arize 8.0.0a23__py3-none-any.whl → 8.0.0b0__py3-none-any.whl

arize/{models → ml}/casting.py

@@ -9,7 +9,13 @@ from typing import TYPE_CHECKING
 import numpy as np
 
 from arize.logging import log_a_list
-from arize.types import ArizeTypes, Schema, TypedColumns, TypedValue, is_list_of
+from arize.ml.types import (
+    ArizeTypes,
+    Schema,
+    TypedColumns,
+    TypedValue,
+)
+from arize.utils.types import is_list_of
 
 if TYPE_CHECKING:
     import pandas as pd
@@ -125,29 +131,20 @@ def cast_typed_columns(
     This optional feature provides a simple way for users to prevent type drift within
     a column across many SDK uploads.
 
-    Arguments:
-    ---------
-        dataframe: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        schema: Schema
-            The schema, which may include feature and tag column names
+    Args:
+        dataframe (pd.DataFrame): A deepcopy of the user's dataframe.
+        schema (Schema): The schema, which may include feature and tag column names
             in a TypedColumns object or a List[string].
 
     Returns:
-    -------
-        dataframe: pd.DataFrame
-            The dataframe, with columns cast to the specified types.
-        schema: Schema
-            A new Schema object, with feature and tag column names converted to the List[string] format
-            expected in downstream validation.
+        tuple[pd.DataFrame, Schema]: A tuple containing:
+            - dataframe: The dataframe, with columns cast to the specified types.
+            - schema: A new Schema object, with feature and tag column names converted
+                to the List[string] format expected in downstream validation.
 
     Raises:
-    ------
-        ColumnCastingError
-            If casting fails.
-        InvalidTypedColumnsError
-            If the TypedColumns object is invalid.
-
+        ColumnCastingError: If casting fails.
+        InvalidTypedColumnsError: If the TypedColumns object is invalid.
     """
     typed_column_fields = schema.typed_column_fields()
     feature_field = "feature_column_names"
@@ -204,21 +201,14 @@ def _cast_value(
 ) -> str | int | float | list[str] | None:
     """Casts a TypedValue to its provided type, preserving all null values as None or float('nan').
 
-    Arguments:
-    ---------
-    typed_value: TypedValue
-        The TypedValue to cast.
+    Args:
+        typed_value (TypedValue): The TypedValue to cast.
 
     Returns:
-    -------
-    Union[str, int, float, List[str], None]
-        The cast value.
+        str | int | float | list[str] | None: The cast value.
 
     Raises:
-    ------
-    CastingError
-        If the value cannot be cast to the provided type.
-
+        CastingError: If the value cannot be cast to the provided type.
     """
     if typed_value.value is None:
         return None
@@ -274,18 +264,13 @@ def _validate_typed_columns(
 ) -> None:
     """Validate a TypedColumns object.
 
-    Arguments:
-    ---------
-        field_name: str
-            The name of the Schema field that the TypedColumns object is associated with.
-        typed_columns: TypedColumns
-            The TypedColumns object to validate.
+    Args:
+        field_name (str): The name of the Schema field that the TypedColumns object
+            is associated with.
+        typed_columns (TypedColumns): The TypedColumns object to validate.
 
     Raises:
-    ------
-        InvalidTypedColumnsError
-            If the TypedColumns object is invalid.
-
+        InvalidTypedColumnsError: If the TypedColumns object is invalid.
     """
     if typed_columns.is_empty():
         raise InvalidTypedColumnsError(field_name=field_name, reason="is empty")
@@ -304,24 +289,16 @@ def _cast_columns(
 
     (feature_column_names or tag_column_names)
 
-    Arguments:
-    ---------
-        dataframe: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        columns: TypedColumns
-            The TypedColumns object, which specifies the columns to cast
-            (and/or to not cast) and their target types.
+    Args:
+        dataframe (pd.DataFrame): A deepcopy of the user's dataframe.
+        columns (TypedColumns): The TypedColumns object, which specifies the columns
+            to cast (and/or to not cast) and their target types.
 
