ICESat2学习笔记10 ：python批量读取处理ATL08数据

在ICESat2学习笔记9 ：python读取ATL08数据基础上，完成批量处理工作：

import icepyx as ipx
import numpy as np
import pandas as pd
import h5py
import os,json
from pprint import pprint
import dask.dataframe as dd

# put the full filepath to a data file here. You can get this in JupyterHub by navigating to the file,
# right clicking, and selecting copy path. Then you can paste the path in the quotes below.
def read_atl08(fname, bbox=None):
    """ 
    Read 1 ATL08 file and output 6 reduced files. 
    
    Extract variables of interest and separate the ATL08 file 
    into each beam (ground track) and ascending/descending orbits.
    """

    # Each beam is a group
    group = ['/gt1l', '/gt1r', '/gt2l', '/gt2r', '/gt3l', '/gt3r']

    # Loop trough beams
    for k,g in enumerate(group):
    
        #-----------------------------------#
        # 1) Read in data for a single beam #
        #-----------------------------------#
    
        # Load variables into memory (more can be added!)
        with h5py.File(fname, 'r') as fi:
            lat = fi[g+'/land_segments/latitude'][:]
            lon = fi[g+'/land_segments/longitude'][:]
            canopy_h_metrics = fi[g+'/land_segments/canopy/canopy_h_metrics'][:]
            canopy_openness = fi[g+'/land_segments/canopy/canopy_openness'][:]


        #---------------------------------------------#
        # 2) Filter data according region and quality #
        #---------------------------------------------#
        
        # Select a region of interest
        if bbox:
            lonmin, lonmax, latmin, latmax = bbox
            bbox_mask = (lon >= lonmin) & (lon <= lonmax) & \
                        (lat >= latmin) & (lat <= latmax)
        else:
            bbox_mask = np.ones_like(lat, dtype=bool)  # get all
            
        # Only keep good data, and data inside bbox
        #mask = (q_flag == 0) & (np.abs(h_li) < 10e3) & (bbox_mask == 1)
        

        # Test for no data
        if len(canopy_h_metrics) == 0: continue    
        
        # Define output file name
        ofile = fname.replace('.h5', '_'+g[1:]+'.h5')
                
        # Save variables
        with h5py.File(ofile, 'w') as f:
            f['lon'] = lon
            f['lat'] = lat
            f['canopy_h_metrics'] = canopy_h_metrics
            f['canopy_openness'] = canopy_openness
            print('out ->', ofile)
        # save as csv
        ofilecsv = fname.replace('.h5', '_'+g[1:]+'.csv')
        result = pd.DataFrame()
        result['lon'] = lon
        result['lat'] = lat
        result['canopy_h_metrics_0'] = canopy_h_metrics[:,0]
        result['canopy_h_metrics_1'] = canopy_h_metrics[:,1]
        result['canopy_h_metrics_2'] = canopy_h_metrics[:,2]
        result['canopy_h_metrics_3'] = canopy_h_metrics[:,3]
        result['canopy_h_metrics_4'] = canopy_h_metrics[:,4]
        result['canopy_h_metrics_5'] = canopy_h_metrics[:,5]
        result['canopy_h_metrics_6'] = canopy_h_metrics[:,6]
        result['canopy_h_metrics_7'] = canopy_h_metrics[:,7]
        result['canopy_h_metrics_8'] = canopy_h_metrics[:,8]
        result['canopy_openness'] = canopy_openness
        print('out ->', ofilecsv)
        result.to_csv(ofilecsv,index=None)

# 输入参数为h5文件所在目录
def readMultiH5(dir):
    dfs = []
    # 遍历文件目录，将所有文件类型为h5的文件处理
    # for root_dir, sub_dir, files in os.walk(r'' + dir): 
    # 第一个为起始路径，第二个为起始路径下的文件夹，第三个是起始路径下的文件。
    for root_dir,sub_dir,files in os.walk(dir):
        for file in files:
            if file.endswith('h5'):
                #构造绝对路径
                file_name = os.path.join(root_dir,file)
                read_atl08(file_name, None)

#调用并执行
root_dir = r'G:\6.ICESat2 data\5000000951831-08'
readMultiH5(root_dir)