drafted simulation module + working on Genomes+Phenomes methods and t…

…esting model building

.github/workflows/test_pytest.yml → .github/workflows/python_workflow.yml

@@ -1,4 +1,4 @@
-name: 🌱💚🧬
+name: 🌱🧬
 
 on:
   push:

README.md

@@ -3,7 +3,7 @@ Genomic breeding workflow
 
 |**Build Status**|**License**|
 |:--------------:|:---------:|
-| <a href="https://github.com/jeffersonfparil/gb/actions"><img src="https://github.com/jeffersonfparil/gb/actions/workflows/test_pytest.yml/badge.svg"></a> | [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) |
+| <a href="https://github.com/jeffersonfparil/gb/actions"><img src="https://github.com/jeffersonfparil/gb/actions/workflows/python_workflow.yml/badge.svg"></a> | [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) |
 
 TODO: Consolidate db, gp, and simquantgen into this single workflow plus various selection strategies incorporating selection simulations
 
@@ -14,9 +14,9 @@ cd gb/
 pip install uv
 pip install ruff
 uv init .
-uv add pytest mypy numpy progressbar2 matplotlib polars scipy statsmodels  click
+uv add pytest mypy numpy progressbar2 scikit-learn matplotlib polars click
 uv run ruff format
 uv run ruff check
-uv run mypy */*.py
+uv run mypy data/*.py
 uv run pytest -s
 ```

data/genotype.py

@@ -1,39 +1,104 @@
 import numpy as np
-# from data.error import Error
+from typing import Self
+from data.error import IncompatibleParameters
 
 
 class Genomes:
+    """
+    Genotype data
+    n: number of entries (an entry maybe an individual diploid genotype, or a tetraploid genotype or a pool of 50 diploid genotypes)
+    p: total number of loci
+    m: number of chromosomes
+    k: number of alleles per locus
+    entries: vector (nx0; str) of entry names
+    chromosomes: vector (px0; str) of chromosome names
+    positions: vector (px0; uint64) of positions per chromosome (i.e. starts at 1 per chromosome)
+    alleles: matrix (pxk; str) of allele names across p loci and k alleles
+    genotypes: matrix (nx(p*(k-1)); np.float64) of allele frequencies across n genotypes and p*(k-1) alleles,
+            where the k-1 alleles per locus are adjacent each other along the columns
+    mask: matrix (nx(p*(k-1)); np.bool) of boolean mask
+    """
+
     n: int
     p: int
+    k: int
     m: int
-    a: int
-    b: np.ndarray
     entries: np.ndarray
     chromosomes: np.ndarray
     positions: np.ndarray
     alleles: np.ndarray
-    X: np.ndarray
+    genotypes: np.ndarray
     mask: np.ndarray
 
-    def __init__(self) -> None:
-        self.n = 1
-        self.p = 1
-        self.m = 1
-        self.a = 1
-        self.b = np.array([1.00])
-        self.entries = np.array(['dummy_entry_1'])
-        self.chromosomes = np.array(['chromosome_1'])
-        self.positions = np.array([123_456_789])
-        self.alleles = np.array(['allele 1|allele_2|allele_3\tallele_2'])
-        self.X = np.array([[1.00]])
-        self.mask = np.array([[False]])
+    def __init__(
+        self: Self,
+        entries: np.ndarray,
+        chromosomes: np.ndarray,
+        positions: np.ndarray,
+        alleles: np.ndarray,
+        genotypes: np.ndarray,
+    ) -> None:
+        n: int = entries.shape[0]
+        if n != genotypes.shape[0]:
+            raise IncompatibleParameters
+        pk1: int = genotypes.shape[1]
+        k: int = alleles.shape[1]
+        if pk1 % (k - 1) > 0:
+            raise IncompatibleParameters
+        p: int = int(pk1 / (k - 1))
+        if (p != chromosomes.shape[0]) or (p != positions.shape[0]) or (p != alleles.shape[0]):
+            raise IncompatibleParameters
+        m: int = np.unique(ar=chromosomes).shape[0]
+        self.n = n
+        self.p = p
+        self.k = k
+        self.m = m
+        self.entries = entries
+        self.chromosomes = chromosomes
+        self.positions = positions
+        self.alleles = alleles
+        self.genotypes = genotypes
+        self.mask = np.ones((n, pk1)).astype(np.bool)
+
+    def __str__(self: Self) -> str:
+        info: str = (
+            '{\n\tn: '
+            + str(self.n)
+            + '\n\t'
+            + 'p: '
+            + str(self.p)
+            + '\n\t'
+            + 'k: '
+            + str(self.k)
+            + '\n\t'
+            + 'm: '
+            + str(self.m)
+            + '\n\t'
+            + 'entries: '
+            + str(self.entries)
+            + '\n\t'
+            + 'chromosomes: '
+            + str(self.chromosomes)
+            + '\n\t'
+            + 'positions: '
+            + str(self.positions)
+            + '\n\t'
+            + 'alleles: '
+            + str(self.alleles)
+            + '\n\t'
+            + 'genotypes: '
+            + str(self.genotypes)
+            + '\n\t'
+            + 'mask: '
+            + str(self.mask)
+            + '\n}'
+        )
+        return info
 
 
 def test_genotype():
-    genotypes = Genomes()
-    print(genotypes.X)
-    assert genotypes.n == 1
-    assert genotypes.n == genotypes.p
-    assert genotypes.p == genotypes.m
-    assert genotypes.m == genotypes.a
-    assert len(genotypes.b) == 1
+    from data.simulation import simulate
+
+    genomes, _ = simulate()
+    print(genomes)
+    assert isinstance(genomes, Genomes)

data/phenotype.py

@@ -1,25 +1,38 @@
 import numpy as np
-# from data.error import Error
+from data.error import IncompatibleParameters
 
 
 class Phenomes:
+    """
+    Phenotype data
+    n: number of entries (an entry maybe an individual diploid genotype, or a tetraploid genotype or a pool of 50 diploid genotypes)
+    ntraits: number of traits
+    entries: vector (nx0; str) of entry names
+    traits: vector (ntraitsx0; str) of trait names
+    genotypes: matrix (nxntraits); np.float64) of phenotype data
+    mask: matrix (nxntraits); np.bool) of boolean mask
+    """
+
     n: int
-    q: int
     entries: np.ndarray
     traits: np.ndarray
-    Y: np.ndarray
+    phenotypes: np.ndarray
     mask: np.ndarray
 
-    def __init__(self) -> None:
-        self.n = 1
-        self.q = 1
-        self.entries = np.array(['dummy_entry_1'])
-        self.traits = np.array(['dummy_trait_1'])
-        self.Y = np.array([[0.00]])
-        self.mask = np.array([[False]])
+    def __init__(self, entries: np.ndarray, traits: np.ndarray, phenotypes: np.ndarray) -> None:
+        n: int = entries.shape[0]
+        if n != phenotypes.shape[0]:
+            raise IncompatibleParameters
+        ntraits: int = traits.shape[0]
+        if ntraits != phenotypes.shape[1]:
+            raise IncompatibleParameters
+        self.n = n
+        self.ntraits = ntraits
+        self.entries = entries
+        self.traits = traits
+        self.phenotypes = phenotypes
+        self.mask = np.ones((n, ntraits)).astype(np.bool)
 
 
 def test_phenomes():
-    Y = Phenomes()
-    assert Y.n == 1
-    assert Y.n == Y.q
+    assert 1 == 1