Merge pull request #223 from kayjan/fix-error-dtype

fix: dataframe_to_tree_by_relation error message to handle different …

Author: kayjan

CHANGELOG.md

@@ -6,6 +6,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.17.1] - 2024-04-23
+### Fixed
+- [#222] Tree Constructor: `dataframe_to_tree_by_relation` duplicate root node name error message to handle
+different data types.
+
 ## [0.17.0] - 2024-04-04
 ### Added
 - Misc: Group tests for benchmark timings to compare the timings by multiplier more effectively.
@@ -540,7 +545,8 @@ ignore null attribute columns.
 - Utility Iterator: Tree traversal methods.
 - Workflow To Do App: Tree use case with to-do list implementation.
 
-[Unreleased]: https://github.com/kayjan/bigtree/compare/0.17.0...HEAD
+[Unreleased]: https://github.com/kayjan/bigtree/compare/0.17.1...HEAD
+[0.17.1]: https://github.com/kayjan/bigtree/compare/0.17.0...0.17.1
 [0.17.0]: https://github.com/kayjan/bigtree/compare/0.16.4...0.17.0
 [0.16.4]: https://github.com/kayjan/bigtree/compare/0.16.3...0.16.4
 [0.16.3]: https://github.com/kayjan/bigtree/compare/0.16.2...0.16.3

bigtree/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.17.0"
+__version__ = "0.17.1"
 
 from bigtree.binarytree.construct import list_to_binarytree
 from bigtree.dag.construct import dataframe_to_dag, dict_to_dag, list_to_dag

bigtree/tree/construct.py

@@ -944,7 +944,8 @@ def dataframe_to_tree_by_relation(
     root_names.update(set(data[parent_col]) - set(data[child_col]) - {None})
     if len(root_names) != 1:
         raise ValueError(
-            f"Unable to determine root node\nPossible root nodes: {sorted(root_names)}"
+            f"Unable to determine root node\n"
+            f"Possible root nodes: {sorted(list(root_names), key=lambda v: (isinstance(v, str), v))}"
         )
     root_name = list(root_names)[0]
 

tests/tree/test_construct.py

@@ -2664,6 +2664,26 @@ def test_dataframe_to_tree_by_relation_multiple_root_error():
             exc_info.value
         ) == Constants.ERROR_NODE_DATAFRAME_MULTIPLE_ROOT.format(root_nodes=["a", "b"])
 
+    @staticmethod
+    def test_dataframe_to_tree_by_relation_multiple_root_and_type_error():
+        relation_data = pd.DataFrame(
+            [
+                ["a", None, 90],
+                ["c", "a", 60],
+                ["d", 1, 40],
+                ["e", 1, 35],
+                ["f", "c", 38],
+                ["g", "e", 10],
+                ["h", "e", 6],
+            ],
+            columns=["child", "parent", "age"],
+        )
+        with pytest.raises(ValueError) as exc_info:
+            dataframe_to_tree_by_relation(relation_data)
+        assert str(
+            exc_info.value
+        ) == Constants.ERROR_NODE_DATAFRAME_MULTIPLE_ROOT.format(root_nodes=[1, "a"])
+
     @staticmethod
     def test_dataframe_to_tree_by_relation_no_root_error():
         relation_data = pd.DataFrame(