mloda 0.4.0__tar.gz → 0.4.1__tar.gz

{mloda-0.4.0/mloda.egg-info → mloda-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mloda
-Version: 0.4.0
+Version: 0.4.1
 Summary: Make data, feature and context engineering shareable
 Author-email: Tom Kaltofen <info@mloda.ai>
 License: Apache-2.0
@@ -76,7 +76,6 @@ class SampleData(FeatureGroup):
 # Step 2: Load mloda plugins and run pipeline
 from mloda.user import PluginLoader
 import mloda
-from mloda_plugins.compute_framework.base_implementations.pandas.dataframe import PandasDataFrame
 
 PluginLoader.all()
 
@@ -86,7 +85,7 @@ result = mloda.run_all(
         "age",                            # Original column
         "income__standard_scaled"         # Transform: scale income to mean=0, std=1
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Get your processed data
@@ -188,7 +187,7 @@ For truly custom configurations, you can use `Feature` objects:
 #
 # result = mloda.run_all(
 #     features=features,
-#     compute_frameworks={PandasDataFrame}
+#     compute_frameworks=["PandasDataFrame"]
 # )
 ```
 
@@ -233,7 +232,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "income__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     data_access_collection=data_access
 # )
 ```
@@ -251,7 +250,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "age__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     api_input_data_collection=api_input_data_collection,
 #     api_data=api_data
 # )
@@ -270,7 +269,7 @@ mloda supports multiple compute frameworks (pandas, polars, pyarrow, etc.). Most
 # Default: Everything processes with pandas
 result = mloda.run_all(
     features=["customer_id", "income__standard_scaled"],
-    compute_frameworks={PandasDataFrame}  # Use pandas for all features
+    compute_frameworks=["PandasDataFrame"]  # Use pandas for all features
 )
 
 data = result[0]  # Returns pandas DataFrame
@@ -283,8 +282,6 @@ print(type(data))  # <class 'pandas.core.frame.DataFrame'>
 - **PyArrow**: Memory-efficient, great for columnar data
 - **Spark**: Distributed processing for big data
 
-> **For most use cases**: Start with `compute_frameworks={PandasDataFrame}` and switch to others only if you need specific performance characteristics.
-
 ### 6. Putting It All Together - Complete ML Pipeline
 
 **Real-World Example: Customer Churn Prediction**
@@ -338,7 +335,7 @@ result = mloda.run_all(
         "customer_segment__label_encoded",
         "churned"
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Prepare for ML

{mloda-0.4.0 → mloda-0.4.1}/README.md

@@ -57,7 +57,6 @@ class SampleData(FeatureGroup):
 # Step 2: Load mloda plugins and run pipeline
 from mloda.user import PluginLoader
 import mloda
-from mloda_plugins.compute_framework.base_implementations.pandas.dataframe import PandasDataFrame
 
 PluginLoader.all()
 
@@ -67,7 +66,7 @@ result = mloda.run_all(
         "age",                            # Original column
         "income__standard_scaled"         # Transform: scale income to mean=0, std=1
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Get your processed data
@@ -169,7 +168,7 @@ For truly custom configurations, you can use `Feature` objects:
 #
 # result = mloda.run_all(
 #     features=features,
-#     compute_frameworks={PandasDataFrame}
+#     compute_frameworks=["PandasDataFrame"]
 # )
 ```
 
@@ -214,7 +213,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "income__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     data_access_collection=data_access
 # )
 ```
@@ -232,7 +231,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "age__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     api_input_data_collection=api_input_data_collection,
 #     api_data=api_data
 # )
@@ -251,7 +250,7 @@ mloda supports multiple compute frameworks (pandas, polars, pyarrow, etc.). Most
 # Default: Everything processes with pandas
 result = mloda.run_all(
     features=["customer_id", "income__standard_scaled"],
-    compute_frameworks={PandasDataFrame}  # Use pandas for all features
+    compute_frameworks=["PandasDataFrame"]  # Use pandas for all features
 )
 
 data = result[0]  # Returns pandas DataFrame
@@ -264,8 +263,6 @@ print(type(data))  # <class 'pandas.core.frame.DataFrame'>
 - **PyArrow**: Memory-efficient, great for columnar data
 - **Spark**: Distributed processing for big data
 
