phylo2vec 1.2.0__tar.gz → 1.3.1__tar.gz

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/Cargo.lock

@@ -460,7 +460,7 @@ checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a"
 
 [[package]]
 name = "phylo2vec"
-version = "0.4.0"
+version = "0.4.1"
 dependencies = [
  "criterion",
  "rand",
@@ -544,7 +544,7 @@ dependencies = [
 
 [[package]]
 name = "py-phylo2vec"
-version = "1.2.0"
+version = "1.3.1"
 dependencies = [
  "phylo2vec",
  "pyo3",

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: phylo2vec
-Version: 1.2.0
+Version: 1.3.1
 Classifier: Development Status :: 3 - Alpha
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Programming Language :: Python
@@ -11,12 +11,17 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)
 Classifier: Operating System :: Unix
 Classifier: Operating System :: Microsoft :: Windows
-Requires-Dist: numba>=0.56.4
 Requires-Dist: numpy>=1.22,<2.1
 Requires-Dist: biopython>=1.84.0
 Requires-Dist: joblib>=1.2.0
 Requires-Dist: ete3==3.1.3
 Requires-Dist: six>=1.16.0
+Requires-Dist: jax ; extra == 'opt'
+Requires-Dist: joblib ; extra == 'opt'
+Requires-Dist: optax ; extra == 'opt'
+Requires-Dist: rpy2 ; extra == 'opt'
+Requires-Dist: tqdm ; extra == 'opt'
+Provides-Extra: opt
 License-File: LICENSE
 Summary: Phylo2Vec: integer vector representation of binary (phylogenetic) trees
 Author: Neil Scheidwasser <neil.clow@sund.ku.dk>
@@ -85,8 +90,10 @@ in Rust.
 
 ### Installing R package
 
-To install the R package, first you need to retrieve one of the compiled file
-within the package [releases](https://github.com/sbhattlab/phylo2vec/releases).
+#### Option 1: from a release (Windows, Mac, Ubuntu >= 22.04)
+
+Retrieve one of the compiled binaries from the
+[releases](https://github.com/sbhattlab/phylo2vec/releases) that fits your OS.
 Once the file is downloaded, simply run `install.packages` in your R command
 line.
 
@@ -94,6 +101,41 @@ line.
 install.packages("/path/to/package_file", repos = NULL, type = 'source')
 ```
 
+#### Option 2: using `devtools`
+
+⚠️ This requires installing [Rust](https://www.rust-lang.org/tools/install) to
+build the core package.
+
+```R
+devtools::install_github("sbhattlab/phylo2vec", subdir="./r-phylo2vec", build = FALSE)
+```
+
+Note: to download a specific version, use:
+
+```R
+devtools::install_github("sbhattlab/phylo2vec@vX.Y.Z", subdir="./r-phylo2vec", build = FALSE)
+```
+
+#### Option 3: manual installation
+
+⚠️ This requires installing [Rust](https://www.rust-lang.org/tools/install) to
+build the core package.
+
+Clone the repository and run the following `install.packages` in your R command
+line.
+
+Note: to download a specific version, you can use `git checkout` to a desired
+tag.
+
+```bash
+git clone https://github.com/sbhattlab/phylo2vec
+cd phylo2vec
+```
+
+```R
+install.packages("./r-phylo2vec", repos = NULL, type = 'source')
+```
+
 ## Basic Usage
 
 ### Python

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/README.md

@@ -58,8 +58,10 @@ in Rust.
 
 ### Installing R package
 
-To install the R package, first you need to retrieve one of the compiled file
-within the package [releases](https://github.com/sbhattlab/phylo2vec/releases).
+#### Option 1: from a release (Windows, Mac, Ubuntu >= 22.04)
+
+Retrieve one of the compiled binaries from the
+[releases](https://github.com/sbhattlab/phylo2vec/releases) that fits your OS.
 Once the file is downloaded, simply run `install.packages` in your R command
 line.
 
@@ -67,6 +69,41 @@ line.
 install.packages("/path/to/package_file", repos = NULL, type = 'source')
 ```
 
+#### Option 2: using `devtools`
+
+⚠️ This requires installing [Rust](https://www.rust-lang.org/tools/install) to
+build the core package.
+
+```R
+devtools::install_github("sbhattlab/phylo2vec", subdir="./r-phylo2vec", build = FALSE)
+```
+
+Note: to download a specific version, use:
+
+```R
+devtools::install_github("sbhattlab/phylo2vec@vX.Y.Z", subdir="./r-phylo2vec", build = FALSE)
+```
+
+#### Option 3: manual installation
+
+⚠️ This requires installing [Rust](https://www.rust-lang.org/tools/install) to
+build the core package.
+
+Clone the repository and run the following `install.packages` in your R command
+line.
+
+Note: to download a specific version, you can use `git checkout` to a desired
+tag.
+
+```bash
+git clone https://github.com/sbhattlab/phylo2vec
+cd phylo2vec
+```
+
+```R
+install.packages("./r-phylo2vec", repos = NULL, type = 'source')
+```
+
 ## Basic Usage
 
