maxframe 2.2.0__cp38-cp38-macosx_10_9_universal2.whl → 2.3.0rc1__cp38-cp38-macosx_10_9_universal2.whl

maxframe/dataframe/datasource/read_parquet.py

@@ -32,6 +32,7 @@ except ImportError:
 
 from ... import opcodes
 from ...config import options
+from ...lib.dtypes_extension import ArrowDtype
 from ...lib.filesystem import FileSystem, get_fs, glob, open_file
 from ...serialization.serializables import (
     AnyField,
@@ -43,10 +44,13 @@ from ...serialization.serializables import (
     StringField,
 )
 from ...utils import lazy_import
-from ..arrays import ArrowStringDtype
 from ..operators import OutputType
 from ..utils import parse_index, to_arrow_dtypes
-from .core import ColumnPruneSupportedDataSourceMixin, IncrementalIndexDatasource
+from .core import (
+    ColumnPruneSupportedDataSourceMixin,
+    DtypeBackendCompatibleMixin,
+    IncrementalIndexDatasource,
+)
 
 PARQUET_MEMORY_SCALE = 15
 STRING_FIELD_OVERHEAD = 50
@@ -89,13 +93,11 @@ class ParquetEngine:
     def read_dtypes(self, f, **kwargs):
         raise NotImplementedError
 
-    def read_to_pandas(
-        self, f, columns=None, nrows=None, use_arrow_dtype=None, **kwargs
-    ):
+    def read_to_pandas(self, f, columns=None, nrows=None, dtype_backend=None, **kwargs):
         raise NotImplementedError
 
     def read_group_to_pandas(
-        self, f, group_index, columns=None, nrows=None, use_arrow_dtype=None, **kwargs
+        self, f, group_index, columns=None, nrows=None, dtype_backend=None, **kwargs
     ):
         raise NotImplementedError
 
@@ -106,11 +108,11 @@ class ParquetEngine:
         partition_keys: Dict,
         columns=None,
         nrows=None,
-        use_arrow_dtype=None,
+        dtype_backend=None,
         **kwargs,
     ):
         raw_df = self.read_to_pandas(
-            f, columns=columns, nrows=nrows, use_arrow_dtype=use_arrow_dtype, **kwargs
+            f, columns=columns, nrows=nrows, dtype_backend=dtype_backend, **kwargs
         )
         for col, value in partition_keys.items():
             dictionary = partitions[col]
@@ -169,28 +171,26 @@ class ArrowEngine(ParquetEngine):
         return file.schema_arrow.empty_table().to_pandas().dtypes
 
     @classmethod
-    def _table_to_pandas(cls, t, nrows=None, use_arrow_dtype=None):
+    def _table_to_pandas(cls, t, nrows=None, dtype_backend=None):
         if nrows is not None:
             t = t.slice(0, nrows)
-        if use_arrow_dtype:
-            df = t.to_pandas(types_mapper={pa.string(): ArrowStringDtype()}.get)
+        if dtype_backend == "pyarrow":
+            df = t.to_pandas(types_mapper={pa.string(): ArrowDtype(pa.string())}.get)
         else:
             df = t.to_pandas()
         return df
 
-    def read_to_pandas(
-        self, f, columns=None, nrows=None, use_arrow_dtype=None, **kwargs
-    ):
+    def read_to_pandas(self, f, columns=None, nrows=None, dtype_backend=None, **kwargs):
         file = pq.ParquetFile(f)
         t = file.read(columns=columns, **kwargs)
-        return self._table_to_pandas(t, nrows=nrows, use_arrow_dtype=use_arrow_dtype)
+        return self._table_to_pandas(t, nrows=nrows, dtype_backend=dtype_backend)
 
     def read_group_to_pandas(
-        self, f, group_index, columns=None, nrows=None, use_arrow_dtype=None, **kwargs
+        self, f, group_index, columns=None, nrows=None, dtype_backend=None, **kwargs
     ):
         file = pq.ParquetFile(f)
         t = file.read_row_group(group_index, columns=columns, **kwargs)
-        return self._table_to_pandas(t, nrows=nrows, use_arrow_dtype=use_arrow_dtype)
+        return self._table_to_pandas(t, nrows=nrows, dtype_backend=dtype_backend)
 
 
 class FastpaquetEngine(ParquetEngine):
@@ -203,14 +203,12 @@ class FastpaquetEngine(ParquetEngine):
         dtypes_dict = file._dtypes()
         return pd.Series(dict((c, dtypes_dict[c]) for c in file.columns))
 
