complex reclassification example

complexreclassificationexample.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# complex reclassification example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### gin up some sample data "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Replace this with code to read in a numpy array from your raster file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[83, 83, 76, 63, 69, 83, 83, 60, 83, 75],\n",
       "       [83, 67, 83, 76, 73, 83, 65, 83, 83, 83],\n",
       "       [83, 62, 75, 83, 83, 83, 71, 74, 71, 83],\n",
       "       [83, 83, 83, 76, 60, 63, 83, 83, 83, 83],\n",
       "       [62, 70, 72, 83, 83, 83, 73, 77, 83, 83],\n",
       "       [83, 83, 83, 83, 83, 80, 83, 83, 83, 83],\n",
       "       [76, 83, 83, 83, 83, 70, 83, 83, 83, 75],\n",
       "       [77, 83, 83, 73, 60, 83, 83, 83, 83, 83],\n",
       "       [65, 67, 83, 83, 83, 83, 83, 83, 83, 64],\n",
       "       [83, 83, 83, 83, 82, 83, 69, 69, 80, 83]])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = np.random.randint(60,83, size=(10,10))\n",
    "#make a bunch more 83\n",
    "data[np.random.choice([True, False], data.shape)] = 83\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7f34e10>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPgAAAD8CAYAAABaQGkdAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x4571a90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "plt.imshow(data)\n",
    "#yellow below are ag"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "crop_types = ['corn', 'wheat', 'other']\n",
    "crop_types_int = [1, 2, 3]\n",
    "crop_probs = [0.15, 0.2, 0.65]\n",
    "data[data==83] = np.random.choice(crop_types_int, len(data[data==83]), p=crop_probs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 2,  1, 76, 63, 69,  1,  1, 60,  3, 75],\n",
       "       [ 1, 67,  2, 76, 73,  3, 65,  2,  3,  1],\n",
       "       [ 1, 62, 75,  3,  1,  3, 71, 74, 71,  1],\n",
       "       [ 2,  3,  3, 76, 60, 63,  3,  2,  3,  3],\n",
       "       [62, 70, 72,  3,  3,  3, 73, 77,  3,  2],\n",
       "       [ 1,  3,  1,  2,  1, 80,  3,  3,  2,  3],\n",
       "       [76,  1,  2,  3,  2, 70,  3,  3,  3, 75],\n",
       "       [77,  2,  3, 73, 60,  2,  3,  3,  3,  3],\n",
       "       [65, 67,  2,  3,  3,  2,  3,  1,  2, 64],\n",
       "       [ 2,  3,  3,  2, 82,  3, 69, 69, 80,  3]])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.colorbar.Colorbar at 0x8021400>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAR4AAAD8CAYAAAChMsvrAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nqO5/AVx38MHQgoCOAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f6b978>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "im = plt.imshow(data,  clim=(0, 5), cmap=mpl.cm.viridis_r)\n",
    "plt.colorbar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "####  Above the original 83's have been replaced with a new crop values proportionally"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Insert code here to write this array back out to a raster file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}