 ### Python

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "phylo2vec"
 # Rust core version
-version = "0.4.0"
+version = "0.4.1"
 edition.workspace = true
 authors.workspace = true
 description.workspace = true

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/base/ancestry.py

@@ -20,7 +20,7 @@ def from_ancestry(ancestry: np.ndarray) -> np.ndarray:
 
     Returns
     -------
-    numpy.array
+    numpy.ndarray
         Phylo2Vec vector
     """
     v_list = core.from_ancestry(ancestry)
@@ -50,12 +50,12 @@ def to_ancestry(v: np.ndarray) -> np.ndarray:
 
     Parameters
     ----------
-    v : numpy.array
+    v : numpy.ndarray
         Phylo2Vec vector
 
     Returns
     -------
-    ancestry : numpy.array
+    ancestry : numpy.ndarray
         Ancestry matrix
         1st column: child 1
         2nd column: child 2

{phylo2vec-1.2.0/py-phylo2vec → phylo2vec-1.3.1}/phylo2vec/base/edges.py

@@ -21,7 +21,7 @@ def from_edges(edges: List[Tuple[int, int]]) -> np.ndarray:
 
     Returns
     -------
-    v : numpy.array
+    v : numpy.ndarray
         Phylo2Vec vector
     """
     v = core.from_edges(edges)
@@ -35,7 +35,7 @@ def to_edges(v: np.ndarray) -> List[Tuple[int, int]]:
 
     Parameters
     ----------
-    v : numpy.array
+    v : numpy.ndarray
         Phylo2Vec vector
 
     Returns

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/base/newick.py

@@ -31,7 +31,7 @@ def to_newick(vector_or_matrix: np.ndarray) -> str:
 
     Parameters
     ----------
-    vector_or_matrix : numpy.array
+    vector_or_matrix : numpy.ndarray
         Phylo2Vec vector (ndim == 1)/matrix (ndim == 2)
 
     Returns

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/base/pairs.py

@@ -11,10 +11,9 @@ from typing import List, Tuple
 def from_pairs(pairs: List[Tuple[int, int]]) -> np.ndarray:
     """Convert a list of pairs to a Phylo2Vec vector
 
-    Each pair is represented as a list of pairs (B, L)
+    Each pair is represented as a tuple (B, L)
     indicating that leaf L descends from branch B.
 
-
     Parameters
     ----------
     pairs : List[Tuple[int, int]]
@@ -22,7 +21,7 @@ def from_pairs(pairs: List[Tuple[int, int]]) -> np.ndarray:
 
     Returns
     -------
-    v : numpy.array
+    v : numpy.ndarray
         Phylo2Vec vector
     """
     v = core.from_pairs(pairs)
@@ -32,12 +31,12 @@ def from_pairs(pairs: List[Tuple[int, int]]) -> np.ndarray:
 def to_pairs(v: np.ndarray) -> List[Tuple[int, int]]:
     """Convert a Phylo2Vec vector to a list of pairs
 
-    Each pair is represented as a list of pairs (B, L)
+    Each pair is represented as a tuple (B, L)
     indicating that leaf L descends from branch B.
 
     Parameters
     ----------
-    v : numpy.array
+    v : numpy.ndarray
         Phylo2Vec vector
 
     Returns

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/io/writer.py

@@ -44,7 +44,7 @@ def save_newick(
 
     Parameters
     ----------
-    vector_or_matrix : numpy.array
+    vector_or_matrix : numpy.ndarray
         Phylo2Vec vector (ndim == 1)/matrix (ndim == 2)
     filepath : str
         Path to the output file

{phylo2vec-1.2.0 → phylo2vec-1.3.1}/phylo2vec/metrics/pairwise.py

@@ -4,6 +4,7 @@ import warnings
 import numpy as np
 
 from phylo2vec import _phylo2vec_core as core
+from phylo2vec.utils.matrix import check_matrix
 from phylo2vec.utils.vector import check_vector
 
 
@@ -14,7 +15,7 @@ def cophenetic_distances(vector_or_matrix, unrooted=False):
 
     Parameters
     ----------
-    vector_or_matrix : numpy.array
+    vector_or_matrix : numpy.ndarray
         Phylo2Vec vector (ndim == 1)/matrix (ndim == 2)
 
     Returns
@@ -46,7 +47,7 @@ def cophenetic_distances(vector_or_matrix, unrooted=False):
 PAIRWISE_DISTANCES = {"cophenetic": cophenetic_distances}
 
 
-def pairwise_distances(v, metric="cophenetic"):
+def pairwise_distances(vector_or_matrix, metric="cophenetic"):
     """
     Compute a pairwise distance matrix
     for tree nodes from a Phylo2Vec vector.
@@ -55,8 +56,8 @@ def pairwise_distances(v, metric="cophenetic"):
 
     Parameters
     ----------
-    v : numpy.ndarray
-        Phylo2Vec vector
+    vector_or_matrix : numpy.ndarray
+        Phylo2Vec vector (ndim == 1)/matrix (ndim == 2)
     metric : str, optional
         Pairwise distance metric, by default "cophenetic"
 
