phylogenie 2.0.11__tar.gz → 2.0.13__tar.gz

{phylogenie-2.0.11 → phylogenie-2.0.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phylogenie
-Version: 2.0.11
+Version: 2.0.13
 Summary: Generate phylogenetic datasets with minimal setup effort
 Author: Gabriele Marino
 Author-email: gabmarino.8601@gmail.com

{phylogenie-2.0.11 → phylogenie-2.0.13}/phylogenie/__init__.py

@@ -8,6 +8,9 @@ from phylogenie.generators import (
     DatasetGeneratorConfig,
     EpidemiologicalTreeDatasetGenerator,
     FBDTreeDatasetGenerator,
+    SkylineMatrixModel,
+    SkylineParameterModel,
+    SkylineVectorModel,
     TreeDatasetGeneratorConfig,
 )
 from phylogenie.io import load_fasta, load_newick
@@ -48,13 +51,16 @@ __all__ = [
     "FBDTreeDatasetGenerator",
     "SkylineMatrix",
     "SkylineMatrixCoercible",
+    "SkylineMatrixModel",
     "skyline_matrix",
     "SkylineParameter",
     "SkylineParameterLike",
+    "SkylineParameterModel",
     "skyline_parameter",
     "SkylineVector",
     "SkylineVectorCoercible",
     "SkylineVectorLike",
+    "SkylineVectorModel",
     "skyline_vector",
     "Tree",
     "TreeDatasetGeneratorConfig",

{phylogenie-2.0.11 → phylogenie-2.0.13}/phylogenie/generators/__init__.py

@@ -3,6 +3,11 @@ from typing import Annotated
 from pydantic import Field
 
 from phylogenie.generators.alisim import AliSimDatasetGenerator
+from phylogenie.generators.configs import (
+    SkylineMatrixModel,
+    SkylineParameterModel,
+    SkylineVectorModel,
+)
 from phylogenie.generators.dataset import DatasetGenerator
 from phylogenie.generators.trees import (
     BDEITreeDatasetGenerator,
@@ -29,4 +34,7 @@ __all__ = [
     "BDTreeDatasetGenerator",
     "BDEITreeDatasetGenerator",
     "BDSSTreeDatasetGenerator",
+    "SkylineMatrixModel",
+    "SkylineParameterModel",
+    "SkylineVectorModel",
 ]

{phylogenie-2.0.11 → phylogenie-2.0.13}/phylogenie/generators/configs.py

@@ -10,9 +10,9 @@ class Distribution(BaseModel):
 
 Integer = str | int
 Scalar = str | pgt.Scalar
-ManyScalars = str | list[Scalar]
-OneOrManyScalars = Scalar | list[Scalar]
-OneOrMany2DScalars = Scalar | list[list[Scalar]]
+ManyScalars = str | pgt.Many[Scalar]
+OneOrManyScalars = Scalar | pgt.Many[Scalar]
+OneOrMany2DScalars = Scalar | pgt.Many2D[Scalar]
 
 
 class StrictBaseModel(BaseModel):
@@ -25,15 +25,15 @@ class SkylineParameterModel(StrictBaseModel):
 
 
 class SkylineVectorModel(StrictBaseModel):
-    value: str | list[OneOrManyScalars]
+    value: str | pgt.Many[OneOrManyScalars]
     change_times: ManyScalars
 
 
 class SkylineMatrixModel(StrictBaseModel):
-    value: str | list[OneOrMany2DScalars]
+    value: str | pgt.Many[OneOrMany2DScalars]
     change_times: ManyScalars
 
 
 SkylineParameter = Scalar | SkylineParameterModel
-SkylineVector = str | pgt.Scalar | list[SkylineParameter] | SkylineVectorModel
-SkylineMatrix = str | pgt.Scalar | list[SkylineVector] | SkylineMatrixModel | None
+SkylineVector = str | pgt.Scalar | pgt.Many[SkylineParameter] | SkylineVectorModel
+SkylineMatrix = str | pgt.Scalar | pgt.Many[SkylineVector] | SkylineMatrixModel | None

