feature: add joinsource to DataConfig

Author: keerthanvasist

src/sagemaker/clarify.py

@@ -34,6 +34,7 @@ def __init__(
         label=None,
         headers=None,
         features=None,
+        joinsource=None,
         dataset_type="text/csv",
         s3_data_distribution_type="FullyReplicated",
         s3_compression_type="None",
@@ -48,6 +49,11 @@ def __init__(
             headers (list[str]): A list of column names in the input dataset.
             features (str): JSONPath for locating the feature columns for bias metrics if the
                 dataset format is JSONLines.
+            joinsource (str): the name or index of the column in the dataset that acts an
+                identifier column (for instance, while performing a join). This column is only
+                used as an identifier, and not used for any other computations. This is an
+                optional field in all cases except when the dataset contains more than one file,
+                and `save_local_shap_values` is set to true in SHAPConfig.
             dataset_type (str): Format of the dataset. Valid values are "text/csv" for CSV,
                 "application/jsonlines" for JSONLines, and "application/x-parquet" for Parquet.
             s3_data_distribution_type (str): Valid options are "FullyReplicated" or
@@ -72,6 +78,7 @@ def __init__(
         _set(features, "features", self.analysis_config)
         _set(headers, "headers", self.analysis_config)
         _set(label, "label", self.analysis_config)
+        _set(joinsource, "joinsource_name_or_index", self.analysis_config)
 
     def get_config(self):
         """Returns part of an analysis config dictionary."""

tests/unit/test_clarify.py

@@ -326,13 +326,9 @@ def data_config():
         s3_data_input_path="s3://input/train.csv",
         s3_output_path="s3://output/analysis_test_result",
         label="Label",
-        headers=[
-            "Label",
-            "F1",
-            "F2",
-            "F3",
-        ],
+        headers=["Label", "F1", "F2", "F3", "F4"],
         dataset_type="text/csv",
+        joinsource="F4",
     )
 
 
@@ -397,7 +393,9 @@ def test_pre_training_bias(
                 "F1",
                 "F2",
                 "F3",
+                "F4",
             ],
+            "joinsource_name_or_index": "F4",
             "label": "Label",
             "label_values_or_threshold": [1],
             "facet": [{"name_or_index": "F1"}],
@@ -458,9 +456,11 @@ def test_post_training_bias(
                 "F1",
                 "F2",
                 "F3",
+                "F4",
             ],
             "label": "Label",
             "label_values_or_threshold": [1],
+            "joinsource_name_or_index": "F4",
             "facet": [{"name_or_index": "F1"}],
             "group_variable": "F2",
             "methods": {"post_training_bias": {"methods": "all"}},
@@ -526,8 +526,10 @@ def _run_test_shap(
                 "F1",
                 "F2",
                 "F3",
+                "F4",
             ],
             "label": "Label",
+            "joinsource_name_or_index": "F4",
             "methods": {
                 "shap": {
                     "baseline": [