     Returns:
-    -------
-        dataframe: pd.DataFrame
-            The dataframe with columns cast to the specified types.
+        pd.DataFrame: The dataframe with columns cast to the specified types.
 
     Raises:
-    ------
-        ColumnCastingError
-            If casting fails.
-
+        ColumnCastingError: If casting fails.
     """
     if columns.to_str:
         try:
@@ -372,25 +349,17 @@ def _cast_df(
 ) -> pd.DataFrame:
     """Cast columns in a dataframe to the specified type.
 
-    Arguments:
-    ---------
-        df: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        cols: List[str]
-            The list of column names to cast.
-        target_type_str: str
-            The target type to cast to.
+    Args:
+        df (pd.DataFrame): A deepcopy of the user's dataframe.
+        cols (list[str]): The list of column names to cast.
+        target_type_str (str): The target type to cast to.
 
     Returns:
-    -------
-        df: pd.DataFrame
-            The dataframe with columns cast to the specified types.
+        pd.DataFrame: The dataframe with columns cast to the specified types.
 
     Raises:
-    ------
-        Exception
-            If casting fails. Common exceptions raised by astype() are TypeError and ValueError.
-
+        Exception: If casting fails. Common exceptions raised by astype() are
+            TypeError and ValueError.
     """
     nan_mapping = {"nan": np.nan, "NaN": np.nan}
     df = df.replace(nan_mapping)
@@ -404,18 +373,13 @@ def _convert_schema_field_types(
 ) -> Schema:
     """Convert schema field types from TypedColumns to List[string] format.
 
-    Arguments:
-    ---------
-        schema: Schema
-            The schema, which may include feature and tag column names
+    Args:
+        schema (Schema): The schema, which may include feature and tag column names
             in a TypedColumns object or a List[string].
 
     Returns:
-    -------
-        schema: Schema
-            A Schema, with feature and tag column names
-            converted to the List[string] format expected in downstream validation.
-
+        Schema: A Schema, with feature and tag column names converted to the
+            List[string] format expected in downstream validation.
     """
     feature_column_names_list = (
         schema.feature_column_names

arize/{models → ml}/client.py

@@ -33,13 +33,13 @@ from arize.exceptions.parameters import (
 )
 from arize.exceptions.spaces import MissingSpaceIDError
 from arize.logging import get_truncation_warning_message
-from arize.models.bounded_executor import BoundedExecutor
-from arize.models.casting import cast_dictionary, cast_typed_columns
-from arize.models.stream_validation import (
+from arize.ml.bounded_executor import BoundedExecutor
+from arize.ml.casting import cast_dictionary, cast_typed_columns
+from arize.ml.stream_validation import (
     validate_and_convert_prediction_id,
     validate_label,
 )
-from arize.types import (
+from arize.ml.types import (
     CATEGORICAL_MODEL_TYPES,
     NUMERIC_MODEL_TYPES,
     ActualLabelTypes,
@@ -57,8 +57,8 @@ from arize.types import (
     SimilaritySearchParams,
     TypedValue,
     convert_element,
-    is_list_of,
 )
+from arize.utils.types import is_list_of
 
 if TYPE_CHECKING:
     import concurrent.futures as cf
@@ -95,14 +95,18 @@ _MIMIC_EXTRA = "mimic-explainer"
 
 
 class MLModelsClient:
-    """Client for logging ML model predictions and actuals to Arize."""
+    """Client for logging ML model predictions and actuals to Arize.
 
