感谢 Martijn Pieters 的指导和更多阅读，我想出了以下代码作为演示。请注意，Reader 类使用 netcdf 文件和 netCDF4 库。如果您想自己尝试此代码，您将需要一个带有变量“a”和“b”的 netcdf 文件，或者将 Reader 替换为其他可以返回数据数组或数据数组切片的东西。
此解决方案定义了三个类：Reader 执行实际的文件 I/O 处理，Values 管理数据访问部分，如果内存中没有存储数据，则调用 Reader 实例，var 是实际的最终“变量”生活将包含更多的元数据。该代码包含一些用于教育目的的额外打印语句。
"""Implementation of a dynamic variable class which can read data from file when needed or
return the data values from memory if they were read already. This concepts supports
slicing for both memory and file access."""
import numpy as np
import netCDF4 as nc
FILENAME = r"C:\Users\m.schultz\Downloads\data\tmp\MACC_20141224_0001.nc"
VARNAME = "a"
class Reader(object):
"""Implements the actual data access to variable values. Here reading a
slice from a netcdf file.
"""
def __init__(self, filename, varname):
"""Final implementation will also have to take groups into account...
"""
self.filename = filename
self.varname = varname
def read(self, args=slice(None, None, None)):
"""Read a data slice. Args is a tuple of slice objects (e.g.
numpy.index_exp). The default corresponds to [:], i.e. all data
will be read.
"""
with nc.Dataset(self.filename, "r") as f:
values = f.variables[self.varname][args]
return values
class Values(object):
def __init__(self, values=None, reader=None):
"""Initialize Values. You can either pass numerical (or other) values,
preferrably as numpy array, or a reader instance which will read the
values on demand. The reader must have a read(args) method, where
args is a tuple of slices. If no args are given, all data should be
returned.
"""
if values is not None:
self._values = np.array(values)
self.reader = reader
def __getattr__(self, name):
"""This is only be called if attribute name is not present.
Here, the only attribute we care about is _values.
Self.reader should always be defined.
This method is necessary to allow access to variable.values without
a slicing index. If only __getitem__ were defined, one would always
have to write variable.values[:] in order to make sure that something
is returned.
"""
print ">>> in __getattr__, trying to access ", name
if name == "_values":
print ">>> calling reader and reading all values..."
self._values = self.reader.read()
return self._values
def __getitem__(self, args):
print "in __getitem__"
if not "_values" in self.__dict__:
values = self.reader.read(args)
print ">>> read from file. Shape = ", values.shape
if args == slice(None, None, None):
self._values = values # all data read, store in memory
return values
else:
print ">>> read from memory. Shape = ", self._values[args].shape
return self._values[args]
def __repr__(self):
return self._values.__repr__()
def __str__(self):
return self._values.__str__()
class var(object):
def __init__(self, name=VARNAME, filename=FILENAME, values=None):
self.name = name
self.values = Values(values, Reader(filename, name))
if __name__ == "__main__":
# define a variable and access all data first
# this will read the entire array and save it in memory, so that
# subsequent access with or without index returns data from memory
a = var("a", filename=FILENAME)
print "1: a.values = ", a.values
print "2: a.values[-1] = ", a.values[-1]
print "3: a.values = ", a.values
# define a second variable, where we access a data slice first
# In this case the Reader only reads the slice and no data are stored
# in memory. The second access indexes the complete array, so Reader
# will read everything and the data will be stored in memory.
# The last access will then use the data from memory.
b = var("b", filename=FILENAME)
print "4: b.values[0:3] = ", b.values[0:3]
print "5: b.values[:] = ", b.values[:]
print "6: b.values[5:8] = ",b.values[5:8]