phylogenie 2.0.10__tar.gz → 2.0.12__tar.gz

{phylogenie-2.0.10 → phylogenie-2.0.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phylogenie
-Version: 2.0.10
+Version: 2.0.12
 Summary: Generate phylogenetic datasets with minimal setup effort
 Author: Gabriele Marino
 Author-email: gabmarino.8601@gmail.com

phylogenie-2.0.12/phylogenie/generators/configs.py

@@ -0,0 +1,39 @@
+from pydantic import BaseModel, ConfigDict
+
+import phylogenie.typings as pgt
+
+
+class Distribution(BaseModel):
+    type: str
+    model_config = ConfigDict(extra="allow")
+
+
+Integer = str | int
+Scalar = str | pgt.Scalar
+ManyScalars = str | pgt.Many[Scalar]
+OneOrManyScalars = Scalar | pgt.Many[Scalar]
+OneOrMany2DScalars = Scalar | pgt.Many2D[Scalar]
+
+
+class StrictBaseModel(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+
+class SkylineParameterModel(StrictBaseModel):
+    value: ManyScalars
+    change_times: ManyScalars
+
+
+class SkylineVectorModel(StrictBaseModel):
+    value: str | pgt.Many[OneOrManyScalars]
+    change_times: ManyScalars
+
+
+class SkylineMatrixModel(StrictBaseModel):
+    value: str | pgt.Many[OneOrMany2DScalars]
+    change_times: ManyScalars
+
+
+SkylineParameter = Scalar | SkylineParameterModel
+SkylineVector = str | pgt.Scalar | pgt.Many[SkylineParameter] | SkylineVectorModel
+SkylineMatrix = str | pgt.Scalar | pgt.Many[SkylineVector] | SkylineMatrixModel | None

{phylogenie-2.0.10 → phylogenie-2.0.12}/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-2.0.10 → phylogenie-2.0.12}/phylogenie/generators/factories.py

@@ -80,8 +80,6 @@ def one_or_many_scalars(
 def skyline_parameter(
     x: cfg.SkylineParameter, data: dict[str, Any]
 ) -> SkylineParameterLike:
-    if isinstance(x, SkylineParameter):
-        return x
     if isinstance(x, cfg.Scalar):
         return scalar(x, data)
     return SkylineParameter(
@@ -93,8 +91,6 @@ def skyline_parameter(
 def skyline_vector(
     x: cfg.SkylineVector, data: dict[str, Any]
 ) -> SkylineVectorCoercible:
-    if isinstance(x, SkylineVector):
-        return x
     if isinstance(x, str):
         e = _eval_expression(x, data)
         if tg.is_one_or_many_scalars(e):
@@ -104,7 +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)
@@ -155,8 +151,7 @@ def skyline_matrix(
 ) -> SkylineMatrixCoercible | None:
     if x is None:
         return None
-    if isinstance(x, SkylineMatrix):
-        return x
+
     if isinstance(x, str):
         e = _eval_expression(x, data)
         if tg.is_one_or_many_2D_scalars(e):
@@ -166,7 +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-2.0.12/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-2.0.10 → phylogenie-2.0.12}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phylogenie"
-version = "2.0.10"
+version = "2.0.12"
 description = "Generate phylogenetic datasets with minimal setup effort"
 authors = ["Gabriele Marino <gabmarino.8601@gmail.com>"]
 readme = "README.md"

phylogenie-2.0.10/phylogenie/generators/configs.py

@@ -1,46 +0,0 @@
-from pydantic import BaseModel, ConfigDict
-
-import phylogenie.typings as pgt
-from phylogenie.skyline import SkylineMatrix as _SkylineMatrix
-from phylogenie.skyline import SkylineParameter as _SkylineParameter
-from phylogenie.skyline import SkylineVector as _SkylineVector
-
-
-class Distribution(BaseModel):
-    type: str
-    model_config = ConfigDict(extra="allow")
-
-
-Integer = str | int
-Scalar = str | pgt.Scalar
-ManyScalars = str | list[Scalar]
-OneOrManyScalars = Scalar | list[Scalar]
-OneOrMany2DScalars = Scalar | list[list[Scalar]]
-
-
-class StrictBaseModel(BaseModel):
-    model_config = ConfigDict(extra="forbid")
-
-
-class SkylineParameterModel(StrictBaseModel):
-    value: ManyScalars
-    change_times: ManyScalars
-
-
-class SkylineVectorModel(StrictBaseModel):
-    value: str | list[OneOrManyScalars]
-    change_times: ManyScalars
-
-
-class SkylineMatrixModel(StrictBaseModel):
-    value: str | list[OneOrMany2DScalars]
-    change_times: ManyScalars
-
-
-SkylineParameter = Scalar | SkylineParameterModel | _SkylineParameter
-SkylineVector = (
-    str | pgt.Scalar | list[SkylineParameter] | SkylineVectorModel | _SkylineVector
-)
-SkylineMatrix = (
-    str | pgt.Scalar | list[SkylineVector] | SkylineMatrixModel | None | _SkylineMatrix
-)

phylogenie-2.0.10/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)