phylogenie 2.0.2__tar.gz → 2.0.4__tar.gz

{phylogenie-2.0.2 → phylogenie-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phylogenie
-Version: 2.0.2
+Version: 2.0.4
 Summary: Generate phylogenetic datasets with minimal setup effort
 Author: Gabriele Marino
 Author-email: gabmarino.8601@gmail.com
@@ -23,7 +23,7 @@ Description-Content-Type: text/markdown
 ---
 
 [![AliSim](https://img.shields.io/badge/Powered%20by-AliSim-orange?style=flat-square)](https://iqtree.github.io/doc/AliSim)
-[![PyPI package](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
+[![PyPI version](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
 [![PyPI downloads](https://shields.io/pypi/dm/phylogenie)](https://pypi.org/project/phylogenie/)
 
 Phylogenie is a [Python](https://www.python.org/) package designed to easily simulate phylogenetic datasets—such as trees and multiple sequence alignments (MSAs)—with minimal setup effort. Simply specify the distributions from which your parameters should be sampled, and Phylogenie will handle the rest!

{phylogenie-2.0.2 → phylogenie-2.0.4}/README.md

@@ -5,7 +5,7 @@
 ---
 
 [![AliSim](https://img.shields.io/badge/Powered%20by-AliSim-orange?style=flat-square)](https://iqtree.github.io/doc/AliSim)
-[![PyPI package](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
+[![PyPI version](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
 [![PyPI downloads](https://shields.io/pypi/dm/phylogenie)](https://pypi.org/project/phylogenie/)
 
 Phylogenie is a [Python](https://www.python.org/) package designed to easily simulate phylogenetic datasets—such as trees and multiple sequence alignments (MSAs)—with minimal setup effort. Simply specify the distributions from which your parameters should be sampled, and Phylogenie will handle the rest!

phylogenie-2.0.4/phylogenie/__init__.py

@@ -0,0 +1,72 @@
+from phylogenie.generators import (
+    AliSimDatasetGenerator,
+    BDEITreeDatasetGenerator,
+    BDSSTreeDatasetGenerator,
+    BDTreeDatasetGenerator,
+    CanonicalTreeDatasetGenerator,
+    DatasetGenerator,
+    DatasetGeneratorConfig,
+    EpidemiologicalTreeDatasetGenerator,
+    FBDTreeDatasetGenerator,
+    TreeDatasetGeneratorConfig,
+)
+from phylogenie.io import load_fasta, load_newick
+from phylogenie.msa import MSA
+from phylogenie.skyline import (
+    SkylineMatrix,
+    SkylineMatrixCoercible,
+    SkylineParameter,
+    SkylineParameterLike,
+    SkylineVector,
+    SkylineVectorCoercible,
+    SkylineVectorLike,
+    skyline_matrix,
+    skyline_parameter,
+    skyline_vector,
+)
+from phylogenie.tree import Tree
+from phylogenie.treesimulator import (
+    Event,
+    get_BD_events,
+    get_BDEI_events,
+    get_BDSS_events,
+    get_canonical_events,
+    get_epidemiological_events,
+    get_FBD_events,
+    simulate_tree,
+)
+
+__all__ = [
+    "AliSimDatasetGenerator",
+    "BDEITreeDatasetGenerator",
+    "BDSSTreeDatasetGenerator",
+    "BDTreeDatasetGenerator",
+    "CanonicalTreeDatasetGenerator",
+    "DatasetGenerator",
+    "DatasetGeneratorConfig",
+    "EpidemiologicalTreeDatasetGenerator",
+    "FBDTreeDatasetGenerator",
+    "SkylineMatrix",
+    "SkylineMatrixCoercible",
+    "skyline_matrix",
+    "SkylineParameter",
+    "SkylineParameterLike",
+    "skyline_parameter",
+    "SkylineVector",
+    "SkylineVectorCoercible",
+    "SkylineVectorLike",
+    "skyline_vector",
+    "Tree",
+    "TreeDatasetGeneratorConfig",
+    "Event",
+    "get_BD_events",
+    "get_BDEI_events",
+    "get_BDSS_events",
+    "get_canonical_events",
+    "get_epidemiological_events",
+    "get_FBD_events",
+    "simulate_tree",
+    "load_fasta",
+    "load_newick",
+    "MSA",
+]

