Merge pull request #226 from kayjan/fix-zero-null-check

fix: null checks to ignore zero values

Author: kayjan

CHANGELOG.md

@@ -5,11 +5,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+
+## [0.17.2] - 2024-04-24
 ### Changed:
 - DAG Constructor: `list_to_dag` and `dict_to_dag` does not rely on `dataframe_to_dag` as pandas dataframe operation
 is phased out.
 ### Fixed:
 - DAG Constructor: Handle cases where reserved keywords are part of attribute upon creation and throw error accordingly.
+- [#224] Tree/DAG Constructor: Null checks to not interpret 0 as null, this affects `dataframe_to_tree_by_relation`,
+`add_dataframe_to_tree_by_path`, `add_dataframe_to_tree_by_name`, `dataframe_to_tree`, and `dataframe_to_dag`.
+This will also affect showing/printing of trees when `attr_omit_null` is set to True.
 
 ## [0.17.1] - 2024-04-23
 ### Fixed
@@ -550,7 +555,8 @@ 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/0.17.1...HEAD
+[Unreleased]: https://github.com/kayjan/bigtree/compare/0.17.2...HEAD
+[0.17.2]: https://github.com/kayjan/bigtree/compare/0.17.1...0.17.2
 [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

bigtree/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.17.1"
+__version__ = "0.17.2"
 
 from bigtree.binarytree.construct import list_to_binarytree
 from bigtree.dag.construct import dataframe_to_dag, dict_to_dag, list_to_dag

bigtree/utils/assertions.py

@@ -206,7 +206,7 @@ def isnull(value: Any) -> bool:
     """
     import math
 
-    if not value or (isinstance(value, float) and math.isnan(value)):
+    if value is None or (isinstance(value, float) and math.isnan(value)):
         return True
     return False
 

tests/dag/test_construct.py

@@ -180,6 +180,42 @@ def test_dataframe_to_dag_reverse():
         assert_dag_structure_root(dag)
         assert_dag_structure_root_attr(dag)
 
+    @staticmethod
+    def test_dataframe_to_dag_zero_attribute():
+        from bigtree.utils.iterators import dag_iterator
+
+        data = pd.DataFrame(
+            [
+                ["a", None, 0],
+                ["b", None, None],
+                ["c", "a", -1],
+                ["c", "b", -1],
+                ["d", "a", 40],
+                ["d", "c", 40],
+                ["e", "d", 35],
+                ["f", "c", 38],
+                ["f", "d", 38],
+                ["g", "c", 10],
+                ["h", "g", 6],
+            ],
+            columns=["child", "parent", "value"],
+        )
+        dag = dataframe_to_dag(data)
+        assert_dag_structure_root(dag)
+        for parent, _ in dag_iterator(dag):
+            match parent.name:
+                case "a":
+                    assert hasattr(
+                        parent, "value"
+                    ), "Check a attribute, expected value attribute"
+                    assert parent.value == 0, "Check a value, expected 0"
+                case "b":
+                    assert not hasattr(
+                        parent, "value"
+                    ), "Check b attribute, expected no value attribute"
+                case "c":
+                    assert parent.value == -1, "Check c value, expected -1"
+
     def test_dataframe_to_dag_empty_row_error(self):
         with pytest.raises(ValueError) as exc_info:
             dataframe_to_dag(pd.DataFrame(columns=["child", "parent", "age"]))

tests/tree/test_construct.py

@@ -616,6 +616,32 @@ def test_add_dataframe_to_tree_by_path_col_name(self):
         assert_tree_structure_node_root(self.root)
 
     def test_add_dataframe_to_tree_by_path_col_name_reverse(self):
+        data = pd.DataFrame(
+            [
+                ["a", 0],
+                ["a/b", None],
+                ["a/c", -1],
+                ["a/b/d", 40],
+                ["a/b/e", 35],
+                ["a/c/f", 38],
+                ["a/b/e/g", 10],
+                ["a/b/e/h", 6],
+            ],
+            columns=["PATH", "value"],
+        )
+        add_dataframe_to_tree_by_path(self.root, data)
+        assert_tree_structure_basenode_root(self.root)
+        assert_tree_structure_node_root(self.root)
+        assert hasattr(
+            self.root, "value"
+        ), "Check root attribute, expected value attribute"
+        assert self.root.value == 0, "Check root value, expected 0"
+        assert not hasattr(
+            self.root["b"], "value"
+        ), "Check b attribute, expected no value attribute"
+        assert self.root["c"].value == -1, "Check c value, expected -1"
+
+    def test_add_dataframe_to_tree_by_path_zero_attribute(self):
         add_dataframe_to_tree_by_path(
             self.root,
             self.data[["age", "PATH"]],
@@ -1025,6 +1051,32 @@ def test_add_dataframe_to_tree_by_name_col_name_reverse(self):
         assert_tree_structure_basenode_root_attr(self.root)
         assert_tree_structure_node_root(self.root)
 
