xray-demo-python-workers-party.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:4d537a491926b7ac19ec45bec1847188693b00f20f58b33ebec9c1dc1d058c47"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "xray demo - Python workers party"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Docs: http://xray.readthedocs.org <br />\n",
      "Code: http://github.com/xray/xray"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Standard imports"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%matplotlib inline\n",
      "import numpy as np\n",
      "import pandas as pd\n",
      "import xray\n",
      "\n",
      "np.random.seed(123)\n",
      "pd.options.display.max_rows = 10"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xray.__version__"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "'0.3.0.dev-494f6f3'"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Note: this notebook shows off the current development version of xray, but most of this should work in the released version, too. In any case, v0.3 should be released next week."
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Simple examples with a `DataArray`"
     ]
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Create a `DataArray`"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "From numpy"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xray.DataArray(np.random.randn(2, 3))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "<xray.DataArray (dim_0: 2, dim_1: 3)>\n",
        "array([[-1.0856306 ,  0.99734545,  0.2829785 ],\n",
        "       [-1.50629471, -0.57860025,  1.65143654]])\n",
        "Index Coordinates:\n",
        "    dim_0 (dim_0) int64 0 1\n",
        "    dim_1 (dim_1) int64 0 1 2"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xray.DataArray(np.random.randn(2, 3), dims=['x', 'y'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[-2.42667924, -0.42891263,  1.26593626],\n",
        "       [-0.8667404 , -0.67888615, -0.09470897]])\n",
        "Index Coordinates:\n",
        "    x (x) int64 0 1\n",
        "    y (y) int64 0 1 2"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xray.DataArray(np.random.randn(2, 3), [('x', ['a', 'b']), ('y', [-2, 0, 2])])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 1.49138963, -0.638902  , -0.44398196],\n",
        "       [-0.43435128,  2.20593008,  2.18678609]])\n",
        "Index Coordinates:\n",
        "    x (x) |S1 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "From pandas"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.DataFrame(np.random.randn(2, 3), index=['a', 'b'], columns=[-2, 0, 2])\n",
      "df.index.name = 'x'\n",
      "df.columns.name = 'y'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th>y</th>\n",
        "      <th>-2</th>\n",
        "      <th>0</th>\n",
        "      <th>2</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>x</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>a</th>\n",
        "      <td> 1.004054</td>\n",
        "      <td> 0.386186</td>\n",
        "      <td> 0.737369</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>b</th>\n",
        "      <td> 1.490732</td>\n",
        "      <td>-0.935834</td>\n",
        "      <td> 1.175829</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "y        -2         0         2\n",
        "x                              \n",
        "a  1.004054  0.386186  0.737369\n",
        "b  1.490732 -0.935834  1.175829"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo = xray.DataArray(df)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "       [ 1.49073203, -0.93583387,  1.17582904]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "DataArray contents"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.values"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "       [ 1.49073203, -0.93583387,  1.17582904]])"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.dims"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "('x', 'y')"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.coords['y']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "<xray.DataArray 'y' (y: 3)>\n",
        "array([-2,  0,  2])\n",
        "Index Coordinates:\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.attrs"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "OrderedDict()"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Indexing"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Like numpy"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo[[0, 1], 0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "<xray.DataArray (x: 2)>\n",
        "array([ 1.0040539 ,  1.49073203])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "Other Coordinates:\n",
        "    y int64 -2"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Like pandas"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.loc['a':'b', -2]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "<xray.DataArray (x: 2)>\n",
        "array([ 1.0040539 ,  1.49073203])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "Other Coordinates:\n",
