th {\n",

  210.        "        text-align: right;\n",

  211.        "    }\n",

  212.        "</style>\n",

  213.        "<table border=\"1\" class=\"dataframe\">\n",

  214.        "  <thead>\n",

  215.        "    <tr style=\"text-align: right;\">\n",

  216.        "      <th></th>\n",

  217.        "      <th>time</th>\n",

  218.        "      <th>last</th>\n",

  219.        "      <th>bmex_5min</th>\n",

  220.        "      <th>gdax_5min</th>\n",

  221.        "      <th>n_bmex_p5</th>\n",

  222.        "      <th>n_gdax_p5</th>\n",

  223.        "      <th>r5</th>\n",

  224.        "      <th>r15</th>\n",

  225.        "      <th>r60</th>\n",

  226.        "    </tr>\n",

  227.        "  </thead>\n",

  228.        "  <tbody>\n",

  229.        "    <tr>\n",

  230.        "      <td>0</td>\n",

  231.        "      <td>1561939210000000000</td>\n",

  232.        "      <td>10758.5800</td>\n",

  233.        "      <td>10760.7205</td>\n",

  234.        "      <td>10760.4593</td>\n",

  235.        "      <td>22</td>\n",

  236.        "      <td>28</td>\n",

  237.        "      <td>1.0000</td>\n",

  238.        "      <td>1.0000</td>\n",

  239.        "      <td>1.0000</td>\n",

  240.        "    </tr>\n",

  241.        "    <tr>\n",

  242.        "      <td>1</td>\n",

  243.        "      <td>1561939220000000000</td>\n",

  244.        "      <td>10770.0000</td>\n",

  245.        "      <td>10763.6811</td>\n",

  246.        "      <td>10761.2528</td>\n",

  247.        "      <td>230</td>\n",

  248.        "      <td>75</td>\n",

  249.        "      <td>1.0002</td>\n",

  250.        "      <td>1.0002</td>\n",

  251.        "      <td>1.0002</td>\n",

  252.        "    </tr>\n",

  253.        "    <tr>\n",

  254.        "      <td>2</td>\n",

  255.        "      <td>1561939230000000000</td>\n",

  256.        "      <td>10758.0100</td>\n",

  257.        "      <td>10761.8843</td>\n",

  258.        "      <td>10760.1596</td>\n",

  259.        "      <td>418</td>\n",

  260.        "      <td>120</td>\n",

  261.        "      <td>1.0002</td>\n",

  262.        "      <td>1.0002</td>\n",

  263.        "      <td>1.0002</td>\n",

  264.        "    </tr>\n",

  265.        "    <tr>\n",

  266.        "      <td>3</td>\n",

  267.        "      <td>1561939240000000000</td>\n",

  268.        "      <td>10752.5000</td>\n",

  269.        "      <td>10757.6829</td>\n",

  270.        "      <td>10760.3630</td>\n",

  271.        "      <td>507</td>\n",

  272.        "      <td>147</td>\n",

  273.        "      <td>0.9998</td>\n",

  274.        "      <td>0.9998</td>\n",

  275.        "      <td>0.9998</td>\n",

  276.        "    </tr>\n",

  277.        "    <tr>\n",

  278.        "      <td>4</td>\n",

  279.        "      <td>1561939250000000000</td>\n",

  280.        "      <td>10772.6900</td>\n",

  281.        "      <td>10757.5702</td>\n",

  282.        "      <td>10763.0840</td>\n",

  283.        "      <td>537</td>\n",

  284.        "      <td>191</td>\n",

  285.        "      <td>0.9995</td>\n",

  286.        "      <td>0.9995</td>\n",

  287.        "      <td>0.9995</td>\n",

  288.        "    </tr>\n",

  289.        "  </tbody>\n",

  290.        "</table>\n",

  291.        "</div>"

  292.       ],

  293.       "text/plain": [

  294.        "                  time       last  bmex_5min  gdax_5min  n_bmex_p5  n_gdax_p5  \\\n",

  295.        "0  1561939210000000000 10758.5800 10760.7205 10760.4593         22         28   \n",

  296.        "1  1561939220000000000 10770.0000 10763.6811 10761.2528        230         75   \n",

