[Sample] Created a cached version of DelayedSampleSet

Fixed test case

bob/pipelines/__init__.py

@@ -3,7 +3,7 @@ from . import transformers  # noqa
 from . import utils  # noqa
 from . import xarray as xr  # noqa
 from .sample import DelayedSample
-from .sample import DelayedSampleSet
+from .sample import DelayedSampleSet, DelayedSampleSetCached
 from .sample import Sample
 from .sample import SampleSet
 from .sample import SampleBatch

bob/pipelines/sample.py

@@ -187,6 +187,21 @@ class DelayedSampleSet(SampleSet):
         return self._load()
 
 
+class DelayedSampleSetCached(DelayedSampleSet):
+    """A cached version of DelayedSampleSet"""
+
+    def __init__(self, load, parent=None, **kwargs):
+        super().__init__(load, parent=parent, kwargs=kwargs)
+        self._data = None
+        _copy_attributes(self, parent, kwargs)
+
+    @property
+    def samples(self):
+        if self._data is None:
+            self._data = self._load()
+        return self._data
+
+
 class SampleBatch(Sequence, _ReprMixin):
     """A batch of samples that looks like [s.data for s in samples]
 

bob/pipelines/tests/test_samples.py

@@ -8,7 +8,7 @@ import h5py
 import numpy as np
 
 from bob.pipelines import DelayedSample
-from bob.pipelines import DelayedSampleSet
+from bob.pipelines import DelayedSampleSet, DelayedSampleSetCached
 from bob.pipelines import Sample
 from bob.pipelines import SampleSet
 from bob.pipelines import hdf5_to_sample
@@ -56,6 +56,19 @@ def test_sampleset_collection():
         assert len(sampleset) == n_samples
         assert sampleset.samples == samples
 
+    # Testing delayed sampleset cached
+    with tempfile.TemporaryDirectory() as dir_name:
+
+        samples = [Sample(data, key=str(i)) for i, data in enumerate(X)]
+        filename = os.path.join(dir_name, "samples.pkl")
+        with open(filename, "wb") as f:
+            f.write(pickle.dumps(samples))
+
+        sampleset = DelayedSampleSetCached(functools.partial(_load, filename), key=1)
+
+        assert len(sampleset) == n_samples
+        assert sampleset.samples == samples
+
 
 def test_sample_hdf5():
     n_samples = 10

bob/pipelines/tests/test_wrappers.py

@@ -189,8 +189,9 @@ def test_checkpoint_function_sample_transfomer():
         )
 
         features = transformer.transform(samples)
-        # Checking if we have 8 chars in the second level
-        assert len(features[0]._load.args[0].split("/")[-2]) == 8
+        # Checking if we can cast the has as integer
+        assert isinstance(int(features[0]._load.args[0].split("/")[-2]), int)
+
         _assert_all_close_numpy_array(oracle, [s.data for s in features])