phylogenie-2.0.4/phylogenie/generators/__init__.py

@@ -0,0 +1,32 @@
+from typing import Annotated
+
+from pydantic import Field
+
+from phylogenie.generators.alisim import AliSimDatasetGenerator
+from phylogenie.generators.dataset import DatasetGenerator
+from phylogenie.generators.trees import (
+    BDEITreeDatasetGenerator,
+    BDSSTreeDatasetGenerator,
+    BDTreeDatasetGenerator,
+    CanonicalTreeDatasetGenerator,
+    EpidemiologicalTreeDatasetGenerator,
+    FBDTreeDatasetGenerator,
+    TreeDatasetGeneratorConfig,
+)
+
+DatasetGeneratorConfig = Annotated[
+    TreeDatasetGeneratorConfig | AliSimDatasetGenerator,
+    Field(discriminator="data_type"),
+]
+
+__all__ = [
+    "DatasetGeneratorConfig",
+    "DatasetGenerator",
+    "AliSimDatasetGenerator",
+    "CanonicalTreeDatasetGenerator",
+    "EpidemiologicalTreeDatasetGenerator",
+    "FBDTreeDatasetGenerator",
+    "BDTreeDatasetGenerator",
+    "BDEITreeDatasetGenerator",
+    "BDSSTreeDatasetGenerator",
+]

{phylogenie-2.0.2 → phylogenie-2.0.4}/phylogenie/generators/dataset.py

@@ -47,11 +47,12 @@ class DatasetGenerator(ABC, StrictBaseModel):
             return
         os.makedirs(data_dir)
 
-        data: list[dict[str, Any]] = [{}] * n_samples
+        data: list[dict[str, Any]] = [{} for _ in range(n_samples)]
         if self.context is not None:
             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()
+            print(data)
             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)
 

{phylogenie-2.0.2 → phylogenie-2.0.4}/phylogenie/io.py

@@ -85,7 +85,7 @@ def load_fasta(
             else:
                 try:
                     time = float(id.split("|")[-1])
-                except ValueError:
+                except:
                     time = None
             chars = next(f).strip()
             sequences.append(Sequence(id, chars, time))

{phylogenie-2.0.2 → phylogenie-2.0.4}/phylogenie/treesimulator/events.py

@@ -1,11 +1,9 @@
 from abc import ABC, abstractmethod
-from collections.abc import Iterator
 
 from numpy.random import Generator
 
 from phylogenie.skyline import (
     SkylineMatrixCoercible,
-    SkylineParameter,
     SkylineParameterLike,
     SkylineVectorCoercible,
     skyline_matrix,
@@ -97,12 +95,6 @@ def get_canonical_events(
     death_rates = skyline_vector(death_rates, N)
     sampling_rates = skyline_vector(sampling_rates, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if N == 1 and migration_rates is not None:
-        raise ValueError(f"Migration rates cannot be provided for a single state.")
-    if N == 1 and birth_rates_among_states is not None:
-        raise ValueError(
-            f"Birth rates among states cannot be provided for a single state."
-        )
 
     events: list[Event] = []
     for i in range(N):
@@ -111,24 +103,23 @@ def get_canonical_events(
         events.append(DeathEvent(death_rates[i], state))
         events.append(SamplingEvent(sampling_rates[i], state, removal_probabilities[i]))
 
-    def _parse_matrix_events(
-        matrix: SkylineMatrixCoercible | None,
-    ) -> Iterator[tuple[SkylineParameter, str, str]]:
-        if matrix is not None:
-            matrix = skyline_matrix(matrix, N, N - 1)
-            assert states is not None
-            for i, state in enumerate(states):
-                for j, other_state in enumerate([s for s in states if s != state]):
-                    yield matrix[i, j], state, other_state
-
-    events.extend(
-        MigrationEvent(rate, state, other_state)
-        for rate, state, other_state in _parse_matrix_events(migration_rates)
-    )
-    events.extend(
-        BirthEvent(rate, state, other_state)
-        for rate, state, other_state in _parse_matrix_events(birth_rates_among_states)
-    )
+    if states is not None and migration_rates is not None:
+        migration_rates = skyline_matrix(migration_rates, N, N - 1)
+        for i, state in enumerate(states):
+            for j, other_state in enumerate([s for s in states if s != state]):
+                events.append(MigrationEvent(migration_rates[i, j], state, other_state))
+    elif migration_rates is not None:
+        raise ValueError(f"Migration rates require states to be provided.")
+
+    if states is not None and birth_rates_among_states is not None:
+        birth_rates_among_states = skyline_matrix(birth_rates_among_states, N, N - 1)
+        for i, state in enumerate(states):
+            for j, other_state in enumerate([s for s in states if s != state]):
+                events.append(
+                    BirthEvent(birth_rates_among_states[i, j], state, other_state)
+                )
+    elif birth_rates_among_states is not None:
+        raise ValueError(f"Birth rates among states require states to be provided.")
 
