code-loader 1.0.193.dev5__tar.gz → 1.0.195__tar.gz

{code_loader-1.0.193.dev5 → code_loader-1.0.195}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.193.dev5
+Version: 1.0.195
 Summary: 
 Home-page: https://github.com/tensorleap/code-loader
 License: MIT

{code_loader-1.0.193.dev5 → code_loader-1.0.195}/code_loader/leaploader.py

@@ -568,8 +568,8 @@ class LeapLoader(LeapLoaderBase):
         return handler.input_shapes
 
     def run_simulation(self, sim_name, params=None, n_samples=1, seed=0,
-                       sample_ids=None, extend_preprocess=True):
-        # type: (str, Optional[Dict[str, Any]], int, int, Optional[List[str]], bool) -> Dict[str, Any]
+                       sample_ids=None, extend_preprocess=True, allow_partial=False):
+        # type: (str, Optional[Dict[str, Any]], int, int, Optional[List[str]], bool, bool) -> Dict[str, Any]
         # extend_preprocess=True (default): also extend preprocess_result[additional] with the
         # new synthetic sample_ids (producer-side behavior — synthetic worker needs this for
         # enumeration / data_length tracking). Pass False from consumer-side populators that
@@ -596,19 +596,30 @@ class LeapLoader(LeapLoaderBase):
         for sample_id in original_sample_ids:
             for handler in global_leap_binder.setup_container.inputs:
                 per_encoder[handler.name].append(handler.function(sample_id, sim_preprocess))
-        encoded = {name: np.stack(arrays) for name, arrays in per_encoder.items()}
+        encoded = {
+            name: np.stack(arrays) if arrays else np.empty((0,), dtype=np.float32)
+            for name, arrays in per_encoder.items()
+        }
         if sample_ids is not None:
-            if len(sample_ids) != len(original_sample_ids):
-                raise ValueError(
-                    "sample_ids length ({}) does not match simulation output length ({})".format(
-                        len(sample_ids), len(original_sample_ids)
-                    )
-                )
             for sid in sample_ids:
                 if not isinstance(sid, str):
                     raise TypeError(
                         "All sample_ids must be of type str. Got: {}".format(type(sid))
                     )
+            if len(sample_ids) != len(original_sample_ids):
+                if not allow_partial:
+                    raise ValueError(
+                        "sample_ids length ({}) does not match simulation output length ({})".format(
+                            len(sample_ids), len(original_sample_ids)
+                        )
+                    )
+                n_bound = min(len(sample_ids), len(original_sample_ids))
+                sample_ids = list(sample_ids)[:n_bound]
+                original_sample_ids = original_sample_ids[:n_bound]
+                # Over-generation trims sample_ids/original_sample_ids above but encoded was
+                # stacked from the full simulation output; slice it too so the encoded batch dim
+                # stays 1:1 with the returned sample_ids.
+                encoded = {name: arr[:n_bound] for name, arr in encoded.items()}
             for synth_id, original_local_id in zip(sample_ids, original_sample_ids):
                 self._synthetic_lookup[synth_id] = (sim_preprocess, original_local_id)
             if extend_preprocess:
@@ -618,6 +629,19 @@ class LeapLoader(LeapLoaderBase):
             returned_sample_ids = original_sample_ids
         return {"encoded": encoded, "sample_ids": returned_sample_ids}
 
+    def prune_synthetic_lookup(self, keep_ids):
+        # type: (List[str]) -> None
+        # Keep only the given synthetic sample_ids in the in-memory lookup and
+        # drop the rest, so preprocess responses don't accumulate across many
+        # run_simulation calls (e.g. a synthetic calibration loop keeps only its
+        # running top-K trials). Keep-set semantics (rather than evict-list) so
+        # the caller can bound the lookup to a known-good set each iteration
+        # without tracking everything it ever generated.
+        keep = set(keep_ids)
+        self._synthetic_lookup = {
+            sid: entry for sid, entry in self._synthetic_lookup.items() if sid in keep
+        }
+
     def _extend_additional_preprocess(self, new_sample_ids: List[str]) -> None:
         if self._preprocess_result_cached is None:
             self._preprocess_result()

{code_loader-1.0.193.dev5 → code_loader-1.0.195}/code_loader/leaploaderbase.py

@@ -159,8 +159,13 @@ class LeapLoaderBase:
         pass
 
     @abstractmethod
-    def run_simulation(self, sim_name, params=None, n_samples=1, seed=0, sample_ids=None):
-        # type: (str, Optional[Dict[str, Any]], int, int, Optional[List[str]]) -> Dict[str, Any]
+    def run_simulation(self, sim_name, params=None, n_samples=1, seed=0, sample_ids=None,
+                       extend_preprocess=True, allow_partial=False):
+        # type: (str, Optional[Dict[str, Any]], int, int, Optional[List[str]], bool, bool) -> Dict[str, Any]
+        pass
+
+    def prune_synthetic_lookup(self, keep_ids):
+        # type: (List[str]) -> None
         pass
 
     def is_custom_latent_space(self) -> bool:

{code_loader-1.0.193.dev5 → code_loader-1.0.195}/pyproject.toml

@@ -1,7 +1,6 @@
 [tool.poetry]
 name = "code-loader"
-
-version = "1.0.193.dev5"
+version = "1.0.195"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"