-> **For most use cases**: Start with `compute_frameworks={PandasDataFrame}` and switch to others only if you need specific performance characteristics.
-
 ### 6. Putting It All Together - Complete ML Pipeline
 
 **Real-World Example: Customer Churn Prediction**
@@ -319,7 +316,7 @@ result = mloda.run_all(
         "customer_segment__label_encoded",
         "churned"
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Prepare for ML

{mloda-0.4.0 → mloda-0.4.1}/mloda/core/abstract_plugins/components/link.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from dataclasses import FrozenInstanceError
 from enum import Enum
 from uuid import uuid4
-from typing import Any, Dict, Optional, Set, Tuple, Type, Union
+from typing import Any, Dict, Optional, Tuple, Type, Union
 
 
 from mloda.core.abstract_plugins.components.index.index import Index

{mloda-0.4.0 → mloda-0.4.1}/mloda/core/abstract_plugins/compute_framework.py

@@ -1,7 +1,6 @@
 from abc import ABC
 from typing import Any, List, Optional, Set, Type, Union, final
 from uuid import UUID, uuid4
-from mloda.core.abstract_plugins.components.data_access_collection import DataAccessCollection
 from mloda.core.abstract_plugins.components.framework_transformer.cfw_transformer import (
     ComputeFrameworkTransformer,
 )

{mloda-0.4.0 → mloda-0.4.1}/mloda/core/core/engine.py

@@ -28,7 +28,6 @@ from mloda.core.abstract_plugins.components.feature_collection import Features
 from mloda.core.abstract_plugins.components.options import Options
 from mloda.core.abstract_plugins.components.link import Link
 from mloda.core.abstract_plugins.components.validators.link_validator import LinkValidator
-from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys
 
 
 class Engine:

{mloda-0.4.0 → mloda-0.4.1}/mloda/core/prepare/accessible_plugins.py

@@ -1,6 +1,5 @@
 from copy import deepcopy
 from typing import Optional, Set, Type
-from mloda.core.abstract_plugins.components.data_access_collection import DataAccessCollection
 from mloda.core.abstract_plugins.components.plugin_option.plugin_collector import PluginCollector
 from mloda.core.abstract_plugins.compute_framework import ComputeFramework
 

{mloda-0.4.0 → mloda-0.4.1/mloda.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mloda
-Version: 0.4.0
+Version: 0.4.1
 Summary: Make data, feature and context engineering shareable
 Author-email: Tom Kaltofen <info@mloda.ai>
 License: Apache-2.0
@@ -76,7 +76,6 @@ class SampleData(FeatureGroup):
 # Step 2: Load mloda plugins and run pipeline
 from mloda.user import PluginLoader
 import mloda
-from mloda_plugins.compute_framework.base_implementations.pandas.dataframe import PandasDataFrame
 
 PluginLoader.all()
 