        "    y int64 -2"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "By dimension name and integer label"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.isel(x=slice(2))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "       [ 1.49073203, -0.93583387,  1.17582904]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "By dimension name and index label"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.sel(x=['a', 'b'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "       [ 1.49073203, -0.93583387,  1.17582904]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Calculations"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Unary operations"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.mean('x')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "<xray.DataArray (y: 3)>\n",
        "array([ 1.24739296, -0.27482373,  0.95659881])\n",
        "Index Coordinates:\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo + 10"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 11.0040539 ,  10.3861864 ,  10.73736858],\n",
        "       [ 11.49073203,   9.06416613,  11.17582904]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.sin(foo)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 20,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 0.84365439,  0.37665843,  0.67234236],\n",
        "       [ 0.99679657, -0.80509396,  0.92300915]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Binary operations: dimensions align by name"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "bar = xray.DataArray(np.random.randn(3), [foo.coords['y']])\n",
      "zzz = xray.DataArray(np.random.randn(4), dims='z')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "bar"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "<xray.DataArray (y: 3)>\n",
        "array([-1.25388067, -0.6377515 ,  0.9071052 ])\n",
        "Index Coordinates:\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "zzz"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": [
        "<xray.DataArray (z: 4)>\n",
        "array([-1.4286807 , -0.14006872, -0.8617549 , -0.25561937])\n",
        "Index Coordinates:\n",
        "    z (z) int64 0 1 2 3"
       ]
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "bar + zzz"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "<xray.DataArray (y: 3, z: 4)>\n",
        "array([[-2.68256137, -1.39394939, -2.11563556, -1.50950004],\n",
        "       [-2.0664322 , -0.77782022, -1.4995064 , -0.89337087],\n",
        "       [-0.5215755 ,  0.76703648,  0.0453503 ,  0.65148583]])\n",
        "Index Coordinates:\n",
        "    y (y) int64 -2 0 2\n",
        "    z (z) int64 0 1 2 3"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo + bar + zzz"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "<xray.DataArray (x: 2, y: 3, z: 4)>\n",
        "array([[[-1.67850747, -0.38989549, -1.11158167, -0.50544614],\n",
        "        [-1.6802458 , -0.39163382, -1.11332   , -0.50718447],\n",
        "        [ 0.21579307,  1.50440505,  0.78271888,  1.3888544 ]],\n",
        "\n",
        "       [[-1.19182934,  0.09678264, -0.62490354, -0.01876801],\n",
        "        [-3.00226607, -1.71365409, -2.43534027, -1.82920474],\n",
        "        [ 0.65425354,  1.94286552,  1.22117934,  1.82731487]]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2\n",
        "    z (z) int64 0 1 2 3"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "zzz + bar + foo"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 26,
       "text": [
        "<xray.DataArray (z: 4, y: 3, x: 2)>\n",
        "array([[[-1.67850747, -1.19182934],\n",
        "        [-1.6802458 , -3.00226607],\n",
        "        [ 0.21579307,  0.65425354]],\n",
        "\n",
        "       [[-0.38989549,  0.09678264],\n",
        "        [-0.39163382, -1.71365409],\n",
        "        [ 1.50440505,  1.94286552]],\n",
        "\n",
        "       [[-1.11158167, -0.62490354],\n",
        "        [-1.11332   , -2.43534027],\n",
        "        [ 0.78271888,  1.22117934]],\n",
        "\n",
        "       [[-0.50544614, -0.01876801],\n",
        "        [-0.50718447, -1.82920474],\n",
        "        [ 1.3888544 ,  1.82731487]]])\n",
        "Index Coordinates:\n",
        "    z (z) int64 0 1 2 3\n",
        "    y (y) int64 -2 0 2\n",
        "    x (x) object 'a' 'b'"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo - foo.T"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 27,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 0.,  0.,  0.],\n",
        "       [ 0.,  0.,  0.]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 27
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Label based alignment"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Like pandas, but not automatic (yet)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo[:, 1:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "<xray.DataArray (x: 2, y: 2)>\n",
        "array([[ 0.3861864 ,  0.73736858],\n",
        "       [-0.93583387,  1.17582904]])\n",
        "Index Coordinates:\n",
        "    x (x) object 'a' 'b'\n",
        "    y (y) int64 0 2"
