Merge pull request #30 from microsoft/fix-graph-from-dataset

topologic.io.from_dataset ignoring empty directed graphs and creating undirected instead

docs/release_notes.md

@@ -1,5 +1,9 @@
 # Release Notes
 
+## 0.1.1
+- [Issue 29](https://github.com/microsoft/topologic/issues/29) Fixed bug in `topologic.io.from_dataset` where an empty networkx graph object (Graph, DiGraph, etc) was being treated as if no networkx Graph object were provided at all.
+- Added `is_digraph` parameter to `topologic.io.from_file`. This parameter defaults to False for original behavior. Setting it to True will create a networkx DiGraph object instead.
+
 ## 0.1.0
 - Initial release
 

tests/io/test_csv_loader.py

@@ -4,6 +4,7 @@
 import unittest
 
 import csv
+import networkx as nx
 from topologic.io import CsvDataset, from_dataset, from_file, load
 from topologic import projection
 from ..utils import data_file
@@ -141,6 +142,15 @@ def test_edge_then_vertex(self):
                 graph.nodes["frank"]["attributes"][0]
             )
 
+    def test_digraph_from_dataset(self):
+        digraph = nx.DiGraph()
+        with open(data_file("tiny-graph.csv")) as edge_file:
+            dataset = CsvDataset(edge_file, True, "excel")
+            proj = projection.edge_ignore_metadata(1, 2, 4)
+            graph = from_dataset(dataset, proj, digraph)
+
+        self.assertEqual(digraph, graph)
+
 
 class TestCsvLoaderFromFile(unittest.TestCase):
     def test_invalid_projection_values(self):
@@ -313,3 +323,16 @@ def test_vertex_single_projection(self):
                     {"lastName": "redhot", "sandwichPreference": "buffalo chicken"},
                     graph.nodes["frank"]["attributes"][0]
                 )
+
+    def test_digraph_from_file(self):
+        with open(data_file("tiny-graph.csv")) as edge_file:
+            graph = from_file(
+                edge_csv_file=edge_file,
+                source_column_index=1,
+                target_column_index=2,
+                weight_column_index=4,
+                edge_csv_has_headers=True,
+                is_digraph=True
+            )
+
+        self.assertTrue(graph.is_directed())

topologic/io/csv_loader.py

@@ -45,7 +45,7 @@ def from_dataset(
     :return: the graph object
     :rtype: nx.Graph
     """
-    if not graph:
+    if graph is None:
         graph = nx.Graph()
 
     projection_function = projection_function_generator(graph)
@@ -72,7 +72,8 @@ def from_file(
     vertex_csv_use_headers: Optional[List[str]] = None,
     vertex_metadata_behavior: str = "single",
     vertex_ignored_values: Optional[List[str]] = None,
-    sample_size: int = 50
+    sample_size: int = 50,
+    is_digraph: bool = False,
 ) -> nx.Graph:
     """
     This function weaves a lot of graph materialization code into a single call.
@@ -160,6 +161,7 @@ def from_file(
         Please note that this sample_size does NOT advance your underlying iterator, nor is there any guarantee that
         the csv Sniffer class will use every row extracted via sample_size.  Setting this above 50 may not have the
         impact you hope for due to the csv.Sniffer.has_header function - it will use at most 20 rows.
+    :param bool is_digraph: If the data represents an undirected graph or a directed graph. Default is `False`.
     :return: The graph populated graph
     :rtype: nx.Graph
     """
@@ -197,7 +199,8 @@ def from_file(
     if edge_projection_function is None:
         raise ValueError('edge_metadata_behavior must be "none", "collection", or "single"')
 
-    graph = from_dataset(edge_dataset, edge_projection_function)
+    graph = nx.DiGraph() if is_digraph else nx.Graph()
+    graph = from_dataset(edge_dataset, edge_projection_function, graph)
 
     if vertex_csv_file:
         if vertex_column_index is None: