Problema Intentando crear estadísticas zonales usando Gdal y Python.

Question

Estoy tratando de crear zonal estadísticas de uso de Python y Gdal. Tengo un shapefile de polígonos y un archivo raster, y con el fin de hacerlo, estoy usando un pedazo de código que he encontrado en StackExchange.

La trama y shapefile que se utiliza puede ser encontrado aquí

Este es el código que estoy usando:

#!/usr/bin/python
#coding: utf-8

## Code from Stack Exchange: http://gis.stackexchange.com/questions/21888/how-to-overlay-shapefile-and-raster
## User: ustroetz

# Calculates statistics (mean) on values of a raster within the zones of an polygon shapefile

import gdal, ogr, osr, numpy

def zonal_stats(input_value_raster, input_zone_polygon):



 # Open data
    raster = gdal.Open(input_value_raster)
    driver = ogr.GetDriverByName('ESRI Shapefile')
    shp = driver.Open(input_zone_polygon)
    lyr = shp.GetLayer()

    # get raster georeference info
    transform = raster.GetGeoTransform()
    xOrigin = transform[0]
    yOrigin = transform[3]
    pixelWidth = transform[1]
    pixelHeight = transform[5]

    # reproject geometry to same projection as raster
    sourceSR = lyr.GetSpatialRef()
    targetSR = osr.SpatialReference()
    targetSR.ImportFromWkt(raster.GetProjectionRef())
    coordTrans = osr.CoordinateTransformation(sourceSR,targetSR)
    feat = lyr.GetNextFeature()
    geom = feat.GetGeometryRef()
    geom.Transform(coordTrans)

    # Get extent of geometry
    ring = geom.GetGeometryRef(0)
    numpoints = ring.GetPointCount()
    pointsX = []; pointsY = []
    for p in range(numpoints):
            lon, lat, z = ring.GetPoint(p)
            pointsX.append(lon)
            pointsY.append(lat)
    xmin = min(pointsX)
    xmax = max(pointsX)
    ymin = min(pointsY)
    ymax = max(pointsY)

    # Specify offset and rows and columns to read
    xoff = int((xmin - xOrigin)/pixelWidth)
    yoff = int((yOrigin - ymax)/pixelWidth)
    xcount = int((xmax - xmin)/pixelWidth)+1
    ycount = int((ymax - ymin)/pixelWidth)+1


    # create memory target raster
    target_ds = gdal.GetDriverByName('MEM').Create('', xcount, ycount, gdal.GDT_Byte)
    target_ds.SetGeoTransform((
        xmin, pixelWidth, 0,
        ymax, 0, pixelHeight,
    ))

    # create for target raster the same projection as for the value raster
    raster_srs = osr.SpatialReference()
    raster_srs.ImportFromWkt(raster.GetProjectionRef())
    target_ds.SetProjection(raster_srs.ExportToWkt())

    # rasterize zone polygon to raster
    gdal.RasterizeLayer(target_ds, [1], lyr, burn_values=[1])

    # read raster as arrays
    banddataraster = raster.GetRasterBand(1)
    dataraster = banddataraster.ReadAsArray(xoff, yoff, xcount, ycount).astype(numpy.float)

    bandmask = target_ds.GetRasterBand(1)
    datamask = bandmask.ReadAsArray(0, 0, xcount, ycount).astype(numpy.float)

    # mask zone of raster
    zoneraster = numpy.ma.masked_array(dataraster,  numpy.logical_not(datamask))

    # calculate mean of zonal raster
    return numpy.mean(zoneraster) 

Sin embargo, cuando la práctica, a la salida (numpy.media(zoneraster)) es sólo un número y no una matriz o una trama. Lo que me estoy perdiendo? Hay algo mal con los archivos de entrada? El código?

Answer 1

¡Con multiprocesamiento, por solidez! Tiene un formato de salida diferente.