-    def read_to_pandas(
-        self, f, columns=None, nrows=None, use_arrow_dtype=None, **kwargs
-    ):
+    def read_to_pandas(self, f, columns=None, nrows=None, dtype_backend=None, **kwargs):
         file = fastparquet.ParquetFile(f)
         df = file.to_pandas(columns, **kwargs)
         if nrows is not None:
             df = df.head(nrows)
-        if use_arrow_dtype:
+        if dtype_backend == "pyarrow":
             df = df.astype(to_arrow_dtypes(df.dtypes).to_dict())
         return df
 
@@ -265,29 +263,30 @@ class CudfEngine:
 class DataFrameReadParquet(
     IncrementalIndexDatasource,
     ColumnPruneSupportedDataSourceMixin,
+    DtypeBackendCompatibleMixin,
 ):
     _op_type_ = opcodes.READ_PARQUET
 
     path = AnyField("path")
     engine = StringField("engine")
     columns = ListField("columns")
-    use_arrow_dtype = BoolField("use_arrow_dtype")
-    groups_as_chunks = BoolField("groups_as_chunks")
-    group_index = Int32Field("group_index")
-    read_kwargs = DictField("read_kwargs")
-    incremental_index = BoolField("incremental_index")
-    storage_options = DictField("storage_options")
-    is_partitioned = BoolField("is_partitioned")
-    merge_small_files = BoolField("merge_small_files")
-    merge_small_file_options = DictField("merge_small_file_options")
+    dtype_backend = StringField("dtype_backend", default=None)
+    groups_as_chunks = BoolField("groups_as_chunks", default=None)
+    group_index = Int32Field("group_index", default=None)
+    read_kwargs = DictField("read_kwargs", default=None)
+    incremental_index = BoolField("incremental_index", default=None)
+    storage_options = DictField("storage_options", default=None)
+    is_partitioned = BoolField("is_partitioned", default=None)
+    merge_small_files = BoolField("merge_small_files", default=None)
+    merge_small_file_options = DictField("merge_small_file_options", default=None)
     # for chunk
     partitions = DictField("partitions", default=None)
     partition_keys = DictField("partition_keys", default=None)
     num_group_rows = Int64Field("num_group_rows", default=None)
     # as read meta may be too time-consuming when number of files is large,
     # thus we only read first file to get row number and raw file size
-    first_chunk_row_num = Int64Field("first_chunk_row_num")
-    first_chunk_raw_bytes = Int64Field("first_chunk_raw_bytes")
+    first_chunk_row_num = Int64Field("first_chunk_row_num", default=None)
+    first_chunk_raw_bytes = Int64Field("first_chunk_raw_bytes", default=None)
 
     def get_columns(self):
         return self.columns
@@ -319,7 +318,7 @@ def read_parquet(
     engine: str = "auto",
     columns: list = None,
     groups_as_chunks: bool = False,
-    use_arrow_dtype: bool = None,
+    dtype_backend: str = None,
     incremental_index: bool = False,
     storage_options: dict = None,
     memory_scale: int = None,
@@ -356,8 +355,8 @@ def read_parquet(
     incremental_index: bool, default False
         If index_col not specified, ensure range index incremental,
         gain a slightly better performance if setting False.
-    use_arrow_dtype: bool, default None
-        If True, use arrow dtype to store columns.
+    dtype_backend: {'numpy', 'pyarrow'}, default 'numpy'
+        Back-end data type applied to the resultant DataFrame (still experimental).
     storage_options: dict, optional
         Options for storage connection.
     memory_scale: int, optional
@@ -401,9 +400,9 @@ def read_parquet(
     if columns:
         dtypes = dtypes[columns]
 
-    if use_arrow_dtype is None:
-        use_arrow_dtype = options.dataframe.use_arrow_dtype
-    if use_arrow_dtype:
+    if dtype_backend is None:
+        dtype_backend = options.dataframe.dtype_backend
+    if dtype_backend == "pyarrow":
         dtypes = to_arrow_dtypes(dtypes)
 
     index_value = parse_index(pd.RangeIndex(-1))
@@ -413,7 +412,7 @@ def read_parquet(
         engine=engine_type,
         columns=columns,
         groups_as_chunks=groups_as_chunks,
-        use_arrow_dtype=use_arrow_dtype,
+        dtype_backend=dtype_backend,
         read_kwargs=kwargs,
         incremental_index=incremental_index,
         storage_options=storage_options,

maxframe/dataframe/datastore/__init__.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from .direct import df_to_dict, series_to_dict, series_to_list, to_clipboard
 from .to_csv import to_csv
 from .to_odps import to_odps_table
 