@@ -86,7 +85,7 @@ result = mloda.run_all(
         "age",                            # Original column
         "income__standard_scaled"         # Transform: scale income to mean=0, std=1
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Get your processed data
@@ -188,7 +187,7 @@ For truly custom configurations, you can use `Feature` objects:
 #
 # result = mloda.run_all(
 #     features=features,
-#     compute_frameworks={PandasDataFrame}
+#     compute_frameworks=["PandasDataFrame"]
 # )
 ```
 
@@ -233,7 +232,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "income__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     data_access_collection=data_access
 # )
 ```
@@ -251,7 +250,7 @@ mloda supports multiple data access patterns depending on your use case:
 #
 # result = mloda.run_all(
 #     features=["customer_id", "age__standard_scaled"],
-#     compute_frameworks={PandasDataFrame},
+#     compute_frameworks=["PandasDataFrame"],
 #     api_input_data_collection=api_input_data_collection,
 #     api_data=api_data
 # )
@@ -270,7 +269,7 @@ mloda supports multiple compute frameworks (pandas, polars, pyarrow, etc.). Most
 # Default: Everything processes with pandas
 result = mloda.run_all(
     features=["customer_id", "income__standard_scaled"],
-    compute_frameworks={PandasDataFrame}  # Use pandas for all features
+    compute_frameworks=["PandasDataFrame"]  # Use pandas for all features
 )
 
 data = result[0]  # Returns pandas DataFrame
@@ -283,8 +282,6 @@ print(type(data))  # <class 'pandas.core.frame.DataFrame'>
 - **PyArrow**: Memory-efficient, great for columnar data
 - **Spark**: Distributed processing for big data
 
-> **For most use cases**: Start with `compute_frameworks={PandasDataFrame}` and switch to others only if you need specific performance characteristics.
-
 ### 6. Putting It All Together - Complete ML Pipeline
 
 **Real-World Example: Customer Churn Prediction**
@@ -338,7 +335,7 @@ result = mloda.run_all(
         "customer_segment__label_encoded",
         "churned"
     ],
-    compute_frameworks={PandasDataFrame}
+    compute_frameworks=["PandasDataFrame"]
 )
 
 # Step 3: Prepare for ML

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/compute_framework/base_implementations/pyarrow/table.py

@@ -1,5 +1,4 @@
-from typing import Any, Optional, Set, Type
-from mloda.user import DataAccessCollection
+from typing import Any, Set, Type
 from mloda.provider import BaseMergeEngine
 from mloda.provider import BaseFilterEngine
 from mloda_plugins.compute_framework.base_implementations.pyarrow.pyarrow_merge_engine import PyArrowMergeEngine

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/compute_framework/base_implementations/spark/spark_merge_engine.py

@@ -1,7 +1,6 @@
 from typing import Any, Tuple
 
 from mloda.user import Index
-from mloda.user import JoinType
 from mloda.provider import BaseMergeEngine
 
 try:

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/aggregated_feature_group/base.py

@@ -5,13 +5,11 @@ Base implementation for aggregated feature groups.
 from __future__ import annotations
 
 from abc import abstractmethod
-from typing import Any, List, Optional, Set, Union
+from typing import Any, List, Optional, Set
 
 from mloda import FeatureGroup
 from mloda import Feature
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/clustering/base.py

@@ -13,9 +13,7 @@ from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,
 )
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys
 
 

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/data_quality/missing_value/base.py

@@ -4,9 +4,8 @@ Base implementation for missing value imputation feature groups.
 
 from __future__ import annotations
 
-import copy
 from abc import abstractmethod
-from typing import Any, List, Optional, Set, Union
+from typing import Any, List, Optional, Set
 
 from mloda import FeatureGroup
 from mloda import Feature
@@ -14,9 +13,7 @@ from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,
 )
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys
 
 

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/dimensionality_reduction/base.py

@@ -5,7 +5,7 @@ Base implementation for dimensionality reduction feature groups.
 from __future__ import annotations
 
 from abc import abstractmethod
-from typing import Any, Optional, Set, Union
+from typing import Any, Optional
 
 from mloda import FeatureGroup
 from mloda import Feature
@@ -13,7 +13,6 @@ from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,
 )
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
 from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/forecasting/base.py

