sdg-hub 0.4.1__py3-none-any.whl → 0.5.0__py3-none-any.whl

sdg_hub/core/blocks/deprecated_blocks/combine_columns.py

@@ -1,93 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""DEPRECATED: CombineColumnsBlock for backward compatibility.
-
-This module provides a deprecated wrapper for the old CombineColumnsBlock interface.
-Use transform.CombineColumnsBlock instead.
-"""
-
-# Standard
-from typing import Any
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..registry import BlockRegistry
-from ..transform.text_concat import TextConcatBlock
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "CombineColumnsBlock",
-    "deprecated",
-    "DEPRECATED: Use TextConcatBlock instead. Combines multiple columns into a single column using a separator",
-)
-class CombineColumnsBlock(BaseBlock):
-    r"""DEPRECATED: Combine multiple columns into a single column using a separator.
-
-    .. deprecated::
-        Use `sdg_hub.blocks.transform.CombineColumnsBlock` instead.
-        This class will be removed in a future version.
-
-    This block concatenates values from multiple columns into a single output column,
-    using a specified separator between values.
-
-    Parameters
-    ----------
-    block_name : str
-        Name of the block.
-    columns : List[str]
-        List of column names to combine.
-    output_col : str
-        Name of the column to store combined values.
-    separator : str, optional
-        String to use as separator between combined values, by default "\\n\\n".
-    **batch_kwargs : Dict[str, Any]
-        Additional keyword arguments for batch processing.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        columns: list[str],
-        output_col: str,
-        separator: str = "\n\n",
-        **batch_kwargs: dict[str, Any],
-    ) -> None:
-        warnings.warn(
-            "CombineColumnsBlock is deprecated. Use sdg_hub.blocks.transform.TextConcatBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Initialize with dummy values for BaseBlock validation
-        super().__init__(
-            block_name=block_name, input_cols=columns, output_cols=[output_col]
-        )
-
-        # Create the new implementation
-        self._impl = TextConcatBlock(
-            block_name=block_name,
-            input_cols=columns,
-            output_cols=[output_col],
-            separator=separator,
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate a dataset with combined columns.
-
-        Parameters
-        ----------
-        samples : Dataset
-            Input dataset to process.
-
-        Returns
-        -------
-        Dataset
-            Dataset with combined values stored in output column.
-        """
-        return self._impl.generate(samples)

sdg_hub/core/blocks/deprecated_blocks/duplicate_columns.py

@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Deprecated DuplicateColumns for backwards compatibility.
-
-This module provides a deprecated wrapper around DuplicateColumnsBlock
-to maintain backwards compatibility with existing code and configurations.
-"""
-
-# Standard
-from typing import Any
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..registry import BlockRegistry
-from ..transform import DuplicateColumnsBlock
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "DuplicateColumns",
-    "deprecated",
-    "DEPRECATED: Use DuplicateColumnsBlock instead. Duplicates existing columns with new names according to a mapping dictionary",
-)
-class DuplicateColumns(BaseBlock):
-    """DEPRECATED: Block for duplicating existing columns with new names.
-
-    This block is deprecated and maintained only for backwards compatibility.
-    Please use DuplicateColumnsBlock instead.
-
-    This block creates copies of existing columns with new names as specified
-    in the columns mapping dictionary.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        columns_map: dict[str, str],
-    ) -> None:
-        """Initialize the deprecated DuplicateColumns.
-
-        Parameters
-        ----------
-        block_name : str
-            Name of the block.
-        columns_map : Dict[str, str]
-            Dictionary mapping existing column names to new column names.
-            Keys are existing column names, values are new column names.
-        """
-        # Issue deprecation warning
-        warnings.warn(
-            "DuplicateColumns is deprecated and will be removed in a future version. "
-            "Please use DuplicateColumnsBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Map old signature to new signature
-        super().__init__(
-            block_name=block_name,
-            input_cols=columns_map,
-            output_cols=list(columns_map.values()),
-        )
-
-        # Create the new block instance with mapped parameters
-        self._new_block = DuplicateColumnsBlock(
-            block_name=block_name,
-            input_cols=columns_map,
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate dataset with duplicated columns using the new DuplicateColumnsBlock.
-
-        Parameters
-        ----------
-        samples : Dataset
-            The input dataset to duplicate columns from.
-
-        Returns
-        -------
-        Dataset
-            The dataset with additional duplicated columns.
-        """
-        return self._new_block.generate(samples, **kwargs)

