mostlyai-engine 2.3.0__tar.gz → 2.3.1__tar.gz

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyai-engine
-Version: 2.3.0
+Version: 2.3.1
 Summary: Synthetic Data Engine
 Project-URL: homepage, https://github.com/mostly-ai/mostlyai-engine
 Project-URL: repository, https://github.com/mostly-ai/mostlyai-engine
@@ -251,6 +251,9 @@ Compute log likelihood of observations:
 ```python
 # compute log probability for each observation
 log_probs = argn.log_prob(data_test)
+
+# list top 10 outliers
+data_test.iloc[log_probs.argsort()[:10]]
 ```
 
 ## TabularARGN for Sequential Data

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/README.md

@@ -200,6 +200,9 @@ Compute log likelihood of observations:
 ```python
 # compute log probability for each observation
 log_probs = argn.log_prob(data_test)
+
+# list top 10 outliers
+data_test.iloc[log_probs.argsort()[:10]]
 ```
 
 ## TabularARGN for Sequential Data

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/mostlyai/engine/__init__.py

@@ -34,7 +34,7 @@ __all__ = [
     "TabularARGN",
     "LanguageModel",
 ]
-__version__ = "2.3.0"
+__version__ = "2.3.1"
 
 # suppress specific warning related to os.fork() in multi-threaded processes
 warnings.filterwarnings("ignore", category=DeprecationWarning, message=".*multi-threaded.*fork.*")

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/mostlyai/engine/_tabular/interface.py

@@ -737,7 +737,7 @@ class TabularARGN(BaseEstimator):
         X: pd.DataFrame,
         ctx_data: pd.DataFrame | None = None,
         **kwargs,
-    ) -> pd.DataFrame:
+    ) -> np.ndarray:
         """
         Compute log probability of observations.
 
@@ -754,8 +754,8 @@ class TabularARGN(BaseEstimator):
             **kwargs: Additional generation parameters (device, etc.).
 
         Returns:
-            pd.DataFrame of shape (n_samples, 1) with log probability per row.
-            Column name is "log_prob". Values are <= 0 (log probabilities).
+            np.ndarray of shape (n_samples,) with log probability per row.
+            Values are <= 0 (log probabilities).
             More negative values indicate less likely samples.
 
         Raises:

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/mostlyai/engine/_tabular/probability.py

@@ -535,7 +535,7 @@ def log_prob(
     data: pd.DataFrame,
     ctx_data: pd.DataFrame | None = None,
     device: torch.device | str | None = None,
-) -> pd.DataFrame:
+) -> np.ndarray:
     """
     Compute log probability of full observations.
 
@@ -556,8 +556,8 @@ def log_prob(
         device: Device to run inference on ('cuda' or 'cpu'). Defaults to 'cuda' if available.
 
     Returns:
-        pd.DataFrame of shape (n_samples, 1) with log probability per row.
-        Column name is "log_prob". Values are <= 0 (log probabilities).
+        np.ndarray of shape (n_samples,) with log probability per row.
+        Values are <= 0 (log probabilities).
     """
     _LOG.info("LOG_PROB started")
 
@@ -594,4 +594,4 @@ def log_prob(
     log_probs = -losses.cpu().numpy()
 
     _LOG.info(f"LOG_PROB finished: computed log probs for {n_samples} samples")
-    return pd.DataFrame({"log_prob": log_probs})
+    return log_probs

{mostlyai_engine-2.3.0 → mostlyai_engine-2.3.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyai-engine"
-version = "2.3.0"
+version = "2.3.1"
 description = "Synthetic Data Engine"
 authors = [{ name = "MOSTLY AI", email = "dev@mostly.ai" }]
 requires-python = ">=3.10"