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "xray.align(foo[:, 1:], foo[:1], join='outer')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "(<xray.DataArray (x: 2, y: 3)>\n",
        " array([[        nan,  0.3861864 ,  0.73736858],\n",
        "        [        nan, -0.93583387,  1.17582904]])\n",
        " Index Coordinates:\n",
        "     x (x) object 'a' 'b'\n",
        "     y (y) int64 -2 0 2, <xray.DataArray (x: 2, y: 3)>\n",
        " array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "        [        nan,         nan,         nan]])\n",
        " Index Coordinates:\n",
        "     x (x) object 'a' 'b'\n",
        "     y (y) int64 -2 0 2)"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "GroupBy: split-apply-combine"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Just like pandas"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "labels = xray.DataArray(['E', 'F', 'E'], [foo.coords['y']], name='labels')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 30
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "labels"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 31,
       "text": [
        "<xray.DataArray 'labels' (y: 3)>\n",
        "array(['E', 'F', 'E'], \n",
        "      dtype='|S1')\n",
        "Index Coordinates:\n",
        "    y (y) int64 -2 0 2"
       ]
      }
     ],
     "prompt_number": 31
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.groupby(labels).mean('y')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 32,
       "text": [
        "<xray.DataArray (x: 2, labels: 2)>\n",
        "array([[ 0.87071124,  0.3861864 ],\n",
        "       [ 1.33328054, -0.93583387]])\n",
        "Index Coordinates:\n",
        "    x      (x) object 'a' 'b'\n",
        "    labels (labels) |S1 'E' 'F'"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.groupby(labels).apply(lambda x: x.max() - x.min())"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 33,
       "text": [
        "<xray.DataArray (labels: 2)>\n",
        "array([ 0.75336345,  1.32202027])\n",
        "Index Coordinates:\n",
        "    labels (labels) |S1 'E' 'F'"
       ]
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Can also use strings"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.coords['labels'] = labels"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 34
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 35,
       "text": [
        "<xray.DataArray (x: 2, y: 3)>\n",
        "array([[ 1.0040539 ,  0.3861864 ,  0.73736858],\n",
        "       [ 1.49073203, -0.93583387,  1.17582904]])\n",
        "Index Coordinates:\n",
        "    x      (x) object 'a' 'b'\n",
        "    y      (y) int64 -2 0 2\n",
        "Other Coordinates:\n",
        "    labels (y) |S1 'E' 'F' 'E'"
       ]
      }
     ],
     "prompt_number": 35
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "foo.groupby('labels').mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 36,
       "text": [
        "<xray.DataArray (labels: 2)>\n",
        "array([ 1.10199589, -0.27482373])\n",
        "Index Coordinates:\n",
        "    labels (labels) |S1 'E' 'F'"
       ]
      }
     ],
     "prompt_number": 36
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Examples with a Dataset"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Generate some random numbers"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "temp = 15 + 8 * np.random.randn(8, 8, 10) + np.linspace(-8, 8, num=8).reshape(1, -1, 1)\n",
      "pres = np.exp(0.25 * np.random.randn(8, 8, 10) + 0.03 * (temp - 15))\n",
      "lon, lat = np.broadcast_arrays(np.linspace(-100, -80, 8)[:, None],\n",
      "                               np.linspace(30, 50, 8)[None, :])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 37
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "`Dataset` constructor"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds = xray.Dataset({'temperature': (['x', 'y', 'z'], temp),\n",
      "                   'pressure': (['x', 'y', 'z'], pres)},\n",
      "                  coords={'lat': (['x', 'y'], lat),\n",
      "                          'lon': (['x', 'y'], lon),\n",
      "                          'z': 100 * np.arange(10),\n",
      "                         'time': pd.Timestamp('2014-09-05')},\n",
      "                  attrs={'title': 'Example dataset'})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 38
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 39,
       "text": [
        "<xray.Dataset>\n",
        "Dimensions:      (x: 8, y: 8, z: 10)\n",
        "Index Coordinates:\n",
        "    x            (x) int64 0 1 2 3 4 5 6 7\n",
        "    y            (y) int64 0 1 2 3 4 5 6 7\n",
        "    z            (z) int64 0 100 200 300 400 500 600 700 800 900\n",
        "Other Coordinates:\n",
        "    lat          (x, y) float64 30.0 32.86 35.71 38.57 41.43 44.29 47.14 50.0 30.0 32.86 ...\n",
        "    lon          (x, y) float64 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 ...\n",
        "    time         datetime64[ns] 2014-09-05\n",
