datreant-view

datreant-view.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import datreant\n",
    "import numpy as np\n",
    "from os.path import split, join"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This Notebook should serve as a testing ground for a new static treant view. First we create a dummy treant with a struture that resembles what I usually end up with during my research"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "obs = datreant.Treant('test-obs')\n",
    "data = np.ones((40, 40))\n",
    "\n",
    "# First simulation runs\n",
    "obs.data.add('sim-setup-1/var-value-1/energy', data)\n",
    "obs.data.add('sim-setup-1/var-value-1/rmsd', data)\n",
    "\n",
    "obs.data.add('sim-setup-1/var-value-2/energy', data)\n",
    "obs.data.add('sim-setup-1/var-value-2/rmsd', data)\n",
    "\n",
    "obs.data.add('sim-setup-1/var-value-3/energy', data)\n",
    "obs.data.add('sim-setup-1/var-value-3/rmsd', data)\n",
    "\n",
    "obs.data.add('sim-setup-1/var-value-10/energy', data)\n",
    "obs.data.add('sim-setup-1/var-value-10/rmsd', data)\n",
    "\n",
    "# second simulation runs\n",
    "obs.data.add('sim-setup-2/var-value-1/energy', data)\n",
    "obs.data.add('sim-setup-2/var-value-1/rmsd', data)\n",
    "\n",
    "obs.data.add('sim-setup-2/var-value-2/energy', data)\n",
    "obs.data.add('sim-setup-2/var-value-2/rmsd', data)\n",
    "\n",
    "obs.data.add('sim-setup-2/var-value-3/energy', data)\n",
    "obs.data.add('sim-setup-2/var-value-3/rmsd', data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's write a static treant view. The view is able to get specific leaves of the treant and additionally can also\n",
    "be constrained to a subset of the leave with a filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "class TreantView(object):\n",
    "    def __init__(self, treant, head, tail=None, include=None, exclude=None,\n",
    "                 sort_func=None):\n",
    "        self._treant = treant\n",
    "        self._head = head\n",
    "        self._tail = None\n",
    "        self._get_keys()\n",
    "        \n",
    "        if include is not None:\n",
    "            self.filter(include, exclude)\n",
    "            \n",
    "        self._tail = tail\n",
    "        if tail is not None:\n",
    "            self.use_tail(tail)\n",
    "            \n",
    "        if sort_func is not None:\n",
    "            self.sort(sort_func)\n",
    "        \n",
    "    def _get_keys(self):\n",
    "        \"\"\"get keys of treant leave\"\"\"\n",
    "        keys = self._treant.data.keys()\n",
    "        keys = [k.replace(self._head + '/', '') for k in keys if self._head in k]\n",
    "        if self._tail is not None:\n",
    "            keys = [k.replace('/' + self._tail, '/') for k in keys]\n",
    "        self._keys = keys\n",
    "    \n",
    "    def use_tail(self, tail):\n",
    "        \"\"\"use a common tail for all keys and blend that out in the selection process\"\"\"\n",
    "        self._tail = tail\n",
    "        self._keys = [k.replace('/' + tail, '') for k in self._keys]\n",
    "        \n",
    "    def sort(self, sort_func):\n",
    "        \"\"\"Use sort_func to convert elements to a data-type according to which\n",
    "           the keys will get sorted\n",
    "        \"\"\"\n",
    "        sort_idx = np.argsort([sort_func(k) for k in self._keys])\n",
    "        self._keys = list(np.array(self._keys)[sort_idx])\n",
    "        \n",
    "    def filter(self, include, exclude=None):\n",
    "        \"\"\"filter to subset of leave only\"\"\"\n",
    "        if exclude is None:\n",
    "            exclude = []\n",
    "        keys = [k for k in self._keys if \\\n",
    "                (np.all([w in k for w in include]) and\n",
    "                (np.all([w not in k for w in exclude])))]\n",
    "        self._keys = keys\n",
    "    \n",
    "    def __getitem__(self, item):\n",
    "        if type(item) == int:\n",
    "            return self._treant[self._keys[item]]\n",
    "        elif type(item) == str:\n",
    "            return self._treant[join_paths(self._head, item, self._tail)]\n",
    "        else:\n",
    "            raise NotImplementedError('can only handle \"int\" and \"str\" objects')\n",
    "            \n",
    "    @property\n",
    "    def keys(self):\n",
    "        return self._keys\n",
    "            \n",
    "    @property\n",
    "    def treant(self):\n",
    "        return self._treant\n",
    "    \n",
    "    @property\n",
    "    def head(self):\n",
    "        return self._head\n",
    "            \n",
    "def join_paths(head, middle, tail=None):\n",
    "    if tail:\n",
    "        return join(head, middle, tail)\n",
    "    else:\n",
    "        return join(head, middle)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Let's have some fun with the view"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets begin by only accessing one leave."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['var-value-1/energy',\n",
       " 'var-value-1/rmsd',\n",
       " 'var-value-10/energy',\n",
       " 'var-value-10/rmsd',\n",
       " 'var-value-2/energy',\n",
       " 'var-value-2/rmsd',\n",
       " 'var-value-3/energy',\n",
       " 'var-value-3/rmsd']"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "leave = TreantView(obs, 'sim-setup-1')\n",
    "leave.keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(40, 40)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "leave['var-value-1/rmsd'].shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now I only want to access the energy entries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['var-value-1/energy',\n",
       " 'var-value-10/energy',\n",
       " 'var-value-2/energy',\n",
       " 'var-value-3/energy']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "leave.filter(include='energy')\n",
    "leave.keys"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hm that is already quite good. But now they all have the same ending. I don't really want to type 'energy' everytime\n",
    "I access one of these fields now."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['var-value-1', 'var-value-10', 'var-value-2', 'var-value-3']\n",
