code-loader 1.0.215.dev1__tar.gz → 1.0.216__tar.gz

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.215.dev1
+Version: 1.0.216
 Summary: 
 Home-page: https://github.com/tensorleap/code-loader
 License: MIT

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/code_loader/contract/datasetclasses.py

@@ -84,13 +84,14 @@ class PreprocessResponse:
                 (f"PreprocessResponse.sample_ids should be a list. Got: {type(self.sample_ids).__name__}. "
                  f"Supported: {SUPPORTED_SAMPLE_IDS}. Convert it with .tolist() or list(...), "
                  f"e.g. sample_ids=df.index.tolist().")
-            self._grouped = len(self.sample_ids) > 0 and isinstance(self.sample_ids[0], list)
+            self._grouped = len(self.sample_ids) > 0 and isinstance(self.sample_ids[0], (list, tuple))
             if self._grouped:
                 groups = cast(List[List[SampleId]], self.sample_ids)
                 assert len(groups) >= 1, "Grouped PreprocessResponse must have at least one group."
                 for group in groups:
                     assert type(group) is list and len(group) > 0, \
-                        f"Each group in a grouped PreprocessResponse must be a non-empty list. Got: {type(group).__name__}"
+                        (f"Each group in a grouped PreprocessResponse must be a non-empty list. Got: {type(group).__name__}. "
+                         f"Convert each group with list(...).")
                 first_type = type(groups[0][0])
                 assert first_type in (str, np.str_, int), \
                     f"Sample id should be of type str or int. Got: {first_type.__name__}"

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/code_loader/contract/responsedataclasses.py

@@ -168,6 +168,7 @@ class LeapAnalysisConfiguration:
     feature_flags: Optional[List[str]] = None
     deterministic_results: Optional[bool] = None  # if true, results will be deterministic but will increase memory usage and runtime
     ignore_latent_spaces: Optional[List[str]] = None  # names of latent spaces to skip during extraction; see LeapBinder.check for validation rules
+    use_additional_set_as_unlabeled_candidate: Optional[bool] = None  # None = engine default (ON); False keeps additional samples out of Label Next / Unlabelled Data / aggressor fixing
 
 
 @dataclass

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/code_loader/inner_leap_binder/leapbinder.py

@@ -1133,6 +1133,7 @@ class LeapBinder:
         self.check_false_positive_custom_latent_spaces(preprocess_result)
         self.check_simulations()
         self.validate_ignore_latent_spaces()
+        self.validate_use_additional_set_as_unlabeled_candidate()
         print("Successful!")
 
     def validate_autoregressive_setup(self) -> None:
@@ -1232,5 +1233,15 @@ class LeapBinder:
                     f"tokens=['foreground']."
                 )
 
+    def validate_use_additional_set_as_unlabeled_candidate(self) -> None:
+        if not self.leap_analysis_configuration:
+            return
+        value = self.leap_analysis_configuration.use_additional_set_as_unlabeled_candidate
+        if value is not None and not isinstance(value, bool):
+            raise Exception(
+                f"leap_analysis_configuration.use_additional_set_as_unlabeled_candidate must be "
+                f"True, False or None, got {value!r} ({type(value).__name__})."
+            )
+
     def set_batch_size_to_validate(self, batch_size: int) -> None:
         self.batch_size_to_validate = batch_size

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/code_loader/leaploader.py

@@ -447,6 +447,7 @@ class LeapLoader(LeapLoaderBase):
                             if metadata_name not in m_names:
                                 raise Exception(f"Domain gap metadata '{metadata_name}' is not found in dataset metadata list.")
                     global_leap_binder.validate_ignore_latent_spaces()
+                    global_leap_binder.validate_use_additional_set_as_unlabeled_candidate()
             except DatasetScriptException as e:
                 line_number, file_name, stacktrace = get_root_exception_file_and_line_number()
                 general_error = f"Something went wrong. {repr(e.__cause__)} in file {file_name}, line_number:  {line_number}\nStacktrace:\n{stacktrace}"

{code_loader-1.0.215.dev1 → code_loader-1.0.216}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "code-loader"
-version = "1.0.215.dev1"
+version = "1.0.216"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"