{phylogenie-2.0.11 → phylogenie-2.0.13}/phylogenie/generators/dataset.py

@@ -41,21 +41,24 @@ class DatasetGenerator(ABC, cfg.StrictBaseModel):
         self._generate_one(filename=filename, rng=default_rng(seed), data=data)
 
     def _generate(self, rng: Generator, n_samples: int, output_dir: str) -> None:
+        if os.path.exists(output_dir):
+            print(f"Output directory {output_dir} already exists. Skipping.")
+            return
+
+        data_dir = (
+            output_dir
+            if self.context is None
+            else os.path.join(output_dir, DATA_DIRNAME)
+        )
+        os.makedirs(data_dir)
+
         data: list[dict[str, Any]] = [{} for _ in range(n_samples)]
         if self.context is not None:
-            data_dir = os.path.join(output_dir, DATA_DIRNAME)
             for d, (k, v) in product(data, self.context.items()):
                 args = v.model_extra if v.model_extra is not None else {}
                 d[k] = np.array(getattr(rng, v.type)(**args)).tolist()
             df = pd.DataFrame([{"file_id": str(i), **d} for i, d in enumerate(data)])
             df.to_csv(os.path.join(output_dir, METADATA_FILENAME), index=False)
-        else:
-            data_dir = output_dir
-
-        if os.path.exists(data_dir):
-            print(f"Output directory {data_dir} already exists. Skipping.")
-            return
-        os.makedirs(data_dir)
 
         joblib.Parallel(n_jobs=self.n_jobs)(
             joblib.delayed(self.generate_one)(

{phylogenie-2.0.11 → phylogenie-2.0.13}/phylogenie/generators/factories.py

@@ -100,7 +100,7 @@ def skyline_vector(
         )
     if isinstance(x, pgt.Scalar):
         return x
-    if ctg.is_list_of_skyline_parameter_configs(x):
+    if ctg.is_many_skyline_parameter_configs(x):
         return [skyline_parameter(p, data) for p in x]
 
     assert isinstance(x, cfg.SkylineVectorModel)
@@ -161,7 +161,7 @@ def skyline_matrix(
         )
     if isinstance(x, pgt.Scalar):
         return x
-    if ctg.is_list_of_skyline_vector_configs(x):
+    if ctg.is_many_skyline_vector_configs(x):
         return [skyline_vector(v, data) for v in x]
 
     assert isinstance(x, cfg.SkylineMatrixModel)

phylogenie-2.0.13/phylogenie/generators/typeguards.py

@@ -0,0 +1,25 @@
+from typing import Any, TypeGuard
+
+import phylogenie.generators.configs as cfg
+import phylogenie.typeguards as tg
+import phylogenie.typings as pgt
+
+
+def is_many_scalar_configs(x: Any) -> TypeGuard[pgt.Many[cfg.Scalar]]:
+    return tg.is_many(x) and all(isinstance(v, cfg.Scalar) for v in x)
+
+
+def is_many_skyline_parameter_configs(
+    x: Any,
+) -> TypeGuard[pgt.Many[cfg.SkylineParameter]]:
+    return tg.is_many(x) and all(isinstance(v, cfg.SkylineParameter) for v in x)
+
+
+def is_skyline_vector_config(x: Any) -> TypeGuard[cfg.SkylineVector]:
+    return isinstance(
+        x, str | pgt.Scalar | cfg.SkylineVectorModel
+    ) or is_many_skyline_parameter_configs(x)
+
+
+def is_many_skyline_vector_configs(x: Any) -> TypeGuard[pgt.Many[cfg.SkylineVector]]:
+    return tg.is_many(x) and all(is_skyline_vector_config(v) for v in x)

{phylogenie-2.0.11 → phylogenie-2.0.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phylogenie"
-version = "2.0.11"
+version = "2.0.13"
 description = "Generate phylogenetic datasets with minimal setup effort"
 authors = ["Gabriele Marino <gabmarino.8601@gmail.com>"]
 readme = "README.md"

phylogenie-2.0.11/phylogenie/generators/typeguards.py

@@ -1,28 +0,0 @@
-from typing import Any, TypeGuard
-
-import phylogenie.generators.configs as cfg
-import phylogenie.typings as pgt
-
-
-def is_list(x: Any) -> TypeGuard[list[Any]]:
-    return isinstance(x, list)
-
-
-def is_list_of_scalar_configs(x: Any) -> TypeGuard[list[cfg.Scalar]]:
-    return is_list(x) and all(isinstance(v, cfg.Scalar) for v in x)
-
-
-def is_list_of_skyline_parameter_configs(
-    x: Any,
-) -> TypeGuard[list[cfg.SkylineParameter]]:
-    return is_list(x) and all(isinstance(v, cfg.SkylineParameter) for v in x)
-
-
-def is_skyline_vector_config(x: Any) -> TypeGuard[cfg.SkylineVector]:
-    return isinstance(
-        x, str | pgt.Scalar | cfg.SkylineVectorModel
-    ) or is_list_of_skyline_parameter_configs(x)
-
-
-def is_list_of_skyline_vector_configs(x: Any) -> TypeGuard[list[cfg.SkylineVector]]:
-    return is_list(x) and all(is_skyline_vector_config(v) for v in x)