      "(40, 40)\n"
     ]
    }
   ],
   "source": [
    "leave.use_tail('energy')\n",
    "print(leave.keys)\n",
    "print(leave['var-value-1'].shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We are already pretty good right now. But the order is still a bit of. Wouldn't it be nice if we can change that as well?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['var-value-1', 'var-value-2', 'var-value-3', 'var-value-10']\n"
     ]
    }
   ],
   "source": [
    "leave.sort(lambda x: int(x[10:]))\n",
    "print(leave.keys)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And now all together"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "tv = TreantView(obs, 'sim-setup-1', include=['energy'], tail='energy', sort_func=lambda x: int(x[10:]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['var-value-1', 'var-value-2', 'var-value-3', 'var-value-10']"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tv.keys"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# What happens if we add a new analysis?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "obs.data.add('sim-setup-1/energy_hist', data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We just added a new entry in the datreant where we save an energy histogram calculated from all 'sim-setup-1' simulations. Let's try to create a TreantView like before again.\n",
    "\n",
    "**Note**\n",
    "You have to create a new View. The views are static and NOT updated with the underlying treant object!!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "invalid literal for int() with base 10: 't'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-44-bcb22c20ed50>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtv\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTreantView\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'sim-setup-1'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minclude\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'energy'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtail\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'energy'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort_func\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m<ipython-input-9-8e1a6d3ff422>\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, treant, head, tail, include, exclude, sort_func)\u001b[0m\n\u001b[0;32m     15\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     16\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0msort_func\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 17\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msort_func\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     18\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     19\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_get_keys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-9-8e1a6d3ff422>\u001b[0m in \u001b[0;36msort\u001b[1;34m(self, sort_func)\u001b[0m\n\u001b[0;32m     29\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     30\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0msort\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort_func\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 31\u001b[1;33m         \u001b[0msort_idx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margsort\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0msort_func\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mk\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mk\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_keys\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     32\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_keys\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_keys\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0msort_idx\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-44-bcb22c20ed50>\u001b[0m in \u001b[0;36m<lambda>\u001b[1;34m(x)\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtv\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTreantView\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'sim-setup-1'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minclude\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'energy'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtail\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'energy'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort_func\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m: invalid literal for int() with base 10: 't'"
     ]
    }
   ],
   "source": [
    "tv = TreantView(obs, 'sim-setup-1', include=['energy'], tail='energy', sort_func=lambda x: int(x[10:]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This resulted in an error. It looks like we can't use the sorting anymore right now. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "tv = TreantView(obs, 'sim-setup-1', include=['energy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['energy_hist',\n",
       " 'var-value-1/energy',\n",
       " 'var-value-10/energy',\n",
       " 'var-value-2/energy',\n",
       " 'var-value-3/energy']"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tv.keys"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ah there is the problem. We now have also included the 'energy_hist' analysis. Let's exclude that one"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['var-value-1/energy', 'var-value-10/energy', 'var-value-2/energy', 'var-value-3/energy']\n"
     ]
    }
   ],
   "source": [
    "tv.filter(include=['v'], exclude=['hist'])\n",
    "print(tv.keys)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we have the same values as before. Ok lets create a quick view a gain that excludes the histogram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "tv = TreantView(obs, 'sim-setup-1', include=['energy'], exclude=['hist'],\n",
    "                tail='energy', sort_func=lambda x: int(x[10:]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['var-value-1', 'var-value-2', 'var-value-3', 'var-value-10']"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tv.keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}