稍后，hdf文件python中更多信息

Question

我有一个hdf文件，想要从中提取数据。由于某些原因，我无法提取纬度和经度值：

我尝试的代码是：

from pyhdf import SD
hdf = SD.SD('MOD10C2.A2001033.006.2016092173057.hdf')
data = hdf.select('Eight_Day_CMG_Snow_Cover')
lat = (hdf.select('Latitude'))[:]

它给了我一个错误：

HDF4Error: select: non-existent dataset

我尝试过：

lat = (hdf.select('Lat'))[:]

还是无济于事！

可以在此link中找到数据

任何帮助我们都将不胜感激！

数据格式如下：

我得到的错误是：

---------------------------------------------------------------------------
HDF4Error                                 Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/pyhdf/SD.py in select(self, name_or_index)
   1635             try:
-> 1636                 idx = self.nametoindex(name_or_index)
   1637             except HDF4Error:

~/anaconda3/lib/python3.6/site-packages/pyhdf/SD.py in nametoindex(self, sds_name)
   1528         sds_idx = _C.SDnametoindex(self._id, sds_name)
-> 1529         _checkErr('nametoindex', sds_idx, 'non existent SDS')
   1530         return sds_idx

~/anaconda3/lib/python3.6/site-packages/pyhdf/error.py in _checkErr(procName, val, msg)
     22             err = "%s : %s" % (procName, msg)
---> 23         raise HDF4Error(err)

HDF4Error: nametoindex : non existent SDS

During handling of the above exception, another exception occurred:

HDF4Error                                 Traceback (most recent call last)
<ipython-input-11-21e6a4fdf8eb> in <module>()
----> 1 hdf.select('Lat')

~/anaconda3/lib/python3.6/site-packages/pyhdf/SD.py in select(self, name_or_index)
   1636                 idx = self.nametoindex(name_or_index)
   1637             except HDF4Error:
-> 1638                 raise HDF4Error("select: non-existent dataset")
   1639         id = _C.SDselect(self._id, idx)
   1640         _checkErr('select', id, "cannot execute")

HDF4Error: select: non-existent dataset

​

​

Answer 1

您使用的数据文件是MODIS Level 3产品。所有3级产品都被插值到一些规则网格上。在MOD10C2的情况下，网格是所谓的气候建模网格。此栅格的间隔为0.05度。Panoply知道这一点。

CMG是柱面投影中的规则矩形网格。我们可以使用这些信息来对数据进行地理定位。考虑下面的例子。

from pyhdf import SD
import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.basemap import Basemap
from matplotlib.colors import LinearSegmentedColormap
hdf = SD.SD('MOD10C2.A2001033.006.2016092173057.hdf')
data = hdf.select('Eight_Day_CMG_Snow_Cover')
snowcover=np.array(data[:,:],np.float)
snowcover[np.where(snowcover==255)]=np.nan
m = Basemap(projection='cyl', resolution = 'l',
    llcrnrlat=-90, urcrnrlat=90,llcrnrlon=-180,urcrnrlon=180)
cdict = {'red' : [(0,0.,0.), (100./255.,1.,1.),(1.,0.,0.)],
         'green' : [(0,0.,0.),(1.,0.,0.)] , 
         'blue' : [(0,0.,0.),(100./255.,0.,0.),(1.,1.,1.)] }
blue_red = LinearSegmentedColormap('BlueRed',cdict)

m.drawcoastlines(linewidth=0.5)
m.drawparallels(np.arange(-90,120,30), labels=[1,0,0,0])
m.drawmeridians(np.arange(-180,181,45),labels=[0,0,0,1])
m.imshow(np.flipud(snowcover),cmap=blue_red)
plt.title('MOD10C2: Eight Day Global Snow Cover')
plt.show()

这段代码应该显示一张积雪的图片。

​

​

如果需要处理不同投影中的数据，可以使用python GDAL接口将snowcover数组转换为地理位置数据集。

将数据作为不规则网格处理也是可能的，但效率非常低。

lon,lat = np.meshgrid(np.arange(-180,180,0.05),np.arange(-90,90,0.05))