sdg_hub/core/blocks/deprecated_blocks/filter_by_value.py

@@ -1,103 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Deprecated FilterByValueBlock for backwards compatibility.
-
-This module provides a deprecated wrapper around ColumnValueFilterBlock
-to maintain backwards compatibility with existing code and configurations.
-"""
-
-# Standard
-from typing import Any, Callable, Optional, Union
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..filtering import ColumnValueFilterBlock
-from ..registry import BlockRegistry
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "FilterByValueBlock",
-    "deprecated",
-    "DEPRECATED: Use ColumnValueFilterBlock instead. Filters datasets based on column values using various comparison operations",
-)
-class FilterByValueBlock(BaseBlock):
-    """DEPRECATED: A block for filtering datasets based on column values.
-
-    This block is deprecated and maintained only for backwards compatibility.
-    Please use ColumnValueFilterBlock instead.
-
-    This block allows filtering of datasets using various operations (e.g., equals, contains)
-    on specified column values, with optional data type conversion.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        filter_column: str,
-        filter_value: Union[Any, list[Any]],
-        operation: Callable[[Any, Any], bool],
-        convert_dtype: Optional[Union[type[float], type[int]]] = None,
-        **batch_kwargs: dict[str, Any],
-    ) -> None:
-        """Initialize the deprecated FilterByValueBlock.
-
-        Parameters
-        ----------
-        block_name : str
-            Name of the block.
-        filter_column : str
-            Column name to filter on.
-        filter_value : Union[Any, list[Any]]
-            The value(s) to filter by.
-        operation : Callable[[Any, Any], bool]
-            A binary operator from the operator module.
-        convert_dtype : Optional[Union[type[float], type[int]]], optional
-            Type to convert the filter column to.
-        **batch_kwargs : dict[str, Any]
-            Additional batch processing arguments.
-        """
-        # Issue deprecation warning
-        warnings.warn(
-            "FilterByValueBlock is deprecated and will be removed in a future version. "
-            "Please use ColumnValueFilterBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Map old signature to new signature
-        super().__init__(
-            block_name=block_name,
-            input_cols=[filter_column],
-            output_cols=[],
-        )
-
-        # Create the new block instance with mapped parameters
-        self._new_block = ColumnValueFilterBlock(
-            block_name=block_name,
-            input_cols=[filter_column],
-            output_cols=[],
-            filter_value=filter_value,
-            operation=operation,
-            convert_dtype=convert_dtype,
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate filtered dataset using the new ColumnValueFilterBlock.
-
-        Parameters
-        ----------
-        samples : Dataset
-            The input dataset to filter.
-
-        Returns
-        -------
-        Dataset
-            The filtered dataset.
-        """
-        return self._new_block.generate(samples, **kwargs)

sdg_hub/core/blocks/deprecated_blocks/flatten_columns.py

@@ -1,94 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Deprecated FlattenColumnsBlock for backwards compatibility.
-
-This module provides a deprecated wrapper around MeltColumnsBlock
-to maintain backwards compatibility with existing code and configurations.
-"""
-
-# Standard
-from typing import Any
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..registry import BlockRegistry
-from ..transform import MeltColumnsBlock
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "FlattenColumnsBlock",
-    "deprecated",
-    "DEPRECATED: Use MeltColumnsBlock instead. Transforms wide dataset format into long format by melting columns into rows",
-)
-class FlattenColumnsBlock(BaseBlock):
-    """DEPRECATED: Block for flattening multiple columns into a long format.
-
-    This block is deprecated and maintained only for backwards compatibility.
-    Please use MeltColumnsBlock instead.
-
-    This block transforms a wide dataset format into a long format by melting
-    specified columns into rows, creating new variable and value columns.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        var_cols: list[str],
-        value_name: str,
-        var_name: str,
-    ) -> None:
-        """Initialize the deprecated FlattenColumnsBlock.
-
-        Parameters
-        ----------
-        block_name : str
-            Name of the block.
-        var_cols : List[str]
-            List of column names to be melted into rows.
-        value_name : str
-            Name of the new column that will contain the values.
-        var_name : str
-            Name of the new column that will contain the variable names.
-        """
-        # Issue deprecation warning
-        warnings.warn(
-            "FlattenColumnsBlock is deprecated and will be removed in a future version. "
-            "Please use MeltColumnsBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Map old signature to new signature
-        super().__init__(
-            block_name=block_name,
-            input_cols=var_cols,
-            output_cols=[value_name, var_name],
-        )
-
-        # Create the new block instance with mapped parameters
-        self._new_block = MeltColumnsBlock(
-            block_name=block_name,
-            input_cols=var_cols,
-            output_cols=[value_name, var_name],
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate flattened dataset using the new MeltColumnsBlock.
-
-        Parameters
-        ----------
-        samples : Dataset
-            The input dataset to flatten.
-
-        Returns
-        -------
-        Dataset
-            The flattened dataset in long format.
-        """
-        return self._new_block.generate(samples, **kwargs)