     return [event for event in events if event.rate]
 
@@ -148,20 +139,20 @@ def get_epidemiological_events(
     become_uninfectious_rates = skyline_vector(become_uninfectious_rates, N)
     sampling_proportions = skyline_vector(sampling_proportions, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if N == 1 and reproduction_numbers_among_states is not None:
-        raise ValueError(
-            f"Reproduction numbers among states cannot be provided for a single state."
-        )
 
     birth_rates = reproduction_numbers * become_uninfectious_rates
     sampling_rates = become_uninfectious_rates * sampling_proportions
-    birth_rates_among_states = (
-        None
-        if reproduction_numbers_among_states is None
-        else skyline_matrix(reproduction_numbers_among_states, N, N - 1)
-        * become_uninfectious_rates
-    )
     death_rates = become_uninfectious_rates - removal_probabilities * sampling_rates
+    birth_rates_among_states = None
+    if states is None and reproduction_numbers_among_states is not None:
+        raise ValueError(
+            f"Reproduction numbers among states require states to be provided."
+        )
+    elif reproduction_numbers_among_states is not None:
+        birth_rates_among_states = (
+            skyline_matrix(reproduction_numbers_among_states, N, N - 1)
+            * become_uninfectious_rates
+        )
 
     return get_canonical_events(
         states=states,
@@ -189,23 +180,20 @@ def get_FBD_events(
     turnover = skyline_vector(turnover, N)
     sampling_proportions = skyline_vector(sampling_proportions, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if N == 1 and diversification_between_types is not None:
-        raise ValueError(
-            f"Diversification rates among states cannot be provided for a single state."
-        )
 
     birth_rates = diversification / (1 - turnover)
     death_rates = turnover * birth_rates
-    sampling_rates = (
-        sampling_proportions
-        * death_rates
-        / (1 - removal_probabilities * sampling_proportions)
-    )
-    birth_rates_among_states = (
-        None
-        if diversification_between_types is None
-        else skyline_matrix(diversification_between_types, N, N - 1) + death_rates
-    )
+    sampling_rates_dividend = 1 - removal_probabilities * sampling_proportions
+    sampling_rates = sampling_proportions * death_rates / sampling_rates_dividend
+    birth_rates_among_states = None
+    if states is None and diversification_between_types is not None:
+        raise ValueError(
+            f"Diversification rates among states require states to be provided."
+        )
+    elif diversification_between_types is not None:
+        birth_rates_among_states = (
+            skyline_matrix(diversification_between_types, N, N - 1) + death_rates
+        )
 
     return get_canonical_events(
         states=states,

{phylogenie-2.0.2 → phylogenie-2.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phylogenie"
-version = "2.0.2"
+version = "2.0.4"
 description = "Generate phylogenetic datasets with minimal setup effort"
 authors = ["Gabriele Marino <gabmarino.8601@gmail.com>"]
 readme = "README.md"

phylogenie-2.0.2/phylogenie/generators/__init__.py

@@ -1,14 +0,0 @@
-from typing import Annotated
-
-from pydantic import Field
-
-from phylogenie.generators.alisim import AliSimDatasetGenerator
-from phylogenie.generators.dataset import DatasetGenerator
-from phylogenie.generators.trees import TreeDatasetGeneratorConfig
-
-DatasetGeneratorConfig = Annotated[
-    TreeDatasetGeneratorConfig | AliSimDatasetGenerator,
-    Field(discriminator="data_type"),
-]
-
-__all__ = ["DatasetGeneratorConfig", "DatasetGenerator"]