是对应的经度和纬度网格。

Answer 2

正常的纬度和经度信息不在hdf文件的科学模式中，这主要是因为lat = (hdf.select('Lat'))[:]不像其他变量一样工作。使用以下函数，您可以提取hdf文件中存储的任何类型的变量

from pyhdf.HDF import *
from pyhdf.V   import *
from pyhdf.VS  import *
from pyhdf.SD  import *

def HDFread(filename, variable, Class=None):
    """
    Extract the data for non scientific data in V mode of hdf file
    """
    hdf = HDF(filename, HC.READ)

    # Initialize the SD, V and VS interfaces on the file.
    sd = SD(filename)
    vs = hdf.vstart()
    v  = hdf.vgstart()

    # Encontrar el puto id de las Geolocation Fields
    if Class == None:
        ref = v.findclass('SWATH Vgroup')
    else:
        ref = v.findclass(Class)

    # Open all data of the class
    vg = v.attach(ref)
    # All fields in the class
    members = vg.tagrefs()

    nrecs = []
    names = []
    for tag, ref in members:
        # Vdata tag
        vd = vs.attach(ref)
        # nrecs, intmode, fields, size, name = vd.inquire()
        nrecs.append(vd.inquire()[0]) # number of records of the Vdata
        names.append(vd.inquire()[-1])# name of the Vdata
        vd.detach()

    idx = names.index(variable)
    var = vs.attach(members[idx][1])
    V   = var.read(nrecs[idx])
    var.detach()
    # Terminate V, VS and SD interfaces.
    v.end()
    vs.end()
    sd.end()
    # Close HDF file.
    hdf.close()

    return np.array(V).ravel()

如果您不知道确切的变量名，可以使用以下程序尝试使用whit，该程序显示任何pyhdf.V文件中包含的vgroup的内容。

from pyhdf.HDF import *
from pyhdf.V   import *
from pyhdf.VS  import *
from pyhdf.SD  import *

def describevg(refnum):
    # Describe the vgroup with the given refnum.
    # Open vgroup in read mode.
    vg = v.attach(refnum)
    print "----------------"
    print "name:", vg._name, "class:",vg._class, "tag,ref:",
    print vg._tag, vg._refnum

    # Show the number of members of each main object type.
    print "members: ", vg._nmembers,
    print "datasets:", vg.nrefs(HC.DFTAG_NDG),
    print "vdatas:  ", vg.nrefs(HC.DFTAG_VH),
    print "vgroups: ", vg.nrefs(HC.DFTAG_VG)

    # Read the contents of the vgroup.
    members = vg.tagrefs()

    # Display info about each member.
    index = -1
    for tag, ref in members:
        index += 1
        print "member index", index
        # Vdata tag
        if tag == HC.DFTAG_VH:
            vd = vs.attach(ref)
            nrecs, intmode, fields, size, name = vd.inquire()
            print "  vdata:",name, "tag,ref:",tag, ref
            print "    fields:",fields
            print "    nrecs:",nrecs
            vd.detach()

        # SDS tag
        elif tag == HC.DFTAG_NDG:
            sds = sd.select(sd.reftoindex(ref))
            name, rank, dims, type, nattrs = sds.info()
            print "  dataset:",name, "tag,ref:", tag, ref
            print "    dims:",dims
            print "    type:",type
            sds.endaccess()

        # VS tag
        elif tag == HC.DFTAG_VG:
            vg0 = v.attach(ref)
            print "  vgroup:", vg0._name, "tag,ref:", tag, ref
            vg0.detach()

        # Unhandled tag
        else:
            print "unhandled tag,ref",tag,ref

    # Close vgroup
    vg.detach()

# Open HDF file in readonly mode.
filename = 'yourfile.hdf'
hdf = HDF(filename)

# Initialize the SD, V and VS interfaces on the file.
sd = SD(filename)
vs = hdf.vstart()
v  = hdf.vgstart()

# Scan all vgroups in the file.
ref = -1
while 1:
    try:
        ref = v.getid(ref)
        print ref
    except HDF4Error,msg:    # no more vgroup
        break
    describevg(ref)

Answer 3

我认为问题在于这个文件没有传统的纬度和经度数据(像许多.nc文件一样)。当我想要处理MYD14数据时，我遇到了类似的问题(这是一个关于防火面具的MODIS文件)。我花了很长时间才找到答案。这是我的发现:1如果MODIS文件使用SIN-Grid(正弦投影)来定义数据，该文件将不会给你提供传统的经纬度数据。2有关正弦投影的更多详细信息，您可以阅读以下网站：https://code.env.duke.edu/projects/mget/wiki/SinusoidalMODIS