Experimental NetCDFTimeIndex.ipynb

{
 "cells": [
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Experimental NetCDFTimeIndex\n----------------------------"
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "import xarray as xr\nimport numpy as np\n\nfrom pandas import Index\nfrom netCDF4 import netcdftime",
   "execution_count": 1,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "def get_date_field(datetimes, field):\n    \"\"\"This is implemented in cython in pandas; perhaps we \n    could implement something similar for our purposes upstream\n    in netcdftime, but as a proof of concept I'll just use\n    this for now.\n    \"\"\"\n    a = []\n    for d in datetimes:\n        a.append(getattr(d, field))\n    return np.array(a)\n\ndef _field_accessor(name, docstring=None):\n    def f(self):\n        values = self._data\n        return get_date_field(values, name)\n    \n    f.__name__ = name\n    f.__doc__ = docstring\n    return property(f)\n\nclass NetCDFTimeIndex(Index):\n    def __new__(cls, data):\n        result = object.__new__(cls)\n        result._data = np.array(data)\n        return result\n    \n    year = _field_accessor('year', 'The year of the datetime')\n    month = _field_accessor('month', 'The month of the datetime')\n    day = _field_accessor('day', 'The days of the datetime')\n    hour = _field_accessor('hour', 'The hours of the datetime')\n    minute = _field_accessor('minute', 'The minutes of the datetime')\n    second = _field_accessor('second', 'The seconds of the datetime')\n    millisecond = _field_accessor('millisecond', 'The milliseconds of the datetime')\n    microsecond = _field_accessor('microsecond', 'The microseconds of the datetime')\n    \n    def _maybe_convert_str_to_date(self, key):\n        if isinstance(key, str):\n            date_type = type(self._data[0])  # Is there a better way of doing this?\n            return date_type(*netcdftime._parse_date(key))\n        else:\n            return key\n    \n    def get_loc(self, key, method=None, tolerance=None):\n        \"\"\"Add support for ISO 8601 format string date specification\"\"\"\n        return Index.get_loc(self, self._maybe_convert_str_to_date(key),\n                             method, tolerance)\n        \n    def slice_locs(self, start=None, end=None, step=None, kind=None):\n        \"\"\"Add support for ISO 8601 format string date specification\"\"\"\n        return Index.slice_locs(self, self._maybe_convert_str_to_date(start),\n                                self._maybe_convert_str_to_date(end),\n                                step, kind)",
   "execution_count": 2,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "dates_0001 = [netcdftime.DatetimeAllLeap(1, m, 1) for m in range(1, 13)]\ndates_0002 = [netcdftime.DatetimeAllLeap(2, m, 1) for m in range(1, 13)]",
   "execution_count": 3,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "# Create a DataArray with a NetCDFTimeIndex as a coordinate\nda = xr.DataArray(np.arange(35, 35 + 24), coords=[NetCDFTimeIndex(dates_0001 + dates_0002)], dims=['time'])",
   "execution_count": 4,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da",
   "execution_count": 5,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 24)>\narray([35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51,\n       52, 53, 54, 55, 56, 57, 58])\nCoordinates:\n  * time     (time) object    1-01-01 00:00:00    1-02-01 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 5
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.time",
   "execution_count": 6,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray 'time' (time: 24)>\narray([netcdftime._netcdftime.DatetimeAllLeap(1, 1, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 2, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 3, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 4, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 5, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 6, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 7, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 8, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 9, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 10, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 11, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(1, 12, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 1, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 2, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 3, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 4, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 5, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 6, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 7, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 8, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 9, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 10, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 11, 1, 0, 0, 0, 0, -1, 1),\n       netcdftime._netcdftime.DatetimeAllLeap(2, 12, 1, 0, 0, 0, 0, -1, 1)], dtype=object)\nCoordinates:\n  * time     (time) object    1-01-01 00:00:00    1-02-01 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 6
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.sel(time=slice(netcdftime.DatetimeAllLeap(1, 5, 1), netcdftime.DatetimeAllLeap(1, 7, 1)))",
   "execution_count": 7,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 3)>\narray([39, 40, 41])\nCoordinates:\n  * time     (time) object    1-05-01 00:00:00    1-06-01 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 7
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.sel(time=slice('0001-05-01', '0001-07-01'))",
   "execution_count": 8,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 3)>\narray([39, 40, 41])\nCoordinates:\n  * time     (time) object    1-05-01 00:00:00    1-06-01 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 8
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.groupby('time.month').mean('time')",
   "execution_count": 9,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (month: 12)>\narray([ 41.,  42.,  43.,  44.,  45.,  46.,  47.,  48.,  49.,  50.,  51.,\n        52.])\nCoordinates:\n  * month    (month) int64 1 2 3 4 5 6 7 8 9 10 11 12"
     },
     "metadata": {},
     "execution_count": 9
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.groupby('time.year').mean('time')",
   "execution_count": 10,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (year: 2)>\narray([ 40.5,  52.5])\nCoordinates:\n  * year     (year) int64 1 2"
     },
     "metadata": {},
     "execution_count": 10
    }
   ]
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "The approach is calendar-agnostic\n---------------------------------"
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "# Try out a 360-day calendar\ndates_0001 = [netcdftime.Datetime360Day(1, m, 30) for m in range(1, 13)]\ndates_0002 = [netcdftime.Datetime360Day(2, m, 30) for m in range(1, 13)]",
   "execution_count": 11,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da = xr.DataArray(np.arange(35, 35 + 24), coords=[NetCDFTimeIndex(dates_0001 + dates_0002)], dims=['time'])",
   "execution_count": 12,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.sel(time=slice(netcdftime.Datetime360Day(1, 2, 1), netcdftime.Datetime360Day(1, 7, 1)))",
   "execution_count": 13,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 5)>\narray([36, 37, 38, 39, 40])\nCoordinates:\n  * time     (time) object    1-02-30 00:00:00    1-03-30 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 13
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.sel(time=slice('0001-02-01', '0001-07-01'))",
   "execution_count": 14,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (time: 5)>\narray([36, 37, 38, 39, 40])\nCoordinates:\n  * time     (time) object    1-02-30 00:00:00    1-03-30 00:00:00 ..."
     },
     "metadata": {},
     "execution_count": 14
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.groupby('time.month').mean('time')",
   "execution_count": 15,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (month: 12)>\narray([ 41.,  42.,  43.,  44.,  45.,  46.,  47.,  48.,  49.,  50.,  51.,\n        52.])\nCoordinates:\n  * month    (month) int64 1 2 3 4 5 6 7 8 9 10 11 12"
     },
     "metadata": {},
     "execution_count": 15
    }
   ]
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "da.groupby('time.year').mean('time')",
   "execution_count": 16,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "<xarray.DataArray (year: 2)>\narray([ 40.5,  52.5])\nCoordinates:\n  * year     (year) int64 1 2"
     },
     "metadata": {},
     "execution_count": 16
    }
   ]
  }
 ],
 "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": 0
}