arize-phoenix 0.0.24rc1__tar.gz → 0.0.24rc2__tar.gz

{arize_phoenix-0.0.24rc1 → arize_phoenix-0.0.24rc2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arize-phoenix
-Version: 0.0.24rc1
+Version: 0.0.24rc2
 Summary: ML Observability in your notebook
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues

{arize_phoenix-0.0.24rc1 → arize_phoenix-0.0.24rc2}/src/phoenix/__init__.py

@@ -3,7 +3,7 @@ from .datasets.fixtures import ExampleDatasets, load_example
 from .datasets.schema import EmbeddingColumnNames, Schema
 from .session.session import Session, active_session, close_app, launch_app
 
-__version__ = "0.0.24rc1"
+__version__ = "0.0.24rc2"
 
 # module level doc-string
 __doc__ = """

{arize_phoenix-0.0.24rc1 → arize_phoenix-0.0.24rc2}/src/phoenix/core/model_schema.py

@@ -599,10 +599,8 @@ class Events(ModelData):
     @cached_property
     def time_range(self) -> TimeRange:
         if self._self_model is None or self.empty:
-            # NOTE: as of Python 3.8.16, pandas 1.5.3:
-            # >>> isinstance(pd.NaT, datetime.datetime)
-            # True
-            return TimeRange(pd.NaT, pd.NaT)  # type: ignore
+            now = datetime.now(timezone.utc)
+            return TimeRange(now, now)
         model = cast(Model, self._self_model)
         min_max = _agg_min_max(model[TIMESTAMP](self))
         start_time = cast(datetime, min_max.min())

{arize_phoenix-0.0.24rc1 → arize_phoenix-0.0.24rc2}/src/phoenix/datasets/dataset.py

@@ -443,7 +443,11 @@ def _normalize_timestamps(
     if (timestamp_column_name := schema.timestamp_column_name) is None:
         timestamp_column_name = "timestamp"
         schema = replace(schema, timestamp_column_name=timestamp_column_name)
-        timestamp_column = Series([default_timestamp] * len(dataframe), index=dataframe.index)
+        timestamp_column = (
+            Series([default_timestamp] * len(dataframe), index=dataframe.index)
+            if len(dataframe)
+            else Series([default_timestamp]).iloc[:0].set_axis(dataframe.index, axis=0)
+        )
     elif is_numeric_dtype(timestamp_column_dtype := dataframe[timestamp_column_name].dtype):
         timestamp_column = to_datetime(dataframe[timestamp_column_name], unit="s", utc=True)
     elif is_datetime64tz_dtype(timestamp_column_dtype):

{arize_phoenix-0.0.24rc1 → arize_phoenix-0.0.24rc2}/src/phoenix/pointcloud/projectors.py

@@ -11,6 +11,7 @@ with warnings.catch_warnings():
 
     warnings.simplefilter("ignore", category=NumbaWarning)
     from umap import UMAP
+
 Matrix: TypeAlias = npt.NDArray[np.float64]
 
 
@@ -24,4 +25,11 @@ class Umap:
     min_dist: float = 0.1
 
     def project(self, mat: Matrix, n_components: int) -> Matrix:
-        return _center(UMAP(**asdict(self), n_components=n_components).fit_transform(mat))
+        config = asdict(self)
+        config["n_components"] = n_components
+        if len(mat) <= n_components:
+            # init='spectral', the default, cannot be used when n_components
+            # is greater or equal to the number of samples.
+            # see https://github.com/lmcinnes/umap/issues/201#issuecomment-462097103
+            config["init"] = "random"
+        return _center(UMAP(**config).fit_transform(mat))