Fix python3 dendrogram display bug (#25)

Author: Seth-Rothschild

henchman/plotting.py

@@ -512,71 +512,69 @@ def dendrogram(D, figargs=None):
     '''
     if figargs is None:
         return lambda figargs: dendrogram(D, figargs=figargs)
+    G = nx.Graph()
+
+    vertices_source = ColumnDataSource(
+        pd.DataFrame({'index': D.columns.keys(),
+                      'desc': list(D.columns.values())}))
+    edges_source = ColumnDataSource(
+        pd.DataFrame(D.edges[0]).rename(
+            columns={1: 'end', 0: 'start'}))
+    step_source = ColumnDataSource(
+        pd.DataFrame({'step': [0],
+                      'thresh': [D.threshlist[0]],
+                      'components': [len(D.graphs[0])]}))
+
+    G.add_nodes_from([str(x) for x in vertices_source.data['index']])
+    G.add_edges_from(zip(
+        [str(x) for x in edges_source.data['start']],
+        [str(x) for x in edges_source.data['end']]))
+
+    graph_renderer = from_networkx(G, nx.circular_layout,
+                                   scale=1, center=(0, 0))
+
+    graph_renderer.node_renderer.data_source = vertices_source
+    graph_renderer.node_renderer.view = CDSView(source=vertices_source)
+    graph_renderer.edge_renderer.data_source = edges_source
+    graph_renderer.edge_renderer.view = CDSView(source=edges_source)
+
+    plot = Plot(plot_width=400, plot_height=400,
+                x_range=Range1d(-1.1, 1.1),
+                y_range=Range1d(-1.1, 1.1))
+    plot.title.text = "Feature Connectivity"
+    graph_renderer.node_renderer.glyph = Circle(
+        size=5, fill_color=Spectral4[0])
+    graph_renderer.node_renderer.selection_glyph = Circle(
+        size=15, fill_color=Spectral4[2])
+    graph_renderer.edge_renderer.data_source = edges_source
+    graph_renderer.edge_renderer.glyph = MultiLine(line_color="#CCCCCC",
+                                                   line_alpha=0.6,
+                                                   line_width=.5)
+    graph_renderer.edge_renderer.selection_glyph = MultiLine(
+        line_color=Spectral4[2],
+        line_width=3)
+    graph_renderer.node_renderer.hover_glyph = Circle(
+        size=5,
+        fill_color=Spectral4[1])
+    graph_renderer.selection_policy = NodesAndLinkedEdges()
+    graph_renderer.inspection_policy = NodesAndLinkedEdges()
+
+    plot.renderers.append(graph_renderer)
+
+    plot.add_tools(
+        HoverTool(tooltips=[("feature", "@desc"),
+                            ("index", "@index"), ]),
+        TapTool(),
+        BoxZoomTool(),
+        SaveTool(),
+        ResetTool())
 
-    def modify_doc(doc, D, figargs):
-        G = nx.Graph()
-
-        vertices_source = ColumnDataSource(
-            pd.DataFrame({'index': D.columns.keys(),
-                          'desc': D.columns.values()}))
-        edges_source = ColumnDataSource(
-            pd.DataFrame(D.edges[0]).rename(
-                columns={1: 'end', 0: 'start'}))
-        step_source = ColumnDataSource(
-            pd.DataFrame({'step': [0],
-                          'thresh': [D.threshlist[0]],
-                          'components': [len(D.graphs[0])]}))
-
-        G.add_nodes_from(vertices_source.data['index'])
-        G.add_edges_from(zip(
-            edges_source.data['start'],
-            edges_source.data['end']))
-
-        graph_renderer = from_networkx(G, nx.circular_layout,
-                                       scale=1, center=(0, 0))
-
-        graph_renderer.node_renderer.data_source = vertices_source
-        graph_renderer.node_renderer.view = CDSView(source=vertices_source)
-        graph_renderer.edge_renderer.data_source = edges_source
-        graph_renderer.edge_renderer.view = CDSView(source=edges_source)
-
-        plot = Plot(plot_width=400, plot_height=400,
-                    x_range=Range1d(-1.1, 1.1),
-                    y_range=Range1d(-1.1, 1.1))
-        plot.title.text = "Feature Connectivity"
-
-        graph_renderer.node_renderer.glyph = Circle(
-            size=5, fill_color=Spectral4[0])
-        graph_renderer.node_renderer.selection_glyph = Circle(
-            size=15, fill_color=Spectral4[2])
-
-        graph_renderer.edge_renderer.data_source = edges_source
-        graph_renderer.edge_renderer.glyph = MultiLine(line_color="#CCCCCC",
-                                                       line_alpha=0.6,
-                                                       line_width=.5)
-        graph_renderer.edge_renderer.selection_glyph = MultiLine(
-            line_color=Spectral4[2],
-            line_width=3)
-
-        graph_renderer.node_renderer.hover_glyph = Circle(
-            size=5,
-            fill_color=Spectral4[1])
-
-        graph_renderer.selection_policy = NodesAndLinkedEdges()
-        graph_renderer.inspection_policy = NodesAndLinkedEdges()
-
-        plot.renderers.append(graph_renderer)
-
-        plot.add_tools(
-            HoverTool(tooltips=[("feature", "@desc"),
-                                ("index", "@index"), ]),
-            TapTool(),
-            BoxZoomTool(),
-            SaveTool(),
-            ResetTool())
-
-        plot = _modify_plot(plot, figargs)
+    plot = _modify_plot(plot, figargs)
+
+    if figargs['static']:
+        return plot
 