  297.        "2  1561939230000000000 10758.0100 10761.8843 10760.1596        418        120   \n",

  298.        "3  1561939240000000000 10752.5000 10757.6829 10760.3630        507        147   \n",

  299.        "4  1561939250000000000 10772.6900 10757.5702 10763.0840        537        191   \n",

  300.        "\n",

  301.        "      r5    r15    r60  \n",

  302.        "0 1.0000 1.0000 1.0000  \n",

  303.        "1 1.0002 1.0002 1.0002  \n",

  304.        "2 1.0002 1.0002 1.0002  \n",

  305.        "3 0.9998 0.9998 0.9998  \n",

  306.        "4 0.9995 0.9995 0.9995  "

  307.       ]

  308.      },

  309.      "execution_count": 8,

  310.      "metadata": {},

  311.      "output_type": "execute_result"

  312.     }

  313.    ],

  314.    "source": [

  315.     "ref = pd.read_csv('../var/hard.csv')\n",

  316.     "ref.head()"

  317.    ]

  318.   },

  319.   {

  320.    "cell_type": "code",

  321.    "execution_count": 12,

  322.    "metadata": {},

  323.    "outputs": [

  324.     {

  325.      "data": {

  326.       "text/plain": [

  327.        "array([1567295750000000000, 1567295760000000000, 1567295770000000000, 1567295780000000000, 1567295790000000000, 1567295800000000000, 1567295810000000000, 1567295820000000000, 1567295830000000000,\n",

  328.        "       1567295840000000000, 1567295850000000000, 1567295860000000000, 1567295870000000000, 1567295880000000000, 1567295890000000000, 1567295900000000000, 1567295910000000000, 1567295920000000000,\n",

  329.        "       1567295930000000000, 1567295940000000000, 1567295950000000000, 1567295960000000000, 1567295970000000000, 1567295980000000000, 1567295990000000000])"

  330.       ]

  331.      },

  332.      "execution_count": 12,

  333.      "metadata": {},

  334.      "output_type": "execute_result"

  335.     }

  336.    ],

  337.    "source": [

  338.     "ref['time'].tail(25).values"

  339.    ]

  340.   },

  341.   {

  342.    "cell_type": "code",

  343.    "execution_count": 13,

  344.    "metadata": {},

  345.    "outputs": [

  346.     {

  347.      "name": "stdout",

  348.      "output_type": "stream",

  349.      "text": [

  350.       "finished in 487.8sec\n"

  351.      ]

  352.     }

  353.    ],

  354.    "source": [

  355.     "import time\n",

  356.     "\n",

  357.     "start = time.time()\n",

  358.     "rows = []\n",

  359.     "\n",

  360.     "for example_time in ref['time'].tail(25).values:\n",

  361.     "    last_5min = (df['time'] > example_time - SECOND * 60 * 5) & (df['time'] <= example_time)\n",

  362.     "    last_15min = (df['time'] > example_time - SECOND * 60 * 15) & (df['time'] <= example_time)\n",

  363.     "    last_60min = (df['time'] > example_time - SECOND * 60 * 60) & (df['time'] <= example_time)\n",

  364.     "    of_btc_usd = df['ticker'] == 'btc_usd'\n",

  365.     "    of_gdax = df['exch'] == 'gdax'\n",

  366.     "    of_bmex = df['exch'] == 'bmex'\n",

  367.     "\n",

  368.     "    g5 = last_5min & of_btc_usd & of_gdax\n",

  369.     "    b5 = last_5min & of_btc_usd & of_bmex\n",

  370.     "    g15 = last_15min & of_btc_usd & of_gdax\n",

  371.     "    b15 = last_15min & of_btc_usd & of_bmex\n",

  372.     "    g60 = last_60min & of_btc_usd & of_gdax\n",

  373.     "    b60 = last_60min & of_btc_usd & of_bmex\n",

  374.     "\n",

  375.     "    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",

  376.     "    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",

  377.     "    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",

  378.     "    rows.append(dict(example_time=example_time, r5=ratio_5min, r15=ratio_15min, r60=ratio_60min))\n",

  379.     "    \n",

  380.     "took = time.time() - start\n",

  381.     "print('finished in {:.1f}sec'.format(took))"