 #!/usr/bin/python
import gdal, ogr, osr, numpy, sys
from multiprocessing import Pool


# Raster dataset
input_value_raster = sys.argv[1]

# Vector dataset(zones)
input_zone_polygon = sys.argv[2]

# Open data
rast = gdal.Open(input_value_raster)
shp = ogr.Open(input_zone_polygon)

# Get raster georeference info
transform = rast.GetGeoTransform()
xOrigin = transform[0]
yOrigin = transform[3]
pixelWidth = transform[1]
pixelHeight = transform[5]

def proc(fid):

    # Each process needs its own pointer it seems.
    shape = ogr.Open(input_zone_polygon)
    lyr = shape.GetLayer()
    feat = lyr.GetFeature(fid)
    raster = gdal.Open(input_value_raster)

    # Get extent of feat
    geom = feat.GetGeometryRef()
    if (geom.GetGeometryName() == 'MULTIPOLYGON'):
        count = 0
        pointsX = []; pointsY = []
        for polygon in geom:
            geomInner = geom.GetGeometryRef(count)    
            ring = geomInner.GetGeometryRef(0)
            numpoints = ring.GetPointCount()
            for p in range(numpoints):
                    lon, lat, z = ring.GetPoint(p)
                    pointsX.append(lon)
                    pointsY.append(lat)    
            count += 1
    elif (geom.GetGeometryName() == 'POLYGON'):
        ring = geom.GetGeometryRef(0)
        numpoints = ring.GetPointCount()
        pointsX = []; pointsY = []
        for p in range(numpoints):
                lon, lat, z = ring.GetPoint(p)
                pointsX.append(lon)
                pointsY.append(lat)

    else:
        sys.exit()

    xmin = min(pointsX)
    xmax = max(pointsX)
    ymin = min(pointsY)
    ymax = max(pointsY)

    # Specify offset and rows and columns to read
    xoff = int((xmin - xOrigin)/pixelWidth)
    yoff = int((yOrigin - ymax)/pixelWidth)
    xcount = int((xmax - xmin)/pixelWidth)+1
    ycount = int((ymax - ymin)/pixelWidth)+1

    # Create memory target raster
    target_ds = gdal.GetDriverByName('MEM').Create('', xcount, ycount, gdal.GDT_Byte)
    target_ds.SetGeoTransform((
        xmin, pixelWidth, 0,
        ymax, 0, pixelHeight,
    ))

    # Create for target raster the same projection as for the value raster
    raster_srs = osr.SpatialReference()
    raster_srs.ImportFromWkt(raster.GetProjectionRef())
    target_ds.SetProjection(raster_srs.ExportToWkt())

    # Rasterize zone polygon to raster
    gdal.RasterizeLayer(target_ds, [1], lyr, burn_values=[1])

    # Read raster as arrays
    banddataraster = raster.GetRasterBand(1)
    dataraster = banddataraster.ReadAsArray(xoff, yoff, xcount, ycount).astype(numpy.float)

    bandmask = target_ds.GetRasterBand(1)
    datamask = bandmask.ReadAsArray(0, 0, xcount, ycount).astype(numpy.float)

    # Mask zone of raster
    zoneraster = numpy.ma.masked_array(dataraster,  numpy.logical_not(datamask))

    # Calculate statistics of zonal raster
    value = numpy.max(zoneraster)
    #print value
    return str(fid)+": "+str(value)


# Start the processes
layer = shp.GetLayer()
featList = range(layer.GetFeatureCount())
pool = Pool(processes=24)   
print pool.map(proc,featList,8)




 

Answer 2

Si desea obtener zonal estadísticas varias características en un shapefile, tiene un bucle en el zonal_stats función. Usted puede escribir los resultados del bucle, por ejemplo, para un diccionario. A continuación es la versión modificada de la zonal_stats función junto con un bucle, bucle sobre la entrada del shapefile. Como salida se obtiene un Diccionario que contiene para cada Característica de IDENTIFICACIÓN de la media de la cubierta de la trama.

