mostlyai-engine 1.5.3__tar.gz → 1.5.4__tar.gz

{mostlyai_engine-1.5.3 → mostlyai_engine-1.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-engine
-Version: 1.5.3
+Version: 1.5.4
 Summary: Synthetic Data Engine
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-engine
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-engine

{mostlyai_engine-1.5.3 → mostlyai_engine-1.5.4}/mostlyai/engine/__init__.py

@@ -22,7 +22,7 @@ from mostlyai.engine.splitting import split
 from mostlyai.engine.training import train
 
 __all__ = ["split", "analyze", "encode", "train", "generate", "init_logging", "set_random_state"]
-__version__ = "1.5.3"
+__version__ = "1.5.4"
 
 # suppress specific warning related to os.fork() in multi-threaded processes
 warnings.filterwarnings("ignore", category=DeprecationWarning, message=".*multi-threaded.*fork.*")

{mostlyai_engine-1.5.3 → mostlyai_engine-1.5.4}/mostlyai/engine/_common.py

@@ -864,6 +864,7 @@ def dp_non_rare(value_counts: dict[str, int], epsilon: float, threshold: int = 5
     noisy_counts = np.clip(np.array(list(value_counts.values())) + noise, 0, None).astype(int)
     for i, cat in enumerate(value_counts):
         value_counts[cat] = noisy_counts[i]
+    # NOTE: total_counts can be 0 in the edge case when the column only has null values
     total_counts = sum(value_counts.values())
 
     # 2. Collect all categories whose noisy count >= threshold
@@ -871,7 +872,7 @@ def dp_non_rare(value_counts: dict[str, int], epsilon: float, threshold: int = 5
 
     # 3. Compute the non-rare ratio
     noisy_total_counts = sum(selected.values())
-    non_rare_ratio = noisy_total_counts / total_counts
+    non_rare_ratio = noisy_total_counts / total_counts if total_counts > 0 else 0
 
     return list(selected.keys()), non_rare_ratio
 

{mostlyai_engine-1.5.3 → mostlyai_engine-1.5.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyai-engine"
-version = "1.5.3"
+version = "1.5.4"
 description = "Synthetic Data Engine"
 authors = [{ name = "MOSTLY AI", email = "dev@mostly.ai" }]
 requires-python = ">=3.10"