  382.    ]

  383.   },

  384.   {

  385.    "cell_type": "code",

  386.    "execution_count": 19,

  387.    "metadata": {},

  388.    "outputs": [

  389.     {

  390.      "data": {

  391.       "text/plain": [

  392.        "3.342554545733013"

  393.       ]

  394.      },

  395.      "execution_count": 19,

  396.      "metadata": {},

  397.      "output_type": "execute_result"

  398.     }

  399.    ],

  400.    "source": [

  401.     "hypothetical_full_took = (took / 25) * 5401808\n",

  402.     "hypothetical_full_took / 60 / 60 / 24 / 365"

  403.    ]

  404.   },

  405.   {

  406.    "cell_type": "code",

  407.    "execution_count": 20,

  408.    "metadata": {},

  409.    "outputs": [

  410.     {

  411.      "data": {

  412.       "text/plain": [

  413.        "0.1016643329480867"

  414.       ]

  415.      },

  416.      "execution_count": 20,

  417.      "metadata": {},

  418.      "output_type": "execute_result"

  419.     }

  420.    ],

  421.    "source": [

  422.     "92331988 / 908204336"

  423.    ]

  424.   },

  425.   {

  426.    "cell_type": "code",

  427.    "execution_count": 21,

  428.    "metadata": {},

  429.    "outputs": [

  430.     {

  431.      "data": {

  432.       "text/plain": [

  433.        "19.513984975814818"

  434.       ]

  435.      },

  436.      "execution_count": 21,

  437.      "metadata": {},

  438.      "output_type": "execute_result"

  439.     }

  440.    ],

  441.    "source": [

  442.     "took / 25"

  443.    ]

  444.   },

  445.   {

  446.    "cell_type": "code",

  447.    "execution_count": 24,

  448.    "metadata": {},

  449.    "outputs": [

  450.     {

  451.      "data": {

  452.       "text/plain": [

  453.        "('105,410,800.2', 105410800.15423629)"

  454.       ]

  455.      },

  456.      "execution_count": 24,

  457.      "metadata": {},

  458.      "output_type": "execute_result"

  459.     }

  460.    ],

  461.    "source": [

  462.     "'{:,.1f}'.format(hypothetical_full_took), hypothetical_full_took"

  463.    ]

  464.   },

  465.   {

  466.    "cell_type": "code",

  467.    "execution_count": 32,

  468.    "metadata": {},

  469.    "outputs": [

  470.     {

  471.      "data": {

  472.       "text/plain": [

  473.        "r5_delta     0.000000000002368\n",

  474.        "r15_delta    0.000000000010704\n",

  475.        "r60_delta    0.000000000005513\n",

  476.        "dtype: object"

  477.       ]

  478.      },

  479.      "execution_count": 32,

  480.      "metadata": {},

  481.      "output_type": "execute_result"

  482.     }

  483.    ],

  484.    "source": [

  485.     "(pd.DataFrame(rows).join(ref.set_index('time'), on='example_time', rsuffix='_rust')\n",

  486.     " .assign(r5_delta=lambda df: abs(df['r5'] - df['r5_rust']))\n",

  487.     " .assign(r15_delta=lambda df: abs(df['r15'] - df['r15_rust']))\n",

  488.     " .assign(r60_delta=lambda df: abs(df['r60'] - df['r60_rust']))\n",

  489.     ")[['r5_delta','r15_delta','r60_delta']].max(axis=0).map(lambda x: '{:.15f}'.format(x))"

  490.    ]

  491.   }

  492.  ],

  493.  "metadata": {

  494.   "kernelspec": {

  495.    "display_name": "Python 3",

  496.    "language": "python",

  497.    "name": "python3"

  498.   },

  499.   "language_info": {

  500.    "codemirror_mode": {

  501.     "name": "ipython",

  502.     "version": 3

  503.    },

  504.    "file_extension": ".py",

  505.    "mimetype": "text/x-python",

  506.    "name": "python",

  507.    "nbconvert_exporter": "python",

  508.    "pygments_lexer": "ipython3",

  509.    "version": "3.7.5"

  510.   }

  511.  },

  512.  "nbformat": 4,

  513.  "nbformat_minor": 2

  514. }