PCA implementation #95

sgkit-dev · Sep 29, 2020 · aaf48d1 · aaf48d1
1 parent cc7aa7f
commit aaf48d1
Show file tree

Hide file tree

Showing 10 changed files with 839 additions and 3 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -26,4 +26,4 @@ repos:
     hooks:
       - id: mypy
         args: ["--strict", "--show-error-codes"]
-        additional_dependencies: ["numpy", "xarray", "dask[array]", "scipy", "typing-extensions", "zarr", "numba"]
+        additional_dependencies: ["numpy", "xarray", "dask[array]", "scipy", "typing-extensions", "zarr", "numba", "dask-ml"]
diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -4,10 +4,12 @@ pytest
 pytest-cov
 pytest-datadir
 hypothesis
+scikit-allel
 statsmodels
 zarr
 msprime
 scikit-learn
 partd
 fsspec
-bed-reader
+bed-reader
+matplotlib
diff --git a/requirements.txt b/requirements.txt
@@ -1,6 +1,7 @@
 numpy
 xarray
 dask[array]
+dask-ml
 scipy
 typing-extensions
 numba

diff --git a/setup.cfg b/setup.cfg
@@ -28,6 +28,7 @@ install_requires =
     numpy
     xarray
     dask[array]
+    dask-ml
     scipy
     zarr
     numba
@@ -80,7 +81,7 @@ ignore =
 profile = black
 default_section = THIRDPARTY
 known_first_party = sgkit
-known_third_party = dask,fire,glow,hail,hypothesis,invoke,msprime,numba,numpy,pandas,pkg_resources,pyspark,pytest,setuptools,sgkit_plink,sklearn,sphinx,typing_extensions,xarray,yaml,zarr
+known_third_party = allel,dask,fire,glow,hail,hypothesis,invoke,msprime,numba,numpy,pandas,pkg_resources,pyspark,pytest,setuptools,sgkit_plink,sklearn,sphinx,typing_extensions,xarray,yaml,zarr
 multi_line_output = 3
 include_trailing_comma = True
 force_grid_wrap = 0
@@ -89,6 +90,8 @@ line_length = 88
 
 [mypy-dask.*]
 ignore_missing_imports = True
+[mypy-dask_ml.*]
+ignore_missing_imports = True
 [mypy-numpy.*]
 ignore_missing_imports = True
 [mypy-pandas.*]
@@ -111,6 +114,8 @@ ignore_missing_imports = True
 ignore_missing_imports = True
 [mypy-bed_reader.*]
 ignore_missing_imports = True
+[mypy-allel.*]
+ignore_missing_imports = True
 [mypy-sgkit.*]
 allow_redefinition = True
 [mypy-sgkit.*.tests.*]

diff --git a/sgkit/__init__.py b/sgkit/__init__.py
@@ -12,6 +12,7 @@
 from .stats.association import gwas_linear_regression
 from .stats.hwe import hardy_weinberg_test
 from .stats.pc_relate import pc_relate
+from .stats.pca import pca
 from .stats.popgen import Fst, Tajimas_D, divergence, diversity
 from .stats.regenie import regenie
 
@@ -35,4 +36,5 @@
     "Fst",
     "Tajimas_D",
     "pc_relate",
+    "pca",
 ]