feather_vs_hdf5.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# feather vs hdf5 (via pandas)\n",
    "\n",
    "on spinning HD, not SSD :-\\ "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import feather\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "arr = np.random.randn(80000000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(40000, 2000)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr[::10] = np.nan\n",
    "df = pd.DataFrame(arr.reshape(40000,2000)).copy()\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 13.4 s per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "feather.write_dataframe(df, 'test.feather')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 1.2 s per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "df = feather.read_dataframe('test.feather')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 14.5 s per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "df.to_hdf('test.h5', 'table')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 413 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "df = pd.read_hdf('test.h5', 'table')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

requirements.txt

appnope==0.1.0
backports-abc==0.4
Cython==0.24
decorator==4.0.9
entrypoints==0.2
feather-format==0.1.2
gnureadline==6.3.3
ipykernel==4.3.1
ipython==4.1.2
ipython-genutils==0.1.0
ipywidgets==4.1.1
Jinja2==2.8
jsonschema==2.5.1
jupyter==1.0.0
jupyter-client==4.2.2
jupyter-console==4.1.1
jupyter-core==4.1.0
MarkupSafe==0.23
mistune==0.7.2
nbconvert==4.2.0
nbformat==4.0.1
notebook==4.1.0
numexpr==2.5.2
numpy==1.11.0
pandas==0.18.0
pexpect==4.0.1
pickleshare==0.7.2
ptyprocess==0.5.1
Pygments==2.1.3
python-dateutil==2.5.2
pytz==2016.3
pyzmq==15.2.0
qtconsole==4.2.1
simplegeneric==0.8.1
six==1.10.0
tables==3.2.2
terminado==0.6
tornado==4.3
traitlets==4.2.1