Fix ranking normalization for 0-based rankings

This would previously fail due to a division by 0 if the ranking is
0-based and consists of only one object.

csrank/dataset_reader/objectranking/util.py

@@ -109,7 +109,9 @@ def complete_linear_regression_dataset(X, rankings):
     Y_single = []
     for features, rank in zip(X, rankings):
         X1.extend(features)
-        norm_ranks = rank / np.max(rank, axis=0)
+        min_rank = np.min(rank, axis=0)
+        max_rank = np.max(rank, axis=0)
+        norm_ranks = (rank - min_rank + 1) / (max_rank - min_rank + 1)
         Y_single.extend(norm_ranks)
     X1 = np.array(X1)
     Y_single = np.array(Y_single)