Skip to main content
 首页 » 编程设计

python之netCDF 到 *.csv 没有循环(!)

2024年11月01日9birdshome

我遇到了一些性能和“难看的代码”问题,也许你们中的一些人可以提供帮助。 我必须将数据从 netCDF 文件 导出到 *.csv。为此,我写了一些 python 代码。让我们使用一个 3-dim 的 netcdf 文件:

def to3dim_csv(): 
  var = ncf.variables['H2O'] #e.g. data for 'H2O' values 
  one,two,three = var.shape #variable dimension shape e.g. (551,42,94) 
  dim1,dim2,dim3 = var.dimensions #dimensions e.g. (time,lat,lon) 
 
  if crit is not None: 
    bool1 = foo(dim1,crit,ncf) #boolean table: ("value important?",TRUE,FALSE) 
    bool2 = foo(dim2,crit,ncf) 
    bool3 = foo(dim3,crit,ncf) 
 
  writer.writerow([dim1,dim2,dim3,varn]) 
  for i in range(one): 
    for k in range(two): 
      for l in range(three): 
        if bool1[i] and bool2[k] and bool3[l]: 
          writer.writerow([ 
                        ncf.variables[dim1][i], 
                        ncf.variables[dim2][k], 
                        ncf.variables[dim3][l], 
                        var[i,k,l], 
                        ]) 
  ofile.close() 
 
  # Sample csv output is like: 
  # time,lat,lon,H2O 
  # 1,90,10,100 
  # 1,90,11,90 
  # 1,91,10,101 

我想删除 for val in range(d): block 。也许使用递归函数,例如:

var = ncf.variables['H2O'] 
dims = [d for d in var.dimensions] 
shapes = [var.variables[d].shape for d in dims] 
bools = [bool_table(d,crit,ncf) for d in dims] 
dims.append('H2O') 
writer.writerow(dims) 
magic_function(data) 
 
def magic_function(data): 
 
   [enter code] 
 
   writer.writerow(data) 
   magic_function(left_data) 

更新: 对于任何有兴趣的人。这会立即生效...

def data_to_table(dataset, var): 
    assert isinstance(dataset,xr.Dataset), 'Dataset must be xarray.Dataset' 
    obj = getattr(dataset, var) 
    table = np.zeros((obj.data.size, obj.data.ndim+1), dtype=np.object_) 
    table[:,0] = obj.data.flat 
    for i,d in enumerate(obj.dims): 
        repeat = np.prod(obj.data.shape[i+1:]) 
        tile = np.prod(obj.data.shape[:i]) 
        dim = getattr(dataset, d) 
        dimdata = dim.data 
        dimdata = np.repeat(dimdata, repeat) 
        dimdata = np.tile(dimdata, tile) 
        table[:,i+1] = dimdata.flat 
    return table 
 
def export_to_csv(dataset, var, filename, size=None): 
    obj = getattr(dataset, var) 
    header = [var] + [x for x in obj.dims] 
    tabular = data_to_table(dataset, var) 
    size = slice(None,size,None) if size else slice(None,None,None) 
    with open(filename, 'w') as f: 
        writer = csv.writer(f,dialect=csv.excel) 
        writer.writerow(header) 
        writer.writerows(tabular[size]) 

请您参考如下方法:

是这样的。获取 bol1\2\3 的索引,并在获取相关值的同时将它们合并。

    with open('numpy.csv', 'wb') as f: 
        out_csv = csv.writer(f) 
        header = ['dim1','dim2','dim3','varn'] 
        out_csv.writerow(header) 
        bol1_indices = np.nonzero(bol1)[0] 
        bol2_indices = np.nonzero(bol2)[0] 
        bol3_indices = np.nonzero(bol3)[0] 
        out_csv.writerows(([a[i, k, l], dim1[i], dim2[k], dim3[l]] for i in bol1_indices for k in bol2_indices for  l in bol3_indices))