        "Variables:\n",
        "    pressure     (x, y, z) float64 0.2774 0.6976 0.5993 0.9922 0.8829 0.5271 1.394 ...\n",
        "    temperature  (x, y, z) float64 -15.39 -7.172 1.401 14.42 5.611 7.023 12.51 -0.03629 ...\n",
        "Attributes:\n",
        "    title: Example dataset"
       ]
      }
     ],
     "prompt_number": 39
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Or equivalently:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds = xray.Dataset()\n",
      "ds['temperature'] = (('x', 'y', 'z'), temp)\n",
      "ds['pressure'] = (('x', 'y', 'z'), pres)\n",
      "ds.coords['lat'] = (('x', 'y'), lat)\n",
      "ds.coords['lon'] = (('x', 'y'), lon)\n",
      "ds.coords['z'] = 100 * np.arange(10)\n",
      "ds.coords['time'] = pd.Timestamp('2014-09-05')\n",
      "ds.attrs['title'] = 'Example dataset'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 40
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Indexing along dimensions"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds_sub = ds.sel(x=slice(2), y=0, z=slice(100))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 41
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds_sub"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 42,
       "text": [
        "<xray.Dataset>\n",
        "Dimensions:      (x: 3, z: 2)\n",
        "Index Coordinates:\n",
        "    x            (x) int64 0 1 2\n",
        "    z            (z) int64 0 100\n",
        "Other Coordinates:\n",
        "    y            int64 0\n",
        "    lat          (x) float64 30.0 30.0 30.0\n",
        "    lon          (x) float64 -100.0 -97.14 -94.29\n",
        "    time         datetime64[ns] 2014-09-05\n",
        "Variables:\n",
        "    temperature  (x, z) float64 -15.39 -7.172 16.94 1.118 6.76 8.597\n",
        "    pressure     (x, z) float64 0.2774 0.6976 0.9231 0.9651 1.023 0.7428\n",
        "Attributes:\n",
        "    title: Example dataset"
       ]
      }
     ],
     "prompt_number": 42
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Pull out a `DataArray`"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "temp = ds_sub['temperature']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 43
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "temp"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 44,
       "text": [
        "<xray.DataArray 'temperature' (x: 3, z: 2)>\n",
        "array([[-15.38871284,  -7.17226484],\n",
        "       [ 16.9429564 ,   1.11826435],\n",
        "       [  6.76025594,   8.59665689]])\n",
        "Index Coordinates:\n",
        "    x    (x) int64 0 1 2\n",
        "    z    (z) int64 0 100\n",
        "Other Coordinates:\n",
        "    lon  (x) float64 -100.0 -97.14 -94.29\n",
        "    lat  (x) float64 30.0 30.0 30.0\n",
        "    time datetime64[ns] 2014-09-05\n",
        "    y    int64 0"
       ]
      }
     ],
     "prompt_number": 44
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Computation with a `Dataset`"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds.mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "<xray.Dataset>\n",
        "Dimensions:      ()\n",
        "Index Coordinates:\n",
        "    *empty*\n",
        "Other Coordinates:\n",
        "    time         datetime64[ns] 2014-09-05\n",
        "Variables:\n",
        "    temperature  float64 14.89\n",
        "    pressure     float64 1.057"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds.groupby('z').mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 46,
       "text": [
        "<xray.Dataset>\n",
        "Dimensions:      (z: 10)\n",
        "Index Coordinates:\n",
        "    z            (z) int64 0 100 200 300 400 500 600 700 800 900\n",
        "Other Coordinates:\n",
        "    time         datetime64[ns] 2014-09-05\n",
        "Variables:\n",
        "    pressure     (z) float64 1.027 1.035 0.9908 1.04 1.078 1.091 1.047 1.082 1.102 1.074\n",
        "    temperature  (z) float64 13.72 14.32 14.1 15.53 15.5 15.29 14.12 16.05 15.99 14.31"
       ]
      }
     ],
     "prompt_number": 46
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ds.apply(np.sin)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 47,
       "text": [
        "<xray.Dataset>\n",
        "Dimensions:      (x: 8, y: 8, z: 10)\n",
        "Index Coordinates:\n",
        "    x            (x) int64 0 1 2 3 4 5 6 7\n",
        "    y            (y) int64 0 1 2 3 4 5 6 7\n",
        "    z            (z) int64 0 100 200 300 400 500 600 700 800 900\n",
        "Other Coordinates:\n",
        "    lon          (x, y) float64 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 -100.0 ...\n",
        "    lat          (x, y) float64 30.0 32.86 35.71 38.57 41.43 44.29 47.14 50.0 30.0 32.86 ...\n",
        "    time         datetime64[ns] 2014-09-05\n",
        "Variables:\n",
        "    temperature  (x, y, z) float64 -0.3139 -0.7765 0.9856 0.9604 -0.6228 0.674 ...\n",
        "    pressure     (x, y, z) float64 0.2739 0.6424 0.564 0.8372 0.7726 0.503 0.9845 0.7122 ..."
