Merge pull request #176 from thclark/master

Fixed pathologically slow looped plotting routine.

Author: lmcinnes

hdbscan/plots.py

@@ -51,19 +51,19 @@ def _get_leaves(condensed_tree):
 class CondensedTree(object):
     """The condensed tree structure, which provides a simplified or smoothed version
     of the :class:`~hdbscan.plots.SingleLinkageTree`.
-    
+
     Parameters
     ----------
     condensed_tree_array : numpy recarray from :class:`~hdbscan.HDBSCAN`
         The raw numpy rec array version of the condensed tree as produced
         internally by hdbscan.
-        
+
     cluster_selection_method : string, optional (default 'eom')
         The method of selecting clusters. One of 'eom' or 'leaf'
 
     allow_single_cluster : Boolean, optional (default False)
         Whether to allow the root cluster as the only selected cluster
-    
+
     """
     def __init__(self, condensed_tree_array, cluster_selection_method='eom',
                  allow_single_cluster=False):
@@ -75,20 +75,20 @@ def get_plot_data(self,
                       leaf_separation=1,
                       log_size=False,
                       max_rectangle_per_icicle=20):
-        """Generates data for use in plotting the 'icicle plot' or dendrogram 
+        """Generates data for use in plotting the 'icicle plot' or dendrogram
         plot of the condensed tree generated by HDBSCAN.
 
         Parameters
         ----------
         leaf_separation : float, optional
-                          How far apart to space the final leaves of the 
+                          How far apart to space the final leaves of the
                           dendrogram. (default 1)
 
         log_size : boolean, optional
                    Use log scale for the 'size' of clusters (i.e. number of
                    points in the cluster at a given lambda value).
                    (default False)
-        
+
         max_rectangles_per_icicle : int, optional
             To simplify the plot this method will only emit
             ``max_rectangles_per_icicle`` bars per branch of the dendrogram.
@@ -104,7 +104,7 @@ def get_plot_data(self,
                         `bar_bottoms` y coordinate of bottoms of bars
                         `bar_widths` widths of the bars (in x coord scale)
                         `bar_bounds` a 4-tuple of [left, right, bottom, top]
-                                     giving the bounds on a full set of 
+                                     giving the bounds on a full set of
                                      cluster bars
                     Data associates with cluster splits:
                         `line_xs` x coordinates for horizontal dendrogram lines
@@ -135,8 +135,8 @@ def get_plot_data(self,
                 cluster_y_coords[left_child] = split['lambda_val'][0]
                 cluster_y_coords[right_child] = split['lambda_val'][1]
 
-        # We use bars to plot the 'icicles', so we need to generate centers, tops, 
-        # bottoms and widths for each rectangle. We can go through each cluster 
+        # We use bars to plot the 'icicles', so we need to generate centers, tops,
+        # bottoms and widths for each rectangle. We can go through each cluster
         # and do this for each in turn.
         bar_centers = []
         bar_tops = []
@@ -279,7 +279,7 @@ def plot(self, leaf_separation=1, cmap='viridis', select_clusters=False,
         Parameters
         ----------
         leaf_separation : float, optional (default 1)
-                          How far apart to space the final leaves of the 
+                          How far apart to space the final leaves of the
                           dendrogram.
 
         cmap : string or matplotlib colormap, optional (default viridis)
@@ -315,7 +315,7 @@ def plot(self, leaf_separation=1, cmap='viridis', select_clusters=False,
                    Use log scale for the 'size' of clusters (i.e. number of
                    points in the cluster at a given lambda value).
 
