Hysteresis of performance on Dask Dataframes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import dask\n",
    "import dask.dataframe as dd\n",
    "from dask.diagnostics import ProgressBar, Profiler, ResourceProfiler, CacheProfiler\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pandas.tseries.offsets import DateOffset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Versions\n",
    "print('pandas:', pd.__version__)\n",
    "print('numpy:', np.__version__)\n",
    "print('dask:', dask.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(index=pd.DatetimeIndex(end=pd.Timestamp('2017-05-18'), periods=25000, freq='1B', name='date'), columns=['value'], data=np.random.rand(25000)).reset_index()\n",
    "ddf = dd.from_pandas(df, npartitions=10)\n",
    "def my_func(d):\n",
    "    return d + DateOffset(months=3)\n",
    "\n",
    "f = lambda x: my_func(x.date)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# MAP\n",
    "\n",
    "z = ddf.map_partitions(f, meta=(pd.Timestamp))\n",
    "ddf = ddf.assign(date2=z)   # Assignement\n",
    "with ProgressBar():\n",
    "    ddf.compute()\n",
    "ddf.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# APPLY\n",
    "\n",
    "z = ddf.apply(f, axis=1, meta=pd.Timestamp)\n",
    "ddf['date2'] = z  # Assignement\n",
    "with ProgressBar():\n",
    "    ddf.compute()\n",
    "ddf.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:vol_tools3.5]",
   "language": "python",
   "name": "conda-env-vol_tools3.5-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}