       ]
      }
     ],
     "prompt_number": 47
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Not yet implemented:"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "`2 * ds\n",
      "ds + ds2\n",
      "ds + foo`"
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Needs `__numpy_ufunc__` (not until numpy 1.10):"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "`np.sin(ds)`"
     ]
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Convert to `DataFrame`"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = ds.to_dataframe()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 48
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th>temperature</th>\n",
        "      <th>pressure</th>\n",
        "      <th>lat</th>\n",
        "      <th>lon</th>\n",
        "      <th>time</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>x</th>\n",
        "      <th>y</th>\n",
        "      <th>z</th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th rowspan=\"5\" valign=\"top\">0</th>\n",
        "      <th rowspan=\"5\" valign=\"top\">0</th>\n",
        "      <th>0  </th>\n",
        "      <td>-15.388713</td>\n",
        "      <td> 0.277440</td>\n",
        "      <td> 30</td>\n",
        "      <td>-100</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>100</th>\n",
        "      <td> -7.172265</td>\n",
        "      <td> 0.697573</td>\n",
        "      <td> 30</td>\n",
        "      <td>-100</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>200</th>\n",
        "      <td>  1.400982</td>\n",
        "      <td> 0.599262</td>\n",
        "      <td> 30</td>\n",
        "      <td>-100</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>300</th>\n",
        "      <td> 14.419699</td>\n",
        "      <td> 0.992163</td>\n",
        "      <td> 30</td>\n",
        "      <td>-100</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>400</th>\n",
        "      <td>  5.610915</td>\n",
        "      <td> 0.882857</td>\n",
        "      <td> 30</td>\n",
        "      <td>-100</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <th>...</th>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th rowspan=\"5\" valign=\"top\">7</th>\n",
        "      <th rowspan=\"5\" valign=\"top\">7</th>\n",
        "      <th>500</th>\n",
        "      <td> 21.642049</td>\n",
        "      <td> 1.550781</td>\n",
        "      <td> 50</td>\n",
        "      <td> -80</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>600</th>\n",
        "      <td> 36.137462</td>\n",
        "      <td> 1.393358</td>\n",
        "      <td> 50</td>\n",
        "      <td> -80</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>700</th>\n",
        "      <td> 36.190543</td>\n",
        "      <td> 1.540833</td>\n",
        "      <td> 50</td>\n",
        "      <td> -80</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>800</th>\n",
        "      <td> 36.723749</td>\n",
        "      <td> 1.265896</td>\n",
        "      <td> 50</td>\n",
        "      <td> -80</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>900</th>\n",
        "      <td> 21.125450</td>\n",
        "      <td> 1.273941</td>\n",
        "      <td> 50</td>\n",
        "      <td> -80</td>\n",
        "      <td>2014-09-05</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>640 rows \u00d7 5 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 49,
       "text": [
        "         temperature  pressure  lat  lon       time\n",
        "x y z                                              \n",
        "0 0 0     -15.388713  0.277440   30 -100 2014-09-05\n",
        "    100    -7.172265  0.697573   30 -100 2014-09-05\n",
        "    200     1.400982  0.599262   30 -100 2014-09-05\n",
        "    300    14.419699  0.992163   30 -100 2014-09-05\n",
        "    400     5.610915  0.882857   30 -100 2014-09-05\n",
        "...              ...       ...  ...  ...        ...\n",
        "7 7 500    21.642049  1.550781   50  -80 2014-09-05\n",
        "    600    36.137462  1.393358   50  -80 2014-09-05\n",
        "    700    36.190543  1.540833   50  -80 2014-09-05\n",
        "    800    36.723749  1.265896   50  -80 2014-09-05\n",
        "    900    21.125450  1.273941   50  -80 2014-09-05\n",
        "\n",
        "[640 rows x 5 columns]"
       ]
      }
     ],
     "prompt_number": 49
    },
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "Use standard libraries like Seaborn"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import seaborn as sns"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 50
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sns.pairplot(ds.to_dataframe(), vars=ds, hue='lat', palette='cubehelix', size=4);"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAqMAAAI5CAYAAACVYjNNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10a5ff4d0>"
       ]
      }
     ],
     "prompt_number": 51
    }
   ],
   "metadata": {}
  }
 ]
}