-    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
-        """Initialize the ML models client with SDK configuration.
+    This class is primarily intended for internal use within the SDK. Users are
+    highly encouraged to access resource-specific functionality via
+    :class:`arize.ArizeClient`.
+    """
 
-        Args:
-            sdk_config: SDK configuration containing API endpoints and credentials.
+    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
         """
+        Args:
+            sdk_config: Resolved SDK configuration.
+        """  # noqa: D205, D212
         self._sdk_config = sdk_config
 
         # internal cache for the futures session
@@ -202,7 +206,7 @@ class MLModelsClient:
         """
         require(_STREAM_EXTRA, _STREAM_DEPS)
         from arize._generated.protocol.rec import public_pb2 as pb2
-        from arize.models.proto import (
+        from arize.ml.proto import (
             get_pb_dictionary,
             get_pb_label,
             get_pb_timestamp,
@@ -374,9 +378,7 @@ class MLModelsClient:
             if embedding_features or prompt or response:
                 # NOTE: Deep copy is necessary to avoid side effects on the original input dictionary
                 combined_embedding_features = (
-                    dict(embedding_features.items())
-                    if embedding_features
-                    else {}
+                    embedding_features.copy() if embedding_features else {}
                 )
                 # Map prompt as embedding features for generative models
                 if prompt is not None:
@@ -523,7 +525,7 @@ class MLModelsClient:
             indexes=None,
         )
 
-    def log_batch(
+    def log(
         self,
         *,
         space_id: str,
@@ -597,7 +599,7 @@ class MLModelsClient:
         import pandas.api.types as ptypes
         import pyarrow as pa
 
-        from arize.models.batch_validation.validator import Validator
+        from arize.ml.batch_validation.validator import Validator
         from arize.utils.arrow import post_arrow_table
         from arize.utils.dataframe import remove_extraneous_columns
 
@@ -686,7 +688,7 @@ class MLModelsClient:
 
         if surrogate_explainability:
             require(_MIMIC_EXTRA, _MIMIC_DEPS)
-            from arize.models.surrogate_explainer.mimic import Mimic
+            from arize.ml.surrogate_explainer.mimic import Mimic
 
             logger.debug("Running surrogate_explainability.")
             if schema.shap_values_column_names:

arize/{models → ml}/proto.py

@@ -8,7 +8,7 @@ from google.protobuf.wrappers_pb2 import DoubleValue, StringValue
 
 from arize._generated.protocol.rec import public_pb2 as pb2
 from arize.exceptions.parameters import InvalidValueType
-from arize.types import (
+from arize.ml.types import (
     CATEGORICAL_MODEL_TYPES,
     NUMERIC_MODEL_TYPES,
     Embedding,
@@ -22,8 +22,8 @@ from arize.types import (
     RankingPredictionLabel,
     SemanticSegmentationLabel,
     convert_element,
-    is_list_of,
 )
+from arize.utils.types import is_list_of
 
 
 def get_pb_dictionary(d: dict[object, object] | None) -> dict[str, object]:

arize/{models → ml}/stream_validation.py

@@ -6,7 +6,7 @@ from arize.constants.ml import MAX_PREDICTION_ID_LEN, MIN_PREDICTION_ID_LEN
 from arize.exceptions.parameters import (
     InvalidValueType,
 )
-from arize.types import (
+from arize.ml.types import (
     CATEGORICAL_MODEL_TYPES,
     NUMERIC_MODEL_TYPES,
     ActualLabelTypes,

arize/{models → ml}/surrogate_explainer/mimic.py

@@ -15,12 +15,16 @@ from interpret_community.mimic.mimic_explainer import (
 )
 from sklearn.preprocessing import LabelEncoder
 
-from arize.types import CATEGORICAL_MODEL_TYPES, NUMERIC_MODEL_TYPES, ModelTypes
+from arize.ml.types import (
+    CATEGORICAL_MODEL_TYPES,
+    NUMERIC_MODEL_TYPES,
+    ModelTypes,
+)
 
 if TYPE_CHECKING:
     from collections.abc import Callable
 
-    from arize.types import Schema
+    from arize.ml.types import Schema
 
 
 class Mimic: