personal.yaml

distributed:
  version: 2
  scheduler:
    bandwidth: 1000000000     # 100 MB/s estimated worker-worker bandwidth
  worker:
    memory:
      target: 0.90  # target fraction to stay below
      spill: False  # fraction at which we spill to disk
      pause: 0.80  # fraction at which we pause worker threads
      terminate: 0.95  # fraction at which we terminate the worker
  comm:
    compression: null

jobqueue:
  pbs:
    name: dask-worker

    threads: 9
    processes: 4
    memory: 36GB
    interface: ib0
    local-directory: $TMPDIR

    queue: regular
    project: UCLB0022
    walltime: '00:30:00'

    resource-spec: select=9:ncpus=4:mem=16G

scaling-dataframes-arrays.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Launch a modest cluster"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask\n",
    "dask.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dask_jobqueue import PBSCluster\n",
    "cluster = PBSCluster()\n",
    "cluster.scale(50)\n",
    "cluster"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dask.distributed import Client\n",
    "client = Client(cluster)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create a Dask Dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.dataframe as dd\n",
    "\n",
    "df = dd.demo.make_timeseries(start='2000-01-01',\n",
    "                             end='2010-12-31',\n",
    "                             dtypes={'x': float, 'y': float, 'id': int},\n",
    "                             freq='10ms',\n",
    "                             partition_freq='24h')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%time df.groupby('id')[['x', 'y']].mean().compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.x.rolling('1min').std().loc['2000-01-02':'2010-12-30'].idxmax().compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.array as da\n",
    "u, s, v = da.linalg.svd(df.values + 1)\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ss = s.persist()"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}