RLS: Feather 0.4 Python release

Author: wesm

bench/ArrowMigration.ipynb

@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import pyarrow as pa\n",
+    "import feather as fth\n",
+    "\n",
+    "type_ = np.dtype('float64')\n",
+    "DATA_SIZE = (1 << 30)\n",
+    "NCOLS = 100\n",
+    "NROWS = DATA_SIZE / NCOLS / np.dtype(type_).itemsize\n",
+    "\n",
+    "data = {\n",
+    "    'c' + str(i): np.random.randn(int(NROWS))\n",
+    "    for i in range(int(NCOLS))\n",
+    "}\n",
+    "df = pd.DataFrame(data)\n",
+    "df[::5] = np.nan"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "fth.write_dataframe?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "NFILES = 20\n",
+    "for i in range(NFILES):\n",
+    "    fth.write_dataframe(df, 'df{0}.feather'.format(i))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def read_all(nfiles=NFILES, nthreads=1):\n",
+    "    for i in range(nfiles):\n",
+    "        path = 'df{0}.feather'.format(i)\n",
+    "        fth.read_dataframe(path, nthreads=nthreads)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Make sure to run before each command\n",
+    "## echo 3 > /proc/sys/vm/drop_caches"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1.74 s, sys: 7.75 s, total: 9.49 s\n",
+      "Wall time: 16.5 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%time read_all(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 2.08 s, sys: 8.56 s, total: 10.6 s\n",
+      "Wall time: 10.9 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%time read_all(10, nthreads=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "fth.read_dataframe??"
+   ]
+  },
+  {
+   "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": "3.6.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

python/setup.py

@@ -23,7 +23,7 @@
 MINOR = 4
 MICRO = 0
 VERSION = '%d.%d.%d' % (MAJOR, MINOR, MICRO)
-ISRELEASED = False
+ISRELEASED = True
 
 setup_dir = os.path.abspath(os.path.dirname(__file__))
 
@@ -65,10 +65,10 @@ def write_version_py(filename=os.path.join(setup_dir, 'feather/version.py')):
 
 setup(
     name="feather-format",
-    packages=['feather', 'feather.tests'],
+    packages=['feather'],
     version=VERSION,
     package_data={'feather': ['*.pxd', '*.pyx']},
-    install_requires=['pyarrow>=0.3.0'],
+    install_requires=['pyarrow>=0.4.0'],
     description=DESCRIPTION,
     long_description=LONG_DESCRIPTION,
     license='Apache License, Version 2.0',