aspect-data 0.0.1__tar.gz → 0.0.2__tar.gz

{aspect_data-0.0.1 → aspect_data-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aspect-data
-Version: 0.0.1
+Version: 0.0.2
 Summary: General purpose, chemistry, and taxonomic featurization of tabular data with caching.
 Author-email: Eachan Johnson <eachan.johnson@crick.ac.uk>
 License: MIT License

{aspect_data-0.0.1 → aspect_data-0.0.2}/aspect/cli_module/featurize.py

@@ -59,7 +59,8 @@ def _parse_feature_spec(x: str, i: int):
             parsed_kwargs[k] = parsed_v
         parsed_transforms.append({
             "name": name,
-        } | parsed_kwargs)
+            "kwargs": parsed_kwargs
+        })
     return extra, {output_col: (input_col, tuple(parsed_transforms))}
 
 
@@ -142,7 +143,7 @@ def _featurize(args: Namespace) -> None:
     from ..data import DataPipeline
     
     if args.features:
-        extras, column_transforms = _common_feature_spec_routine(args.features)
+        extras, column_transforms = _common_feature_spec_routine(args.features, args.extras)
         pipeline = DataPipeline(
             column_transforms=column_transforms,
             columns_to_keep=extras,

{aspect_data-0.0.1 → aspect_data-0.0.2}/aspect/data.py

@@ -212,7 +212,6 @@ class DataPipeline:
         self._version = _version
         self._app = _app
         self.column_transforms = self.canonicalize_transforms(self._column_transforms)
-        self._column_transforms_serialized = self.serialize_transforms(self.column_transforms)
         self.output_format = output_format
         self.output_format_opts = output_format_opts or {}
         self.data_in = None
@@ -239,7 +238,7 @@ class DataPipeline:
 
     @cached_property
     def column_transforms_serialized(self):
-        self.serialize_transforms(self.column_transforms)
+        return self.serialize_transforms(self.column_transforms)
 
     def _canonicalize_transforms(
         self,
@@ -461,7 +460,7 @@ class DataPipeline:
             .map(
                 self._featurize,
                 fn_kwargs={
-                    "column_transforms": self._column_transforms_serialized,
+                    "column_transforms": self.column_transforms_serialized,
                 },
                 batched=True,
                 batch_size=batch_size,
@@ -493,7 +492,7 @@ class DataPipeline:
     ):
         keys = {
             "kwargs": (
-                ("_column_transforms_serialized", "column_transforms"),
+                ("column_transforms_serialized", "column_transforms"),
                 "columns_to_keep",
                 "output_format",
                 "output_format_opts",

{aspect_data-0.0.1 → aspect_data-0.0.2}/aspect/transform/functions.py

@@ -171,7 +171,12 @@ def Hash(
         if normalize:
             n = np.linalg.norm(vectors, axis=-1, keepdims=True)
             nz = n > 0
-            vectors[nz[:, 0]] = vectors[nz[:, 0]] / n[nz]
+            vectors = np.divide(
+                vectors,
+                n,
+                out=np.zeros_like(vectors),
+                where=n > 0,
+            )
         return vectors
 
     return _hash

{aspect_data-0.0.1 → aspect_data-0.0.2}/aspect_data.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aspect-data
-Version: 0.0.1
+Version: 0.0.2
 Summary: General purpose, chemistry, and taxonomic featurization of tabular data with caching.
 Author-email: Eachan Johnson <eachan.johnson@crick.ac.uk>
 License: MIT License

{aspect_data-0.0.1 → aspect_data-0.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "aspect-data"
-version = "0.0.1"
+version = "0.0.2"
 authors = [
   { name="Eachan Johnson", email="eachan.johnson@crick.ac.uk" },
 ]