Adds more comments for recent changes

hamilton/graph.py

@@ -361,6 +361,8 @@ def _get_legend(node_types: Set[str]):
             concentrate="true",
         ),
     )
+    # we need to update the graph_attr dict instead of overwriting it
+    # so that means we need to handle nested dicts, e.g. graph_attr.
     for g_key, g_value in graphviz_kwargs.items():
         if isinstance(g_value, dict):
             digraph_attr[g_key].update(**g_value)

hamilton/io/utils.py

@@ -11,6 +11,10 @@
 
 def get_file_metadata(path: str) -> Dict[str, Any]:
     """Gives metadata from loading a file.
+
+    Note: we reserve the right to change this schema. So if you're using this come
+    chat so that we can make sure we don't break your code.
+
     This includes:
     - the file size
     - the file path
@@ -27,6 +31,10 @@ def get_file_metadata(path: str) -> Dict[str, Any]:
 
 def get_dataframe_metadata(df: pd.DataFrame) -> Dict[str, Any]:
     """Gives metadata from loading a dataframe.
+
+    Note: we reserve the right to change this schema. So if you're using this come
+    chat so that we can make sure we don't break your code.
+
     This includes:
     - the number of rows
     - the number of columns
@@ -43,6 +51,10 @@ def get_dataframe_metadata(df: pd.DataFrame) -> Dict[str, Any]:
 
 def get_file_and_dataframe_metadata(path: str, df: pd.DataFrame) -> Dict[str, Any]:
     """Gives metadata from loading a file and a dataframe.
+
+    Note: we reserve the right to change this schema. So if you're using this come
+    chat so that we can make sure we don't break your code.
+
     This includes:
         file_meta:
             - the file size
@@ -60,6 +72,10 @@ def get_file_and_dataframe_metadata(path: str, df: pd.DataFrame) -> Dict[str, An
 
 def get_sql_metadata(query_or_table: str, results: Union[int, pd.DataFrame]) -> Dict[str, Any]:
     """Gives metadata from reading a SQL table or writing to SQL db.
+
+    Note: we reserve the right to change this schema. So if you're using this come
+    chat so that we can make sure we don't break your code.
+
     This includes:
     - the number of rows read, added, or to add.
     - the sql query (e.g., "SELECT foo FROM bar")

tests/test_graph.py

@@ -5,9 +5,6 @@
 
 import pandas as pd
 import pytest
-
-import hamilton.graph_utils
-import hamilton.htypes
 import tests.resources.bad_functions
 import tests.resources.compatible_input_types
 import tests.resources.config_modifier
@@ -24,6 +21,9 @@
 import tests.resources.parametrized_nodes
 import tests.resources.test_default_args
 import tests.resources.typing_vs_not_typing
+
+import hamilton.graph_utils
+import hamilton.htypes
 from hamilton import ad_hoc_utils, base, graph, node
 from hamilton.execution import graph_functions
 from hamilton.node import NodeType
@@ -237,7 +237,10 @@ def test_add_dependency_input_nodes_compatible_types():
 
 
 def test_add_dependency_input_nodes_compatible_types_order_check():
-    """Tests that if functions request an input that we correctly accept compatible types independent of order."""
+    """Tests that if functions request an input that we correctly accept compatible types independent of order.
+
+    This just reorders test_add_dependency_input_nodes_compatible_types to ensure the outcome does not change.
+    """
     b_sig = inspect.signature(tests.resources.compatible_input_types.b)
     c_sig = inspect.signature(tests.resources.compatible_input_types.c)
     d_sig = inspect.signature(tests.resources.compatible_input_types.d)

tests/test_hamilton_driver.py

@@ -2,13 +2,13 @@
 
 import pandas as pd
 import pytest
-
 import tests.resources.cyclic_functions
 import tests.resources.dummy_functions
 import tests.resources.dynamic_parallelism.parallel_linear_basic
 import tests.resources.tagging
 import tests.resources.test_default_args
 import tests.resources.very_simple_dag
+
 from hamilton import base, node
 from hamilton.driver import (
     Builder,