fix: timestamp dataset name if there's a collision (#77)

* timestampe dataset name if there's a collision

Author: nabinchha

src/data_designer/engine/dataset_builders/artifact_storage.py

@@ -1,6 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+from datetime import datetime
+from functools import cached_property
 import json
 import logging
 from pathlib import Path
@@ -36,9 +38,21 @@ class ArtifactStorage(BaseModel):
     def artifact_path_exists(self) -> bool:
         return self.artifact_path.exists()
 
+    @cached_property
+    def resolved_dataset_name(self) -> str:
+        dataset_path = self.artifact_path / self.dataset_name
+        if dataset_path.exists() and len(list(dataset_path.iterdir())) > 0:
+            new_dataset_name = f"{self.dataset_name}_{datetime.now().strftime('%m-%d-%Y_%H%M%S')}"
+            logger.info(
+                f"📂 Dataset path {str(dataset_path)!r} already exists. Dataset from this session"
+                f"\n\t\t     will be saved to {str(self.artifact_path / new_dataset_name)!r} instead."
+            )
+            return new_dataset_name
+        return self.dataset_name
+
     @property
     def base_dataset_path(self) -> Path:
-        return self.artifact_path / self.dataset_name
+        return self.artifact_path / self.resolved_dataset_name
 
     @property
     def dropped_columns_dataset_path(self) -> Path:

src/data_designer/interface/data_designer.py

@@ -173,7 +173,11 @@ def create(
                 configuration (columns, constraints, seed data, etc.).
             num_records: Number of records to generate.
             dataset_name: Name of the dataset. This name will be used as the dataset
-                folder name in the artifact path directory.
+                folder name in the artifact path directory. If a non-empty directory with the
+                same name already exists, dataset will be saved to a new directory with
+                a datetime stamp. For example, if the dataset name is "awesome_dataset" and a directory
+                with the same name already exists, the dataset will be saved to a new directory
+                with the name "awesome_dataset_2025-01-01_12-00-00".
 
         Returns:
             DatasetCreationResults object with methods for loading the generated dataset,

tests/engine/dataset_builders/test_artifact_storage.py

@@ -1,7 +1,9 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+from datetime import datetime
 import json
+from unittest.mock import patch
 
 import pandas as pd
 from pyarrow import ArrowNotImplementedError
@@ -213,3 +215,22 @@ def test_artifact_storage_batch_numbering(stub_artifact_storage, batch_number):
     path = stub_artifact_storage.create_batch_file_path(batch_number, BatchStage.FINAL_RESULT)
     expected_name = f"batch_{batch_number:05d}.parquet"
     assert path.name == expected_name
+
+
+@patch("data_designer.engine.dataset_builders.artifact_storage.datetime")
+def test_artifact_storage_resolved_dataset_name(mock_datetime, tmp_path):
+    mock_datetime.now.return_value = datetime(2025, 1, 1, 12, 3, 4)
+
+    # dataset path does not exist yet
+    assert ArtifactStorage(artifact_path=tmp_path).resolved_dataset_name == "dataset"
+
+    # dataset path exists but is empty
+    af_storage = ArtifactStorage(artifact_path=tmp_path)
+    (af_storage.artifact_path / af_storage.dataset_name).mkdir()
+    assert af_storage.resolved_dataset_name == "dataset"
+
+    # dataset path exists and is not empty
+    af_storage = ArtifactStorage(artifact_path=tmp_path)
+    (af_storage.artifact_path / af_storage.dataset_name / "stub_file.txt").touch()
+    print(af_storage.resolved_dataset_name)
+    assert af_storage.resolved_dataset_name == "dataset_01-01-2025_120304"