@@ -65,8 +66,15 @@ def pairwise_distances(v, metric="cophenetic"):
     numpy.ndarray
         Distance matrix
     """
-    check_vector(v)
+    if vector_or_matrix.ndim == 2:
+        check_matrix(vector_or_matrix)
+    elif vector_or_matrix.ndim == 1:
+        check_vector(vector_or_matrix)
+    else:
+        raise ValueError(
+            "vector_or_matrix should either be a vector (ndim == 1) or matrix (ndim == 2)"
+        )
 
     func = PAIRWISE_DISTANCES[metric]
 
-    return func(v)
+    return func(vector_or_matrix)

phylo2vec-1.3.1/phylo2vec/opt/__init__.py

@@ -0,0 +1,7 @@
+"""Phylo2Vec-based optimisation methods."""
+
+from ._gradme import GradME
+from ._gradme_losses import gradme_loss
+from ._hc import HillClimbing
+
+__all__ = ["GradME", "gradme_loss", "HillClimbing"]

phylo2vec-1.3.1/phylo2vec/opt/_base.py

@@ -0,0 +1,132 @@
+"""Base class for all optimisation methods in Phylo2Vec."""
+
+import multiprocessing
+import random
+import time
+
+from dataclasses import dataclass
+from typing import Dict, List, Final
+
+import numpy as np
+
+from phylo2vec.datasets import read_fasta
+from phylo2vec.utils.matrix import sample_matrix
+from phylo2vec.utils.vector import sample_vector
+
+# Multiprocessing
+DEFAULT_N_JOBS: Final = multiprocessing.cpu_count() // 4
+MIN_N_JOBS: Final = 4
+# Seeding
+MAX_SEED = 42
+
+
+@dataclass
+class BaseResult:
+    """Result of the optimization process.
+
+    Attributes
+    ----------
+    best : numpy.ndarray
+        Optimized phylo2vec vector or matrix.
+    label_mapping : Dict[int, str]
+        Mapping of leaf labels (integer) to taxa.
+    best_score : float
+        The best score achieved during optimization.
+    scores : List[float]
+        List of scores obtained during optimization.
+    """
+
+    best: np.ndarray
+    label_mapping: Dict[int, str]
+    best_score: float
+    scores: List[float]
+
+
+class BaseOptimizer:
+    """
+    Base class for all phylo2vec-based optimizers
+
+    Parameters
+    ----------
+    random_seed : int, optional
+        Random seed, by default None
+    """
+
+    def __init__(self, mode="vector", random_seed=None, verbose=False, n_jobs=None):
+
+        assert mode in ["vector", "matrix"], "Mode must be either 'vector' or 'matrix'."
+        self.mode = mode
+
+        self.random_seed = random_seed or random.randint(0, MAX_SEED)
+        random.seed(self.random_seed)
+        np.random.seed(self.random_seed)
+
+        self.verbose = verbose
+
+        self.n_jobs = self._infer_n_jobs(n_jobs)
+
+    @staticmethod
+    def _infer_n_jobs(n_jobs=None):
+        return n_jobs or max(MIN_N_JOBS, DEFAULT_N_JOBS)
+
+    def fit(self, fasta_path) -> BaseResult:
+        """Fit an optimizer to a fasta file
+
+        Parameters
+        ----------
+        fasta_path : str
+            Path to fasta file
+
+        Returns
+        -------
+        result : BaseResult
+            Result of the optimization process, containing the optimized vector,
+            label mapping, best score, and scores during optimization.
+        """
+        # TODO: figure out how to change this when the user selects load fasta
+        # Probably an boolean "preloaded"
+        # If True, change the fasta path to include the module name
+        records = read_fasta(fasta_path)
+
+        # Make a label mapping from the records
+        label_mapping = dict(enumerate(r.id.replace(" ", ".") for r in records))
+
+        n_leaves = len(label_mapping)
+
+        if self.mode == "vector":
+            obj_init = sample_vector(n_leaves)
+        elif self.mode == "matrix":
+            obj_init = sample_matrix(n_leaves)
+        else:
+            raise ValueError(f"Unknown mode: {self.mode}")
+
+        start_time = time.time()
+
+        result = self._optimise(fasta_path, obj_init, label_mapping)
+
+        end_time = time.time()
+
+        if self.verbose:
+            print(
+                f"Optimisation finished in {end_time - start_time:.2f} seconds "
+                f"with {len(result.scores)} loss evaluations."
+            )
+
+        return result
+
+    def _optimise(self, fasta_path, tree, label_mapping):
+        raise NotImplementedError
+
+    def __repr__(self):
+        # TODO: maybe something like sklearn pprint
+        # https://github.com/scikit-learn/scikit-learn/blob/093e0cf14aff026cca6097e8c42f83b735d26358/sklearn/utils/_pprint.py#L116
+        format_string = f"{self.__class__.__name__}("
+
+        for item in vars(self):
+            format_string += "\n"
+            # TODO: pprint if dict?
+            format_string += f"\t{item}={repr(self.__getattribute__(item))},"
+
+        format_string = format_string[:-1] + "\n)"
+
+        return format_string