Blazing Notebooks 4 GPU Demo

bsql_sf100_4_gpus.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table style=\"border: 2px solid white;\">\n",
       "<tr>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3 style=\"text-align: left;\">Client</h3>\n",
       "<ul style=\"text-align: left; list-style: none; margin: 0; padding: 0;\">\n",
       "  <li><b>Scheduler: </b>tcp://34.201.57.69:8786</li>\n",
       "  <li><b>Dashboard: </b><a href='http://34.201.57.69:8787/status' target='_blank'>http://34.201.57.69:8787/status</a></li>\n",
       "</ul>\n",
       "</td>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3 style=\"text-align: left;\">Cluster</h3>\n",
       "<ul style=\"text-align: left; list-style:none; margin: 0; padding: 0;\">\n",
       "  <li><b>Workers: </b>4</li>\n",
       "  <li><b>Cores: </b>16</li>\n",
       "  <li><b>Memory: </b>65.93 GB</li>\n",
       "</ul>\n",
       "</td>\n",
       "</tr>\n",
       "</table>"
      ],
      "text/plain": [
       "<Client: 'tcp://172.31.50.204:8786' processes=4 threads=16, memory=65.93 GB>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from dask.distributed import Client\n",
    "\n",
    "client = Client('34.201.57.69:8786')\n",
    "client"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from blazingsql import BlazingContext"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BlazingContext ready\n"
     ]
    }
   ],
   "source": [
    "bc = BlazingContext(dask_client = client)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(True,\n",
       " '',\n",
       " OrderedDict([('type', 's3'),\n",
       "              ('bucket_name', 'blazingsql-colab'),\n",
       "              ('access_key_id', ''),\n",
       "              ('secret_key', ''),\n",
       "              ('session_token', ''),\n",
       "              ('encryption_type', <S3EncryptionType.NONE: 1>),\n",
       "              ('kms_key_amazon_resource_name', ''),\n",
       "              ('endpoint_override', ''),\n",
       "              ('region', '')]))"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# register AWS S3 bucket\n",
    "bc.s3('bsql_data', bucket_name='blazingsql-colab')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1.14 s, sys: 560 ms, total: 1.7 s\n",
      "Wall time: 6.01 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "bc.create_table('lineitem', 's3://bsql_data/tpch_sf100/lineitem/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1.64 s, sys: 72.4 ms, total: 1.71 s\n",
      "Wall time: 2.61 s\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>count(*)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>600037902</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    count(*)\n",
       "0  600037902"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "bc.sql('select count(*) from lineitem').head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1.28 s, sys: 65.3 ms, total: 1.34 s\n",
      "Wall time: 13.7 s\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>l_returnflag</th>\n",
       "      <th>l_linestatus</th>\n",
       "      <th>sum_qty</th>\n",
       "      <th>sum_base_price</th>\n",
       "      <th>sum_disc_price</th>\n",
       "      <th>sum_charge</th>\n",
       "      <th>avg_qty</th>\n",
       "      <th>avg_price</th>\n",
       "      <th>avg_disc</th>\n",
       "      <th>count_order</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>F</td>\n",
       "      <td>3.770265e+09</td>\n",
       "      <td>5.654431e+12</td>\n",
       "      <td>5.372649e+12</td>\n",
       "      <td>5.586929e+12</td>\n",
       "      <td>25.466522</td>\n",
       "      <td>38193.261719</td>\n",
       "      <td>0.050031</td>\n",
       "      <td>148047881</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  l_returnflag l_linestatus       sum_qty  sum_base_price  sum_disc_price  \\\n",
       "0            A            F  3.770265e+09    5.654431e+12    5.372649e+12   \n",
       "\n",
       "     sum_charge    avg_qty     avg_price  avg_disc  count_order  \n",
       "0  5.586929e+12  25.466522  38193.261719  0.050031    148047881  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "# Q1\n",
    "query =\"\"\"\n",
    "    select\n",
    "        l_returnflag,\n",
    "        l_linestatus,\n",
    "        sum(l_quantity) as sum_qty,\n",
    "        sum(l_extendedprice) as sum_base_price,\n",
    "        sum(l_extendedprice*(1-l_discount)) as sum_disc_price,\n",
    "        sum(l_extendedprice*(1-l_discount)*(1+l_tax)) as sum_charge,\n",
    "        avg(l_quantity) as avg_qty,\n",
    "        avg(l_extendedprice) as avg_price,\n",
    "        avg(l_discount) as avg_disc,\n",
    "        count(*) as count_order\n",
    "    from\n",
    "        lineitem\n",
    "    where\n",
    "        l_shipdate <= date '1998-12-01' - interval '90' day\n",
    "    group by\n",
    "        l_returnflag,\n",
    "        l_linestatus\n",
    "    order by\n",
    "        l_returnflag,\n",
    "        l_linestatus\n",
    "\"\"\"\n",
    "\n",
    "bc.sql(query).head()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Rapids Stable",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}