+    def test_add_dataframe_to_tree_by_name_zero_attribute(self):
+        data = pd.DataFrame(
+            [
+                ["a", 0],
+                ["b", None],
+                ["c", -1],
+                ["d", 40],
+                ["e", 35],
+                ["f", 38],
+                ["g", 10],
+                ["h", 6],
+            ],
+            columns=["NAME", "value"],
+        )
+        add_dataframe_to_tree_by_name(self.root, data)
+        assert_tree_structure_basenode_root(self.root)
+        assert_tree_structure_node_root(self.root)
+        assert hasattr(
+            self.root, "value"
+        ), "Check root attribute, expected value attribute"
+        assert self.root.value == 0, "Check root value, expected 0"
+        assert not hasattr(
+            self.root["b"], "value"
+        ), "Check b attribute, expected no value attribute"
+        assert self.root["c"].value == -1, "Check c value, expected -1"
+
     def test_add_dataframe_to_tree_by_name_empty_error(self):
         with pytest.raises(ValueError) as exc_info:
             add_dataframe_to_tree_by_name(self.root, pd.DataFrame())
@@ -2075,6 +2127,30 @@ def test_dataframe_to_tree_no_attribute():
         root = dataframe_to_tree(path_data)
         assert_tree_structure_basenode_root(root)
 
+    @staticmethod
+    def test_dataframe_to_tree_zero_attribute():
+        path_data = pd.DataFrame(
+            [
+                ["a", 0],
+                ["a/b", None],
+                ["a/c", -1],
+                ["a/b/d", 1],
+                ["a/b/e", 1],
+                ["a/c/f", 1],
+                ["a/b/e/g", 1],
+                ["a/b/e/h", 1],
+            ],
+            columns=["PATH", "value"],
+        )
+        root = dataframe_to_tree(path_data)
+        assert_tree_structure_basenode_root(root)
+        assert hasattr(root, "value"), "Check root attribute, expected value attribute"
+        assert root.value == 0, "Check root value, expected 0"
+        assert not hasattr(
+            root["b"], "value"
+        ), "Check b attribute, expected no value attribute"
+        assert root["c"].value == -1, "Check c value, expected -1"
+
     @staticmethod
     def test_dataframe_to_tree_empty_row_error():
         path_data = pd.DataFrame(columns=["PATH", "age"])
@@ -2427,6 +2503,31 @@ def test_dataframe_to_tree_by_relation_col_name_reverse(self):
         assert_tree_structure_basenode_root_attr(root)
         assert_tree_structure_node_root(root)
 
+    @staticmethod
+    def test_dataframe_to_tree_by_relation_zero_attribute():
+        relation_data = pd.DataFrame(
+            [
+                ["a", None, 0],
+                ["b", "a", None],
+                ["c", "a", -1],
+                ["d", "b", 40],
+                ["e", "b", 35],
+                ["f", "c", 38],
+                ["g", "e", 10],
+                ["h", "e", 6],
+            ],
+            columns=["child", "parent", "value"],
+        )
+        root = dataframe_to_tree_by_relation(relation_data)
+        assert_tree_structure_basenode_root(root)
+        assert_tree_structure_node_root(root)
+        assert hasattr(root, "value"), "Check root attribute, expected value attribute"
+        assert root.value == 0, "Check root value, expected 0"
+        assert not hasattr(
+            root["b"], "value"
+        ), "Check b attribute, expected no value attribute"
+        assert root["c"].value == -1, "Check c value, expected -1"
+
     @staticmethod
     def test_dataframe_to_tree_by_relation_empty_row_error():
         relation_data = pd.DataFrame(columns=["child", "parent"])

tests/tree/test_export.py

@@ -119,7 +119,7 @@ def test_print_tree_attr_omit_null_true(tree_node_negative_null_attr):
             "│   └── e\n"
             "│       ├── g [age=10]\n"
             "│       └── h\n"
-            "└── c\n"
+            "└── c [age=0]\n"
             "    └── f\n"
         )
         assert_print_statement(