adding functions to generate interactive tree - still needs work, but returns basic data object

Author: vsoch

singularity/analysis/compare.py

@@ -75,6 +75,7 @@ def container_similarity_vector(container1=None,packages_set=None,by=None,custom
     return comparisons
 
 
+
 def compare_containers(container1=None,container2=None,by=None,
                        image_package1=None,image_package2=None):
     '''compare_containers will generate a data structure with common and unique files to
@@ -105,19 +106,29 @@ def compare_containers(container1=None,container2=None,by=None,
     # Do the comparison for each metric
     comparisons = dict()
     for b in by:
-        intersect = list(set(container1_guts[b]).intersection(container2_guts[b]))
-        unique1 = list(set(container1_guts[b]).difference(container2_guts[b]))
-        unique2 = list(set(container2_guts[b]).difference(container1_guts[b]))
-
-        # Return data structure
-        comparison = {"intersect":intersect,
-                      "unique1": unique1,
-                      "unique2": unique2,
-                      "total1": len(container1_guts[b]),
-                      "total2": len(container2_guts[b])}
-        comparisons[b] = comparison 
+        comparisons[b] = compare_lists(container1_guts[b],container2_guts[b])
 
     return comparisons
+
+
+def compare_lists(list1,list2):
+    '''compare lists is the lowest level that drives compare_containers and
+    compare_packages. It returns a comparison object (dict) with the unique,
+    total, and intersecting things between two lists
+    :param list1: the list for container1
+    :param list2: the list for container2
+    '''
+    intersect = list(set(list1).intersection(list2))
+    unique1 = list(set(list1).difference(list2))
+    unique2 = list(set(list2).difference(list1))
+
+    # Return data structure
+    comparison = {"intersect":intersect,
+                  "unique1": unique1,
+                  "unique2": unique2,
+                  "total1": len(list1),
+                  "total2": len(list2)}
+    return comparison
 
 
 def calculate_similarity(container1=None,container2=None,image_package1=None,

singularity/version.py

@@ -1,4 +1,4 @@
-__version__ = "1.1.0"
+__version__ = "1.1.1"
 AUTHOR = 'Vanessa Sochat'
 AUTHOR_EMAIL = '[email protected]'
 NAME = 'singularity'

singularity/views/trees.py

@@ -4,7 +4,7 @@
 singularity views/trees.py: part of singularity package
 
 '''
-
+from functools import reduce
 import json
 
 from singularity.logman import bot
@@ -227,3 +227,63 @@ def make_package_tree(matrix=None,labels=None,width=25,height=10,title=None):
                leaf_font_size=8.,  # font size for the x axis labels
                labels=labels)
     return plt
+
+
+def make_interactive_tree(matrix=None,labels=None):
+    '''make interactive tree will return complete html for an interactive tree
+    :param title: a title for the plot, if not defined, will be left out.
+    '''
+    from scipy.cluster.hierarchy import (
+        dendrogram, 
+        linkage,
+        to_tree
+    )
+
+    d3 = None
+    from scipy.cluster.hierarchy import cophenet
+    from scipy.spatial.distance import pdist
+
+    if isinstance(matrix,pandas.DataFrame):
+        Z = linkage(matrix, 'ward') # clusters
+        T = to_tree(Z, rd=False)
+
+        if labels == None:
+            labels = matrix.index.tolist()
+        lookup = dict(zip(range(len(labels)), labels))
+
+        # Create a dendrogram object without plotting
+        dend = dendrogram(Z,no_plot=True,
+                      orientation="right",
+                      leaf_rotation=90.,  # rotates the x axis labels
+                      leaf_font_size=8.,  # font size for the x axis labels
+                      labels=labels)
+
+        d3 = dict(children=[], name="root")
+        add_node(T, d3)
+        label_tree(d3["children"][0],lookup)
+    else:
+        bot.logger.warning('Please provide data as pandas Data Frame.')
+    return d3
+
+
+def add_node(node, parent):
+    '''add_node will add a node to it's parent
+    '''
+    newNode = dict(node_id=node.id, children=[])
+    parent["children"].append(newNode)
+    if node.left: add_node(node.left, newNode)
+    if node.right: add_node(node.right, newNode)
+
+
+def label_tree(n,lookup):
+    '''label tree will again recursively label the tree
+    :param n: the root node, usually d3['children'][0]
+    :param lookup: the node/id lookup
+    '''
+    if len(n["children"]) == 0:
+        leaves = [lookup[n["node_id"]]]
+    else:
+        leaves = reduce(lambda ls, c: ls + label_tree(c,lookup), n["children"], [])
+    del n["node_id"]
+    n["name"] = name = "-".join(sorted(map(str, leaves)))
+    return leaves