-           
+
         max_rectangles_per_icicle : int, optional (default 20)
             To simplify the plot this method will only emit
             ``max_rectangles_per_icicle`` bars per branch of the dendrogram.
@@ -359,8 +359,14 @@ def plot(self, leaf_separation=1, cmap='viridis', select_clusters=False,
             linewidth=0
         )
 
+        drawlines = []
         for xs, ys in zip(plot_data['line_xs'], plot_data['line_ys']):
-            axis.plot(xs, ys, color='black', linewidth=1)
+            drawlines.append(xs)
+            drawlines.append(ys)
+        axis.plot(*drawlines, color='black', linewidth=1)
+        # for xs, ys in zip(plot_data['line_xs'], plot_data['line_ys']):
+        #     axis.plot(xs, ys, color='black', linewidth=1)
+
         if select_clusters:
             try:
                 from matplotlib.patches import Ellipse
@@ -426,10 +432,10 @@ def to_pandas(self):
 
         Each row of the dataframe corresponds to an edge in the tree.
         The columns of the dataframe are `parent`, `child`, `lambda_val`
-        and `child_size`. 
+        and `child_size`.
 
         The `parent` and `child` are the ids of the
-        parent and child nodes in the tree. Node ids less than the number 
+        parent and child nodes in the tree. Node ids less than the number
         of points in the original dataset represent individual points, while
         ids greater than the number of points are clusters.
 
@@ -482,13 +488,13 @@ def _line_width(y, linkage):
 class SingleLinkageTree(object):
     """A single linkage format dendrogram tree, with plotting functionality
     and networkX support.
-    
+
     Parameters
     ----------
     linkage : ndarray (n_samples, 4)
         The numpy array that holds the tree structure. As output by
         scipy.cluster.hierarchy, hdbscan, of fastcluster.
-    
+
     """
     def __init__(self, linkage):
         self._linkage = linkage
@@ -500,29 +506,29 @@ def plot(self, axis=None, truncate_mode=None, p=0, vary_line_width=True,
         Parameters
         ----------
         truncate_mode : str, optional
-                        The dendrogram can be hard to read when the original 
-                        observation matrix from which the linkage is derived 
-                        is large. Truncation is used to condense the dendrogram. 
+                        The dendrogram can be hard to read when the original
+                        observation matrix from which the linkage is derived
+                        is large. Truncation is used to condense the dendrogram.
                         There are several modes:
 
         ``None/'none'``
                 No truncation is performed (Default).
-    
+
         ``'lastp'``
-                The last p non-singleton formed in the linkage are the only 
-                non-leaf nodes in the linkage; they correspond to rows 
-                Z[n-p-2:end] in Z. All other non-singleton clusters are 
+                The last p non-singleton formed in the linkage are the only
+                non-leaf nodes in the linkage; they correspond to rows
+                Z[n-p-2:end] in Z. All other non-singleton clusters are
                 contracted into leaf nodes.
 
         ``'level'/'mtica'``
-                No more than p levels of the dendrogram tree are displayed. 
+                No more than p levels of the dendrogram tree are displayed.
                 This corresponds to Mathematica(TM) behavior.
 
         p : int, optional
             The ``p`` parameter for ``truncate_mode``.
 
         vary_line_width : boolean, optional
-            Draw downward branches of the dendrogram with line thickness that 
+            Draw downward branches of the dendrogram with line thickness that
             varies depending on the size of the cluster.
 
         cmap : string or matplotlib colormap, optional
@@ -617,11 +623,11 @@ def to_pandas(self):
         """Return a pandas dataframe representation of the single linkage tree.
 
         Each row of the dataframe corresponds to an edge in the tree.
-        The columns of the dataframe are `parent`, `left_child`, 
+        The columns of the dataframe are `parent`, `left_child`,
         `right_child`, `distance` and `size`.
 
         The `parent`, `left_child` and `right_child` are the ids of the
-        parent and child nodes in the tree. Node ids less than the number 
+        parent and child nodes in the tree. Node ids less than the number
         of points in the original dataset represent individual points, while
         ids greater than the number of points are clusters.
 
@@ -731,7 +737,7 @@ def plot(self, axis=None, node_size=40, node_color='k',
                 (default 0.8).
 
         edge_cmap : matplotlib colormap, optional
-                The colormap to color edges by (varying color by edge 
+                The colormap to color edges by (varying color by edge
                     weight/distance). Can be a cmap object or a string
                     recognised by matplotlib. (default `viridis_r`)