Backport PR scverse#1922: Fix paga exact reproducibility

docs/release-notes/1.8.2.rst

@@ -7,6 +7,7 @@
 - Fix ``use_raw=None`` using :attr:`anndata.AnnData.var_names` if :attr:`anndata.AnnData.raw`
   is present in :func:`scanpy.tl.score_genes` :pr:`1999` :smaller:`M Klein`
 - Fix compatibility with UMAP 0.5.2 :pr:`2028` :smaller:`L Mcinnes`
+- Fixed non-determinism in :func:`scanpy.pl.paga` node positions :pr:`1922` :smaller:`I Virshup`
 
 .. rubric:: Performance enhancements
 

scanpy/plotting/_tools/paga.py

@@ -14,6 +14,7 @@
 from matplotlib.axes import Axes
 from matplotlib.colors import is_color_like, Colormap
 from scipy.sparse import issparse
+from sklearn.utils import check_random_state
 
 from .. import _utils
 from .._utils import matrix, _IGraphLayout, _FontWeight, _FontSize
@@ -174,8 +175,11 @@ def _compute_pos(
     root=0,
     layout_kwds: Mapping[str, Any] = MappingProxyType({}),
 ):
+    import random
     import networkx as nx
 
+    random_state = check_random_state(random_state)
+
     nx_g_solid = nx.Graph(adjacency_solid)
     if layout is None:
         layout = 'fr'
@@ -190,9 +194,9 @@ def _compute_pos(
             )
             layout = 'fr'
     if layout == 'fa':
-        np.random.seed(random_state)
+        # np.random.seed(random_state)
         if init_pos is None:
-            init_coords = np.random.random((adjacency_solid.shape[0], 2))
+            init_coords = random_state.random_sample((adjacency_solid.shape[0], 2))
         else:
             init_coords = init_pos.copy()
         forceatlas2 = ForceAtlas2(
@@ -233,6 +237,7 @@ def _compute_pos(
             )
     else:
         # igraph layouts
+        random.seed(random_state.bytes(8))
         g = _sc_utils.get_igraph_from_adjacency(adjacency_solid)
         if 'rt' in layout:
             g_tree = _sc_utils.get_igraph_from_adjacency(adj_tree)
@@ -243,9 +248,11 @@ def _compute_pos(
             pos_list = g.layout(layout).coords
         else:
             # I don't know why this is necessary
-            np.random.seed(random_state)
+            # np.random.seed(random_state)
             if init_pos is None:
-                init_coords = np.random.random((adjacency_solid.shape[0], 2)).tolist()
+                init_coords = random_state.random_sample(
+                    (adjacency_solid.shape[0], 2)
+                ).tolist()
             else:
                 init_pos = init_pos.copy()
                 # this is a super-weird hack that is necessary as igraph’s

scanpy/tests/test_paga.py

@@ -2,6 +2,7 @@
 from pathlib import Path
 
 from matplotlib import cm
+import numpy as np
 
 import scanpy as sc
 
@@ -86,3 +87,21 @@ def test_paga_compare(image_comparer):
     sc.pl.paga_compare(pbmc, basis="umap", show=False)
 
     save_and_compare_images('master_paga_compare_pbmc3k')
+
+
+def test_paga_positions_reproducible():
+    """Check exact reproducibility and effect of random_state on paga positions"""
+    # https://github.com/theislab/scanpy/issues/1859
+    pbmc = sc.datasets.pbmc68k_reduced()
+    sc.tl.paga(pbmc, "bulk_labels")
+
+    a = pbmc.copy()
+    b = pbmc.copy()
+    c = pbmc.copy()
+
+    sc.pl.paga(a, show=False, random_state=42)
+    sc.pl.paga(b, show=False, random_state=42)
+    sc.pl.paga(c, show=False, random_state=13)
+
+    np.testing.assert_array_equal(a.uns["paga"]["pos"], b.uns["paga"]["pos"])
+    assert a.uns["paga"]["pos"].tolist() != c.uns["paga"]["pos"].tolist()