Influence of is_monotonic logic in _partial_date_slice.ipynb

{
 "cells": [
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "import pandas as pd",
   "execution_count": 1,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "import xarray as xr",
   "execution_count": 2,
   "outputs": []
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Here I experiment with removing the ```is_monotonic``` logic from ```_partial_date_slice``` in pd.DatetimeIndex.\n\nBy ```is_monotonic``` logic I primarily mean this if statement: https://github.com/pandas-dev/pandas/blob/master/pandas/tseries/index.py#L1312"
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "class ModifiedDatetimeIndex(pd.DatetimeIndex):\n    def _partial_date_slice(self, reso, parsed,\n                            use_lhs=True, use_rhs=True):\n        t1, t2 = self._parsed_string_to_bounds(reso, parsed)\n        stamps = self.asi8\n        lhs_mask = (stamps >= t1.value) if use_lhs else True\n        rhs_mask = (stamps <= t2.value) if use_rhs else True\n        return (lhs_mask & rhs_mask).nonzero()[0]",
   "execution_count": 3,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "rng = pd.date_range('2000-01-01', '2001-01-01', freq='M')",
   "execution_count": 4,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "series = pd.Series(rng, index=ModifiedDatetimeIndex(rng))",
   "execution_count": 5,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "# I would not expect this to raise a KeyError; I think this stems from the way __contains__\n# is written.\nseries.loc['2000-01']",
   "execution_count": 6,
   "outputs": [
    {
     "output_type": "error",
     "ename": "KeyError",
     "evalue": "'the label [2000-01] is not in the [index]'",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-6-1ad2eaee8288>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# I would not expect this to raise a KeyError; I think this stems from the way __contains__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;31m# is written.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mseries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'2000-01'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m//anaconda/envs/xarray-dev/lib/python2.7/site-packages/pandas/core/indexing.pyc\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1310\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_tuple\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1311\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1312\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1313\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1314\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_getitem_axis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m//anaconda/envs/xarray-dev/lib/python2.7/site-packages/pandas/core/indexing.pyc\u001b[0m in \u001b[0;36m_getitem_axis\u001b[0;34m(self, key, axis)\u001b[0m\n\u001b[1;32m   1480\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1481\u001b[0m         \u001b[0;31m# fall thru to straight lookup\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1482\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_has_valid_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1483\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_label\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1484\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m//anaconda/envs/xarray-dev/lib/python2.7/site-packages/pandas/core/indexing.pyc\u001b[0m in \u001b[0;36m_has_valid_type\u001b[0;34m(self, key, axis)\u001b[0m\n\u001b[1;32m   1417\u001b[0m                 \u001b[0;32mraise\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1418\u001b[0m             \u001b[0;32mexcept\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1419\u001b[0;31m                 \u001b[0merror\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1420\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1421\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m//anaconda/envs/xarray-dev/lib/python2.7/site-packages/pandas/core/indexing.pyc\u001b[0m in \u001b[0;36merror\u001b[0;34m()\u001b[0m\n\u001b[1;32m   1404\u001b[0m                                     \"key\")\n\u001b[1;32m   1405\u001b[0m                 raise KeyError(\"the label [%s] is not in the [%s]\" %\n\u001b[0;32m-> 1406\u001b[0;31m                                (key, self.obj._get_axis_name(axis)))\n\u001b[0m\u001b[1;32m   1407\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1408\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'the label [2000-01] is not in the [index]'"
     ]
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "# Any date other than the first one works OK\nseries['2000-02']",
   "execution_count": 7,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "2000-02-29   2000-02-29\ndtype: datetime64[ns]"
     },
     "metadata": {},
     "execution_count": 7
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "# Using a conventional DatetimeIndex things work OK (presumably because of the is_monotonic logic)\nseries = pd.Series(rng, index=rng)",
   "execution_count": 8,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "series.loc['2000-01']",
   "execution_count": 9,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "2000-01-31   2000-01-31\nFreq: M, dtype: datetime64[ns]"
     },
     "metadata": {},
     "execution_count": 9
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "# In addition the scalar vs. non-scalar behavior changes in a DataArray\n# Here we use the ModifiedDatetimeIndex\nda = xr.DataArray(rng, coords=[ModifiedDatetimeIndex(rng)], dims=['time'])",
   "execution_count": 10,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "da.sel(time='2000-01')",
   "execution_count": 11,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 1)>\narray(['2000-01-31T00:00:00.000000000'], dtype='datetime64[ns]')\nCoordinates:\n  * time     (time) datetime64[ns] 2000-01-31"
     },
     "metadata": {},
     "execution_count": 11
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "# Returns a non-scalar time now.\nda.sel(time='2000-01-31')",
   "execution_count": 12,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 1)>\narray(['2000-01-31T00:00:00.000000000'], dtype='datetime64[ns]')\nCoordinates:\n  * time     (time) datetime64[ns] 2000-01-31"
     },
     "metadata": {},
     "execution_count": 12
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "# Here we use the standard DatetimeIndex\nda = xr.DataArray(rng, coords=[rng], dims=['time'])",
   "execution_count": 13,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "da.sel(time='2000-01')",
   "execution_count": 14,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 1)>\narray(['2000-01-31T00:00:00.000000000'], dtype='datetime64[ns]')\nCoordinates:\n  * time     (time) datetime64[ns] 2000-01-31"
     },
     "metadata": {},
     "execution_count": 14
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "da.sel(time='2000-01-31')",
   "execution_count": 15,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray ()>\narray(949276800000000000L, dtype='datetime64[ns]')\nCoordinates:\n    time     datetime64[ns] 2000-01-31"
     },
     "metadata": {},
     "execution_count": 15
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "",
   "execution_count": null,
   "outputs": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "name": "python2",
   "display_name": "Python 2",
   "language": "python"
  },
  "language_info": {
   "mimetype": "text/x-python",
   "nbconvert_exporter": "python",
   "name": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12",
   "file_extension": ".py",
   "codemirror_mode": {
    "version": 2,
    "name": "ipython"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}