fix InvalidIndexError

spras/analysis/ml.py

@@ -78,6 +78,7 @@ def summarize_networks(file_paths: Iterable[Union[str, PathLike]]) -> pd.DataFra
                 str(tup[0]): 1,
             }, index=tup[1]
         )
+        dataframe = dataframe[~dataframe.index.duplicated(keep='first')]
         edge_dataframes.append(dataframe)
 
     # concatenating all the algorithm-specific dataframes together

test/ml/expected/expected-dataframe.csv

@@ -1,16 +1,16 @@
-,test-data-s1,test-data-s2,test-data-s3,test-data-longName,test-data-longName2,test-data-empty,test-data-spaces,test-data-mixed-direction
-A---B,1,1,0,0,0,0,0,0
-C---D,1,1,0,0,0,0,0,1
-E---F,1,1,0,0,0,0,0,1
-L---M,0,1,1,0,0,0,1,0
-M---N,0,0,1,0,0,0,0,0
-O---P,0,0,1,0,0,0,1,0
-P---Q,0,0,1,0,0,0,0,0
-node1---node2,0,0,0,1,0,0,0,0
-node1---node3,0,0,0,1,1,0,0,0
-node4---node5,0,0,0,1,1,0,0,0
-LONGERNAMES---TEST,0,0,0,1,1,0,0,0
-node2---node3,0,0,0,0,1,0,0,0
-nodes with---spaces in name,0,0,0,0,0,0,1,0
-A-->B,0,0,0,0,0,0,0,1
-B-->A,0,0,0,0,0,0,0,1
+,test-data-s1,test-data-s2,test-data-s3,test-data-longName,test-data-longName2,test-data-empty,test-data-spaces,test-data-mixed-direction,test-repeat-edges
+A---B,1,1,0,0,0,0,0,0,1
+C---D,1,1,0,0,0,0,0,1,1
+E---F,1,1,0,0,0,0,0,1,1
+L---M,0,1,1,0,0,0,1,0,0
+M---N,0,0,1,0,0,0,0,0,0
+O---P,0,0,1,0,0,0,1,0,0
+P---Q,0,0,1,0,0,0,0,0,0
+node1---node2,0,0,0,1,0,0,0,0,0
+node1---node3,0,0,0,1,1,0,0,0,0
+node4---node5,0,0,0,1,1,0,0,0,0
+LONGERNAMES---TEST,0,0,0,1,1,0,0,0,0
+node2---node3,0,0,0,0,1,0,0,0,0
+nodes with---spaces in name,0,0,0,0,0,0,1,0,0
+A-->B,0,0,0,0,0,0,0,1,0
+B-->A,0,0,0,0,0,0,0,1,0

test/ml/test_ml.py

@@ -22,7 +22,7 @@ def setup_class(cls):
     def test_summarize_networks(self):
         dataframe = ml.summarize_networks([INPUT_DIR + 'test-data-s1/s1.txt', INPUT_DIR + 'test-data-s2/s2.txt', INPUT_DIR + 'test-data-s3/s3.txt',
                                            INPUT_DIR + 'test-data-longName/longName.txt', INPUT_DIR + 'test-data-longName2/longName2.txt',
-                                           INPUT_DIR + 'test-data-empty/empty.txt', INPUT_DIR + 'test-data-spaces/spaces.txt', INPUT_DIR + 'test-data-mixed-direction/mixed-direction.txt'])
+                                           INPUT_DIR + 'test-data-empty/empty.txt', INPUT_DIR + 'test-data-spaces/spaces.txt', INPUT_DIR + 'test-data-mixed-direction/mixed-direction.txt',  INPUT_DIR + 'test-repeat-edges/repeat.txt'])
         dataframe.to_csv(OUT_DIR + 'dataframe.csv')
         assert filecmp.cmp(OUT_DIR + 'dataframe.csv', EXPECT_DIR + 'expected-dataframe.csv', shallow=False)
 
@@ -42,9 +42,6 @@ def test_summarize_networks_wrong_direction(self):
         with pytest.raises(ValueError):
             ml.summarize_networks([INPUT_DIR + 'test-data-wrong-direction/wrong-direction.txt'])
 
-    def test_repeat_edges(self):
-        ml.summarize_networks([INPUT_DIR + 'test-data-s1/s1.txt', INPUT_DIR + 'test-repeat-edges/repeat.txt'])
-
     def test_empty(self):
         dataframe = ml.summarize_networks([INPUT_DIR + 'test-data-empty/empty.txt'])
         with pytest.raises(ValueError):  # raises error if empty dataframe is used for post processing