Para su conjunto de datos de ejemplo el diccionario de los primeros cinco características tiene este aspecto

{0: 114.57909872798288, 1: 21.889622561136882, 2: 287.79623686237102, 3: 35.350804240486838, 4: 19.63043032511781}

Las dos funciones:

import gdal, ogr, osr, numpy


def zonal_stats(feat, input_zone_polygon, input_value_raster):

    # Open data
    raster = gdal.Open(input_value_raster)
    shp = ogr.Open(input_zone_polygon)
    lyr = shp.GetLayer()

    # Get raster georeference info
    transform = raster.GetGeoTransform()
    xOrigin = transform[0]
    yOrigin = transform[3]
    pixelWidth = transform[1]
    pixelHeight = transform[5]

    # Get extent of feat
    geom = feat.GetGeometryRef()
    if (geom.GetGeometryName() == 'MULTIPOLYGON'):
        count = 0
        pointsX = []; pointsY = []
        for polygon in geom:
            geomInner = geom.GetGeometryRef(count)    
            ring = geomInner.GetGeometryRef(0)
            numpoints = ring.GetPointCount()
            for p in range(numpoints):
                    lon, lat, z = ring.GetPoint(p)
                    pointsX.append(lon)
                    pointsY.append(lat)    
            count += 1
    elif (geom.GetGeometryName() == 'POLYGON'):
        ring = geom.GetGeometryRef(0)
        numpoints = ring.GetPointCount()
        pointsX = []; pointsY = []
        for p in range(numpoints):
                lon, lat, z = ring.GetPoint(p)
                pointsX.append(lon)
                pointsY.append(lat)

    else:
        sys.exit()

    xmin = min(pointsX)
    xmax = max(pointsX)
    ymin = min(pointsY)
    ymax = max(pointsY)

    # Specify offset and rows and columns to read
    xoff = int((xmin - xOrigin)/pixelWidth)
    yoff = int((yOrigin - ymax)/pixelWidth)
    xcount = int((xmax - xmin)/pixelWidth)+1
    ycount = int((ymax - ymin)/pixelWidth)+1

    # Create memory target raster
    target_ds = gdal.GetDriverByName('MEM').Create('', xcount, ycount, gdal.GDT_Byte)
    target_ds.SetGeoTransform((
        xmin, pixelWidth, 0,
        ymax, 0, pixelHeight,
    ))

    # Create for target raster the same projection as for the value raster
    raster_srs = osr.SpatialReference()
    raster_srs.ImportFromWkt(raster.GetProjectionRef())
    target_ds.SetProjection(raster_srs.ExportToWkt())

    # Rasterize zone polygon to raster
    gdal.RasterizeLayer(target_ds, [1], lyr, burn_values=[1])

    # Read raster as arrays
    banddataraster = raster.GetRasterBand(1)
    dataraster = banddataraster.ReadAsArray(xoff, yoff, xcount, ycount).astype(numpy.float)

    bandmask = target_ds.GetRasterBand(1)
    datamask = bandmask.ReadAsArray(0, 0, xcount, ycount).astype(numpy.float)

    # Mask zone of raster
    zoneraster = numpy.ma.masked_array(dataraster,  numpy.logical_not(datamask))

    # Calculate statistics of zonal raster
    return numpy.mean(zoneraster)


def loop_zonal_stats(input_zone_polygon, input_value_raster):

    shp = ogr.Open(input_zone_polygon)
    lyr = shp.GetLayer()
    featList = range(lyr.GetFeatureCount())
    statDict = {}

    for FID in featList:
        feat = lyr.GetFeature(FID)
        meanValue = zonal_stats(feat, input_zone_polygon, input_value_raster)
        statDict[FID] = meanValue
    return statDict



# Raster dataset
input_value_raster = 'popc_0ADProj.tif'
# Vector dataset(zones)
input_zone_polygon = 'borders_tribes.shp'

print loop_zonal_stats(input_zone_polygon, input_value_raster)