@@ -5,12 +5,12 @@ Base implementation for forecasting feature groups.
 from __future__ import annotations
 
 from abc import abstractmethod
-from typing import Any, List, Optional, Set, Type, Union
+from typing import Any, List, Optional, Set, Type
 
 from mloda import FeatureGroup
 from mloda.provider import BaseArtifact
 from mloda import Feature
-from mloda.provider import CHAIN_SEPARATOR, FeatureChainParser, FeatureChainParserMixin, FeatureSet
+from mloda.provider import FeatureChainParser, FeatureChainParserMixin, FeatureSet
 from mloda.user import FeatureName
 from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/geo_distance/base.py

@@ -4,7 +4,7 @@ Base implementation for geo distance feature groups.
 
 from __future__ import annotations
 
-from typing import Any, Optional, Set, Union
+from typing import Any, Optional, Set
 
 from mloda import FeatureGroup
 from mloda import Feature

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/geo_distance/pandas.py

@@ -4,7 +4,6 @@ Pandas implementation for geo distance feature groups.
 
 from __future__ import annotations
 
-import math
 from typing import Any, Set, Type, Union
 
 import numpy as np

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/node_centrality/base.py

@@ -4,7 +4,7 @@ Base implementation for node centrality feature groups.
 
 from __future__ import annotations
 
-from typing import Any, Optional, Set, Type, Union
+from typing import Any, Optional
 
 from mloda import FeatureGroup
 from mloda import Feature
@@ -12,9 +12,7 @@ from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,
 )
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys
 
 

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/sklearn/encoding/base.py

@@ -5,7 +5,7 @@ Base implementation for scikit-learn encoding feature groups.
 from __future__ import annotations
 
 import datetime
-from typing import Any, Dict, Optional, Set, Type, Union
+from typing import Any, Dict, Optional, Set, Type
 
 from mloda import FeatureGroup
 from mloda import Feature

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/sklearn/pipeline/pandas.py

@@ -4,8 +4,7 @@ Pandas implementation for scikit-learn pipeline feature groups.
 
 from __future__ import annotations
 
-import numpy as np
-from typing import Any, List, Set, Type, Union
+from typing import Any, Set, Type, Union
 
 from mloda import ComputeFramework
 

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/sklearn/scaling/base.py

@@ -5,13 +5,11 @@ Base implementation for scikit-learn scaling feature groups.
 from __future__ import annotations
 
 import datetime
-from typing import Any, Dict, Optional, Set, Type, Union
+from typing import Any, Dict, Optional, Type
 
 from mloda import FeatureGroup
 from mloda import Feature
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/sklearn/sklearn_artifact.py

@@ -4,7 +4,6 @@ Artifact for storing fitted scikit-learn transformers and estimators.
 
 import json
 import base64
-import os
 import hashlib
 import tempfile
 from pathlib import Path

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/text_cleaning/base.py

@@ -4,7 +4,7 @@ Base implementation for text cleaning feature groups.
 
 from __future__ import annotations
 
-from typing import Any, Optional, Set, Union
+from typing import Any, Optional
 
 from mloda import FeatureGroup
 from mloda import Feature
@@ -12,9 +12,7 @@ from mloda.provider import FeatureChainParser
 from mloda.provider import (
     FeatureChainParserMixin,
 )
-from mloda.user import FeatureName
 from mloda.provider import FeatureSet
-from mloda import Options
 from mloda_plugins.feature_group.experimental.default_options_key import DefaultOptionKeys
 
 

{mloda-0.4.0 → mloda-0.4.1}/mloda_plugins/feature_group/experimental/time_window/base.py

@@ -5,7 +5,7 @@ Base implementation for time window feature groups.
 from __future__ import annotations
 
 from abc import abstractmethod
-from typing import Any, List, Optional, Set, Type, Union
+from typing import Any, List, Optional, Set
 
 from mloda import FeatureGroup
 from mloda import Feature

{mloda-0.4.0 → mloda-0.4.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mloda"
-version = "0.4.0"
+version = "0.4.1"
 description = "Make data, feature and context engineering shareable"
 readme = { file = "README.md", content-type = "text/markdown" }
 license = { text = "Apache-2.0" }