dask-sparse.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sparse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.array as da"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = sparse.random((100000, 100000), density=0.0001)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = da.from_array(s, chunks=(10000, 10000), asarray=False, fancy=False).persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.571170042811673e+22\n",
      "CPU times: user 18 s, sys: 2.83 s, total: 20.9 s\n",
      "Wall time: 15.6 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "for i in range(4):\n",
    "    s = (s + s.T) * s.sum(axis=0)\n",
    "print(s.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.5711700428116743e+22\n",
      "CPU times: user 15.5 s, sys: 2.84 s, total: 18.3 s\n",
      "Wall time: 7.34 s\n"
     ]
    }
   ],
   "source": [
    "%%time \n",
    "for i in range(4):\n",
    "    x = (x + x.T) * x.sum(axis=0)\n",
    "y = x.sum()\n",
    "print(y.compute())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/hameerabbasi/anaconda3/lib/python3.6/site-packages/dask/array/core.py:2187: UserWarning: Increasing number of chunks by factor of 10\n",
      "  (nparts / max_parts))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "6.720557033161344e+41"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.dot(x.T).sum().compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sparse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.array as da"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = sparse.random((100000, 100000), density=0.0001)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = da.from_array(s, chunks=(10000, 10000), asarray=False, fancy=False).persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.571170042811673e+22\n",
      "CPU times: user 18 s, sys: 2.83 s, total: 20.9 s\n",
      "Wall time: 15.6 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "for i in range(4):\n",
    "    s = (s + s.T) * s.sum(axis=0)\n",
    "print(s.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.5711700428116743e+22\n",
      "CPU times: user 15.5 s, sys: 2.84 s, total: 18.3 s\n",
      "Wall time: 7.34 s\n"
     ]
    }
   ],
   "source": [
    "%%time \n",
    "for i in range(4):\n",
    "    x = (x + x.T) * x.sum(axis=0)\n",
    "y = x.sum()\n",
    "print(y.compute())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/hameerabbasi/anaconda3/lib/python3.6/site-packages/dask/array/core.py:2187: UserWarning: Increasing number of chunks by factor of 10\n",
      "  (nparts / max_parts))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "6.720557033161344e+41"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.dot(x.T).sum().compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}