python裁剪nc文件数据

问题描述：

若干个nc文件储存全球的1850-2014年月尺度的mrro数据(或其他数据)，从1850-1到2014-12一共1980个月，要提取出最后35年1980.1~2014.12年也就是420个月的数据。

代码实现

def aaa(input_file,output_file,bianliang,start_index,end_index):# 打开输入NetCDF文件ds = nc.Dataset(input_file, 'r')# 获取时间变量和mrro变量 这里不一定是mrro变量，名称由传入参数bianliang确定time_var = ds.variables['time']mrro_var = ds.variables[bianliang]time_indices = np.arange(start_index, end_index)time_data = time_var[time_indices]mrro_data = mrro_var[time_indices, :, :] # 创建新的NetCDF文件new_ds = nc.Dataset(output_file, 'w', format='NETCDF4')# 创建维度（这些在新数据集中还不存在）new_ds.createDimension('time', None)  # 可变长度维度，或者指定确切长度len(time_data)lat_dim = new_ds.createDimension('lat', len(ds.dimensions['lat']))lon_dim = new_ds.createDimension('lon', len(ds.dimensions['lon']))# 创建新变量times = new_ds.createVariable('time', time_var.datatype, ('time',))lats = new_ds.createVariable('lat', ds.variables['lat'].datatype, ('lat',))lons = new_ds.createVariable('lon', ds.variables['lon'].datatype, ('lon',))mrro = new_ds.createVariable(bianliang, mrro_var.datatype, ('time', 'lat', 'lon'))# 复制变量属性times.setncatts({k: time_var.getncattr(k) for k in time_var.ncattrs()})lats.setncatts({k: ds.variables['lat'].getncattr(k) for k in ds.variables['lat'].ncattrs()})lons.setncatts({k: ds.variables['lon'].getncattr(k) for k in ds.variables['lon'].ncattrs()})mrro.setncatts({k: mrro_var.getncattr(k) for k in mrro_var.ncattrs()})# 写入数据times[:] = time_data  # 确保time_data是正确的！lats[:] = ds.variables['lat'][:]lons[:] = ds.variables['lon'][:]mrro[:] = mrro_data  # 确保mrro_data是正确的！# 复制全局属性new_ds.setncatts({k: ds.getncattr(k) for k in ds.ncattrs() if k != 'history'})  # 避免覆盖我们即将设置的历史属性# 更新历史属性history = "Created by subsetting the original dataset"  # 原始数据集的历史属性可能不包含有用的信息，或者我们想要添加新的信息new_ds.setncattr('history', history)# 关闭文件new_ds.close()ds.close()print("完成")
import glob
import netCDF4 as nc
import numpy as np
import osdef get_nc_files(directory):# 使用 os.path.join 确保路径格式正确pattern = os.path.join(directory, '*.nc')nc_files = glob.glob(pattern)# 如果只需要文件名而不是完整路径，可以使用 os.path.basename 提取nc_files = [os.path.basename(file) for file in nc_files]return nc_filesstart_index = 1560  # 数据起点
end_index = 1980  # 数据终点
directory_path = './'
nc_files_list = get_nc_files(directory_path)
for ncfile in nc_files_list:print(ncfile)input_file = ncfiles  = ''s += str(ncfile)output_file = s.replace('185001', '198001')bianliang = input_file.split('_')[0] # 根据文件名称获取变量名aaa(input_file,output_file,bianliang,start_index,end_index)