Tweak minor pieces for v1.3.0 release

Author: ragibson

docs/index.rst

@@ -1,7 +1,7 @@
 .. ModularityPruning documentation master file, created by
-   sphinx-quickstart on Tue Jun 16 12:28:29 2020.
-   You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
+sphinx-quickstart on Tue Jun 16 12:28:29 2020.
+You can adapt this file completely to your liking, but it should at least
+contain the root `toctree` directive.
 
 Welcome to ModularityPruning's documentation!
 =============================================
@@ -12,10 +12,10 @@ perspective of stochastic block model inference.
 This method works for single-layer and multi-layer networks, as well as for restricting focus to a fixed number of
 communities when desired.
 
-Prior to version v1.3, we used the Louvain algorithm for modularity maximization instead of Leiden. The deprecated
-module `modularitypruning.louvain_utilities` now shims single-layer functions to their corresponding Leiden versions in
-`modularitypruning.leiden_utilities` (though it still contains the legacy multi-layer functions since they can be
-faster in general).
+Prior to version v1.3.0, we used the Louvain algorithm for modularity maximization instead of Leiden. The deprecated
+module ``modularitypruning.louvain_utilities`` now shims single-layer functions to their corresponding Leiden versions
+in ``modularitypruning.leiden_utilities`` (though it still contains the legacy multi-layer functions since they can be
+faster in general -- leidenalg does not efficiently implement multilayer optimization).
 
 .. toctree::
    source/installation

setup.py

@@ -9,7 +9,7 @@
 
 setup(
     name='modularitypruning',
-    version='1.2.3',
+    version='1.3.0',
     package_dir={'modularitypruning': 'utilities'},
     packages=['modularitypruning'],
     url='https://github.com/ragibson/ModularityPruning',

tests/test_temporal_multilevel_parameter_estimation.py

@@ -60,7 +60,7 @@ def assert_temporal_SBM_correct_convergence(self, first_layer_membership, copyin
 
     def test_temporal_SBM_correct_convergence_varying_copying_probabilty(self):
         for eta in [0.25, 0.5, 0.75, 0.9]:
-            membership = generate_random_partition(num_nodes=100, K=2)
+            membership = generate_random_partition(num_nodes=250, K=2)
             self.assert_temporal_SBM_correct_convergence(copying_probability=eta, first_layer_membership=membership)
 
     def test_temporal_SBM_correct_convergence_varying_p_in(self):

utilities/leiden_utilities.py

@@ -77,8 +77,8 @@ def split_intralayer_leiden_graph(G_intralayer, layer_membership):
     :return: list of intralayer networks
     :rtype: list[igraph.Graph]
     """
-    warnings.warn("You are using Leiden multilayer modularity optimization, "
-                  "which is inefficiently implemented by leidenalg. THIS CAN BE EXTREMELY SLOW!")
+    warnings.warn("You are using Leiden multilayer modularity optimization. THIS CAN BE EXTREMELY SLOW! "
+                  "leidenalg's implementation is inefficient, especially when there are many layers.")
     T = max(layer_membership) + 1
 
     G_split_layers_list = []

utilities/louvain_utilities.py

@@ -1,7 +1,10 @@
 """
 This is a deprecated version of leiden_utilities. Usage will be shimmed to use Leiden instead of Louvain when possible.
 
-The primary exceptions are the multilayer functions since leidenalg does not properly implement multilayer optimization.
+Prior to version v1.3.0, we used the Louvain algorithm for modularity maximization instead of Leiden. The deprecated
+module ``modularitypruning.louvain_utilities`` now shims single-layer functions to their corresponding Leiden versions
+in ``modularitypruning.leiden_utilities`` (though it still contains the legacy multi-layer functions since they can be
+faster in general -- leidenalg does not efficiently implement multilayer optimization).
 """
 from . import leiden_utilities
 from .leiden_utilities import sorted_tuple, LOW_MEMORY_THRESHOLD