gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Input : http://data.wri.org/Aqueduct/web/aqueduct_global_maps_21_shp.zip\n",
      "Output s3: s3://wri-projects/Aqueduct30/qaData/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/output_V01\n"
     ]
    }
   ],
   "source": [
    "\"\"\" Create Aqueduct 2.1 shapefile with fluxes. \n",
    "-------------------------------------------------------------------------------\n",
    "\n",
    "Author: Rutger Hofste\n",
    "Date: 20180605\n",
    "Kernel: python35\n",
    "Docker: rutgerhofste/gisdocker:ubuntu16.04\n",
    "\n",
    "Args:\n",
    "\n",
    "    TESTING (boolean) : Testing mode. Uses a smaller geography if enabled.\n",
    "    \n",
    "    SCRIPT_NAME (string) : Script name.\n",
    "    EE_INPUT_ZONES_PATH (string) : earthengine input path for zones.\n",
    "    EE_INPUT_VALUES_PATH (string) : earthengine input path for value images.\n",
    "    INPUT_VERSION_ZONES (integer) : input version for zones images.\n",
    "    INPUT_VERSION_VALUES (integer) : input version for value images.\n",
    "    OUTPUT_VERSION (integer) : output version. \n",
    "    EXTRA_PROPERTIES (dictionary) : Extra properties to store in the resulting\n",
    "        pandas dataframe. \n",
    "    \n",
    "\n",
    "Returns:\n",
    "\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "SCRIPT_NAME = \"Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01\"\n",
    "OUTPUT_VERSION = 1\n",
    "OVERWRITE =1 \n",
    "\n",
    "AQUEDUCT21_URL = \"http://data.wri.org/Aqueduct/web/aqueduct_global_maps_21_shp.zip\"\n",
    "FILE_NAME = \"aqueduct21\"\n",
    "DETAILED_FILE_NAME = \"aqueduct_global_dl_20150409.shp\"\n",
    "\n",
    "\n",
    "ECKERT_IV_PROJ4_STRING1 = \"+proj=eck4 +lon_0=0 +x_0=0 +y_0=0 +datum=WGS84 +units=m +no_defs\"\n",
    "ECKERT_IV_PROJ4_STRING2 = \"+proj=eck4 +lon_0=0 +x_0=0 +y_0=0 +ellps=WGS84 +datum=WGS84 +units=m no_defs\"\n",
    "\n",
    "s3_output_path = \"s3://wri-projects/Aqueduct30/qaData/{}/output_V{:02.0f}\".format(SCRIPT_NAME,OUTPUT_VERSION)\n",
    "ec2_input_path = \"/volumes/data/{}/input_V{:02.0f}\".format(SCRIPT_NAME,OUTPUT_VERSION)\n",
    "ec2_output_path = \"/volumes/data/{}/output_V{:02.0f}\".format(SCRIPT_NAME,OUTPUT_VERSION) \n",
    "\n",
    "\n",
    "print(\"Input : \" + AQUEDUCT21_URL +\n",
    "      \"\\nOutput s3: \" + s3_output_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Y2018M06D05 UTC 14:30\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'3.5.4 |Anaconda, Inc.| (default, Nov 20 2017, 18:44:38) \\n[GCC 7.2.0]'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import time, datetime, sys, logging\n",
    "dateString = time.strftime(\"Y%YM%mD%d\")\n",
    "timeString = time.strftime(\"UTC %H:%M\")\n",
    "start = datetime.datetime.now()\n",
    "print(dateString,timeString)\n",
    "sys.version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import subprocess\n",
    "import geopandas as gpd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "if OVERWRITE:\n",
    "    !rm -r {ec2_input_path}\n",
    "    !rm -r {ec2_output_path}\n",
    "    !mkdir -p {ec2_input_path}\n",
    "    !mkdir -p {ec2_output_path}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b''"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "command = \"wget -O {}/{}.zip {}\".format(ec2_input_path,FILE_NAME,AQUEDUCT21_URL)\n",
    "subprocess.check_output(command,shell=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'Archive:  /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct21.zip\\n extracting: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.cpg  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.dbf  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.prj  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.shp  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.shp.xml  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_dl_20150409.shx  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/aqueduct_global_maps_21.pdf  \\n  inflating: /volumes/data/Y2018M06D05_RH_QA_Aqueduct21_Flux_Shapefile_V01/input_V01/dictionary_20150409.xlsx  \\n'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "command = \"unzip {}/{} -d {}\".format(ec2_input_path,FILE_NAME,ec2_input_path)\n",
    "subprocess.check_output(command,shell=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_file_path = \"{}/{}\".format(ec2_input_path,DETAILED_FILE_NAME)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "gdf = gpd.read_file(input_file_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:4326'}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gdf.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "gdf_eckert4 = gdf.to_crs(ECKERT_IV_PROJ4_STRING1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "ename": "RuntimeError",
     "evalue": "b'unknown unit conversion id'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-11-419049ecf17f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgdf_eckert4\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_crs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mECKERT_IV_PROJ4_STRING2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/opt/anaconda3/envs/python35/lib/python3.5/site-packages/geopandas/geodataframe.py\u001b[0m in \u001b[0;36mto_crs\u001b[0;34m(self, crs, epsg, inplace)\u001b[0m\n\u001b[1;32m    384\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    385\u001b[0m             \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 386\u001b[0;31m         \u001b[0mgeom\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgeometry\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_crs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcrs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepsg\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mepsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    387\u001b[0m         \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgeometry\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgeom\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    388\u001b[0m         \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgeom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/python35/lib/python3.5/site-packages/geopandas/geoseries.py\u001b[0m in \u001b[0;36mto_crs\u001b[0;34m(self, crs, epsg)\u001b[0m\n\u001b[1;32m    284\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Must set either crs or epsg for output.'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    285\u001b[0m         \u001b[0mproj_in\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpyproj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mProj\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpreserve_units\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 286\u001b[0;31m         \u001b[0mproj_out\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpyproj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mProj\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcrs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpreserve_units\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    287\u001b[0m         \u001b[0mproject\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpartial\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpyproj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproj_in\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproj_out\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    288\u001b[0m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mgeom\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtransform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mproject\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgeom\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/python35/lib/python3.5/site-packages/pyproj/__init__.py\u001b[0m in \u001b[0;36m__new__\u001b[0;34m(self, projparams, preserve_units, **kwargs)\u001b[0m\n\u001b[1;32m    356\u001b[0m         \u001b[0;31m# on case-insensitive filesystems).\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    357\u001b[0m         \u001b[0mprojstring\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mprojstring\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreplace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'EPSG'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'epsg'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 358\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_proj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mProj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__new__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprojstring\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    359\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    360\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkw\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m_proj.pyx\u001b[0m in \u001b[0;36m_proj.Proj.__cinit__ (_proj.c:1170)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mRuntimeError\u001b[0m: b'unknown unit conversion id'"
     ]
    }
   ],
   "source": [
    "gdf_eckert4 = gdf.to_crs(ECKERT_IV_PROJ4_STRING2)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 35",
   "language": "python",
   "name": "python35"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}