def encode(self, dataset, params: EncoderParams):
cache_key = CacheHandler.generate_cache_key(
self._prepare_caching_params(dataset, params))
encoded_dataset = CacheHandler.memo(
cache_key, lambda: self._encode_new_dataset(dataset, params))
return encoded_dataset
def run(input_params: DataSplitterParams = None):
cache_key = CacheHandler.generate_cache_key(
DataSplitter._prepare_caching_params(input_params))
fn = getattr(
DataSplitter,
"{}_split".format(input_params.split_strategy.name.lower()))
datasets = CacheHandler.memo(cache_key, lambda: fn(input_params))
return datasets
def test_memo(self):
fn = lambda: "abc"
cache_key = "a123"
obj = CacheHandler.memo(cache_key, fn)
self.assertEqual("abc", obj)
os.remove(
CacheHandler._build_filename(cache_key, CacheObjectType.OTHER))
def test_memo_with_object_type(self):
fn = lambda: "abc"
cache_key = "a123"
obj = CacheHandler.memo(cache_key, fn, CacheObjectType.ENCODING)
self.assertEqual("abc", obj)
self.assertTrue(
os.path.isfile(EnvironmentSettings.get_cache_path() /
f"encoding/{cache_key}.pickle"))
os.remove(
CacheHandler._build_filename(cache_key, CacheObjectType.ENCODING))