+    def modify_doc(doc, D, figargs):
         data_table = DataTable(source=step_source,
                                columns=[TableColumn(field='step',
                                                     title='Step'),
@@ -600,7 +598,7 @@ def callback(attr, old, new):
                 print(e)
 
         slider = Slider(start=0,
-                        end=len(D.edges),
+                        end=(len(D.edges) - 1),
                         value=0,
                         step=1,
                         title="Step")

henchman/selection.py

@@ -111,6 +111,9 @@ def fit(self, X, pairing_func=None, max_threshes=None):
         # Make graphs for every thresh
         self._build_graphs()
 
+        assert len(self.edges) > 0, 'Failed to build edges'
+        assert len(self.graphs) > 0, 'Failed to build graphs'
+
     def set_params(self, **params):
         '''Method to functionally assign parameters.
         Expects a dictionary **params as input.
@@ -123,7 +126,7 @@ def _find_all_graphs(self):
 
         self.graphs = []
         for edges in tqdm(self.edges):
-            out = find_connected_components(self.columns.keys(), edges)
+            out = find_connected_components(list(self.columns.keys()), edges)
             self.graphs.append(out)
 
     def _build_graphs(self):
@@ -132,9 +135,6 @@ def _build_graphs(self):
         for i, graph in enumerate(self.graphs):
             if len(graph) == 1:
                 break
-            if len(graph) == len(self.columns) and i > 0:
-                i += -1
-                break
         self.threshlist = self.threshlist[:i]
         self.edges = self.edges[:i]
         self.graphs = self.graphs[:i]
@@ -143,14 +143,12 @@ def _build_edges(self, max_threshes):
         self.edges = []
         self.graphs = []
         uniques = list(np.unique(self.adj))
-        # uniques.reverse()
+        uniques = [x for x in uniques if not math.isnan(x)]
         if max_threshes is None and len(uniques) > 500:
             print('Calculating more than 500 graphs')
             print('You can pass max_threshes as a kwarg to Dendrogram')
         if max_threshes is not None:
             if len(uniques) > max_threshes:
-                # Strip nans
-                uniques = [x for x in uniques if not math.isnan(x)]
                 # Take max_threshes evenly spaced thresholds
                 uniques = uniques[::int(np.floor((len(uniques)/max_threshes)) + 1)]
 

setup.cfg

@@ -18,7 +18,6 @@ universal = 1
 exclude = docs
 max-line-length = 100
 
-
 [aliases]
 # Define setup.py command aliases here
 test = pytest

tests/test_selection.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 
 """Tests for `learning` module"""
+import numpy as np
 import pandas as pd
 import pytest
 
@@ -87,14 +88,29 @@ def test_dend_transform(Xy, fit_dend, capsys):
     assert X_new_2.shape[1] == int(out2[-3:-1])
 
 def test_dend_plot(fit_dend):
+    show(dendrogram(fit_dend), static=True)
     show(dendrogram(fit_dend))
-    
-
-
-
 
+def test_build_edges(capsys):
+    fake_sel = selection.Dendrogram()
+    fake_sel.adj = np.asarray(range(501))
+    fake_sel._build_edges(None)
 
-
-    
-
+    output, _ = capsys.readouterr()
+    split_output = output.split('\n')
 
+    real_line_1 = 'Calculating more than 500 graphs'
+    real_line_2 = 'You can pass max_threshes as a kwarg to Dendrogram'
+    assert split_output[0] == real_line_1
+    assert split_output[1] == real_line_2
+
+def test_build_graphs_exit():
+    fake_sel = selection.Dendrogram()
+    fake_sel.threshlist = [1, 2]
+    fake_sel.edges = [[(0, 1)], [(1, 2), (0, 1)]] 
+    fake_sel.graphs = [{0: {0, 1}, 2: {2}}, {0: {0, 1, 2}}]
+    fake_sel._build_graphs()
+
+    assert fake_sel.threshlist == [1]
+    assert fake_sel.edges[0][0][0] == 0
+    assert fake_sel.graphs[0][2] == {2}