fix: exclude df from seed source serialization (#193)

* exclude from serialization

* add unit test

* should -> must

Author: johnnygreco

src/data_designer/config/seed_source.py

@@ -53,7 +53,11 @@ class HuggingFaceSeedSource(SeedSource):
 
     path: str = Field(
         ...,
-        description="Path to the seed data in HuggingFace. Wildcards are allowed. Examples include 'datasets/my-username/my-dataset/data/000_00000.parquet', 'datasets/my-username/my-dataset/data/*.parquet', 'datasets/my-username/my-dataset/**/*.parquet'",
+        description=(
+            "Path to the seed data in HuggingFace. Wildcards are allowed. Examples include "
+            "'datasets/my-username/my-dataset/data/000_00000.parquet', 'datasets/my-username/my-dataset/data/*.parquet', "
+            "and 'datasets/my-username/my-dataset/**/*.parquet'"
+        ),
     )
     token: str | None = None
     endpoint: str = "https://huggingface.co"
@@ -64,7 +68,14 @@ class DataFrameSeedSource(SeedSource):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
-    df: pd.DataFrame
+    df: pd.DataFrame = Field(
+        ...,
+        exclude=True,
+        description=(
+            "DataFrame to use directly as the seed dataset. NOTE: if you need to write a Data Designer config, "
+            "you must use `LocalFileSeedSource` instead, since DataFrame objects are not serializable."
+        ),
+    )
 
 
 SeedSourceT = Annotated[

tests/config/test_seed_source.py

@@ -7,7 +7,7 @@
 import pytest
 
 from data_designer.config.errors import InvalidFilePathError
-from data_designer.config.seed_source import LocalFileSeedSource
+from data_designer.config.seed_source import DataFrameSeedSource, LocalFileSeedSource
 
 
 def create_partitions_in_path(temp_dir: Path, extension: str, num_files: int = 2) -> Path:
@@ -59,3 +59,14 @@ def test_local_source_from_dataframe(tmp_path: Path):
 
     assert source.path == filepath
     pd.testing.assert_frame_equal(df, pd.read_parquet(filepath))
+
+
+def test_dataframe_seed_source_serialization():
+    """Test that DataFrameSeedSource excludes the DataFrame field during serialization."""
+    df = pd.DataFrame({"col1": [1, 2, 3], "col2": ["a", "b", "c"]})
+    source = DataFrameSeedSource(df=df)
+
+    # Test model_dump excludes the df field
+    serialized = source.model_dump(mode="json")
+    assert "df" not in serialized
+    assert serialized == {"seed_type": "df"}