code-loader 1.0.185__tar.gz → 1.0.186.dev1__tar.gz

{code_loader-1.0.185 → code_loader-1.0.186.dev1}/PKG-INFO

@@ -1,7 +1,8 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.185
+Version: 1.0.186.dev1
 Summary: 
+Home-page: https://github.com/tensorleap/code-loader
 License: MIT
 Author: dorhar
 Author-email: doron.harnoy@tensorleap.ai
@@ -19,7 +20,6 @@ Requires-Dist: numpy (>=2.3.2,<3.0.0) ; python_version >= "3.11" and python_vers
 Requires-Dist: psutil (>=5.9.5,<6.0.0)
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Requires-Dist: requests (>=2.32.3,<3.0.0)
-Project-URL: Homepage, https://github.com/tensorleap/code-loader
 Project-URL: Repository, https://github.com/tensorleap/code-loader
 Description-Content-Type: text/markdown
 

{code_loader-1.0.185 → code_loader-1.0.186.dev1}/code_loader/leaploader.py

@@ -446,8 +446,8 @@ class LeapLoader(LeapLoaderBase):
         return result_payloads
 
     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
@@ -476,17 +476,21 @@ class LeapLoader(LeapLoaderBase):
                 per_encoder[handler.name].append(handler.function(sample_id, sim_preprocess))
         encoded = {name: np.stack(arrays) 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]
             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:

{code_loader-1.0.185 → code_loader-1.0.186.dev1}/code_loader/leaploaderbase.py

@@ -154,8 +154,9 @@ 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 is_custom_latent_space(self) -> bool:

{code_loader-1.0.185 → code_loader-1.0.186.dev1}/pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "code-loader"
 
-version = "1.0.185"
+version = "1.0.186.dev1"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"