add option to disable edge rescaling to provide edge weights as integers, closes #1

tests/analysis/test_graphs.py

@@ -326,6 +326,15 @@ def test_pipe_rescale_graph_edge_weights(tk_graph):
     assert rescaled_undir[1][2]['weight'] == pytest.approx(1.0)
 
 
+def test_pipe_graph_split(tk_graph):
+    graph_copy, graph_undir = graphs.pipe_graph_split(tk_graph)
+    assert len(graph_copy.nodes) == len(tk_graph.nodes)
+    assert len(graph_copy.edges) == len(tk_graph.edges)
+    assert len(graph_copy.nodes) == len(graph_undir.nodes)
+    assert len(graph_undir.nodes) == len(tk_graph.nodes)
+    assert len(graph_undir.edges) != len(tk_graph.edges)
+
+
 @pytest.mark.parametrize('import_graph', ['graph', 'tk_graph'])
 def test_rescale_edge_weights(import_graph, request):
     test_graph = request.getfixturevalue(import_graph)

tests/analysis/test_preprocessing.py

@@ -29,13 +29,6 @@ def test_remove_na(raw_data_path, raw_data_date_cols):
     assert len(data) == 998
 
 
-# def test_string_cleansing():
-#     string = 'Ölleckage   durch\nundichten \t Ölsumpf,, aber Dichtung intakt??!!!'
-#     cleaned_string = shared.clean_string_slim(string)
-#     target_string = 'Ölleckage durch undichten Ölsumpf, aber Dichtung intakt!'
-#     assert cleaned_string == target_string
-
-
 def test_entry_wise_cleansing(raw_data_path, raw_data_date_cols):
     (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
     (data,) = ppc.remove_duplicates(data)