@@ -20,10 +21,15 @@ def _install():
     from ..core import DATAFRAME_TYPE, SERIES_TYPE
 
     for t in DATAFRAME_TYPE:
+        t.to_clipboard = to_clipboard
         t.to_csv = to_csv
+        t.to_dict = df_to_dict
         t.to_odps_table = to_odps_table
     for t in SERIES_TYPE:
+        t.to_clipboard = to_clipboard
         t.to_csv = to_csv
+        t.to_dict = series_to_dict
+        t.to_list = series_to_list
 
 
 _install()

maxframe/dataframe/datastore/direct.py

@@ -0,0 +1,268 @@
+# Copyright 1999-2025 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from ...utils import pd_release_version
+
+_to_dict_has_index = pd_release_version[0] >= 2
+
+
+def df_to_dict(
+    df, orient="dict", into=dict, index=True, batch_size=10000, session=None
+):
+    """
+    Convert the DataFrame to a dictionary.
+
+    The type of the key-value pairs can be customized with the parameters
+    (see below).
+
+    Parameters
+    ----------
+    orient : str {'dict', 'list', 'series', 'split', 'tight', 'records', 'index'}
+        Determines the type of the values of the dictionary.
+
+        - 'dict' (default) : dict like {column -> {index -> value}}
+        - 'list' : dict like {column -> [values]}
+        - 'series' : dict like {column -> Series(values)}
+        - 'split' : dict like
+          {'index' -> [index], 'columns' -> [columns], 'data' -> [values]}
+        - 'tight' : dict like
+          {'index' -> [index], 'columns' -> [columns], 'data' -> [values],
+          'index_names' -> [index.names], 'column_names' -> [column.names]}
+        - 'records' : list like
+          [{column -> value}, ... , {column -> value}]
+        - 'index' : dict like {index -> {column -> value}}
+
+    into : class, default dict
+        The collections.abc.MutableMapping subclass used for all Mappings
+        in the return value.  Can be the actual class or an empty
+        instance of the mapping type you want.  If you want a
+        collections.defaultdict, you must pass it initialized.
+
+    index : bool, default True
+        Whether to include the index item (and index_names item if `orient`
+        is 'tight') in the returned dictionary. Can only be ``False``
+        when `orient` is 'split' or 'tight'.
+
+    Returns
+    -------
+    dict, list or collections.abc.MutableMapping
+        Return a collections.abc.MutableMapping object representing the
+        DataFrame. The resulting transformation depends on the `orient`
+        parameter.
+
+    See Also
+    --------
+    DataFrame.from_dict: Create a DataFrame from a dictionary.
+    DataFrame.to_json: Convert a DataFrame to JSON format.
+
+    Examples
+    --------
+    >>> import maxframe.dataframe as md
+    >>> df = md.DataFrame({'col1': [1, 2],
+    ...                    'col2': [0.5, 0.75]},
+    ...                   index=['row1', 'row2'])
+    >>> df.execute()
+          col1  col2
+    row1     1  0.50
+    row2     2  0.75
+    >>> df.to_dict()
+    {'col1': {'row1': 1, 'row2': 2}, 'col2': {'row1': 0.5, 'row2': 0.75}}
+
+    You can specify the return orientation.
+
+    >>> df.to_dict('series')
+    {'col1': row1    1
+             row2    2
+    Name: col1, dtype: int64,
+    'col2': row1    0.50
+            row2    0.75
+    Name: col2, dtype: float64}
+
+    >>> df.to_dict('split')
+    {'index': ['row1', 'row2'], 'columns': ['col1', 'col2'],
+     'data': [[1, 0.5], [2, 0.75]]}
+
+    >>> df.to_dict('records')
+    [{'col1': 1, 'col2': 0.5}, {'col1': 2, 'col2': 0.75}]
+
+    >>> df.to_dict('index')
+    {'row1': {'col1': 1, 'col2': 0.5}, 'row2': {'col1': 2, 'col2': 0.75}}
+
+    >>> df.to_dict('tight')
+    {'index': ['row1', 'row2'], 'columns': ['col1', 'col2'],
+     'data': [[1, 0.5], [2, 0.75]], 'index_names': [None], 'column_names': [None]}
+
+    You can also specify the mapping type.
+
+    >>> from collections import OrderedDict, defaultdict
+    >>> df.to_dict(into=OrderedDict)
+    OrderedDict([('col1', OrderedDict([('row1', 1), ('row2', 2)])),
+                 ('col2', OrderedDict([('row1', 0.5), ('row2', 0.75)]))])
+
+    If you want a `defaultdict`, you need to initialize it:
+
+    >>> dd = defaultdict(list)
+    >>> df.to_dict('records', into=dd)
+    [defaultdict(<class 'list'>, {'col1': 1, 'col2': 0.5}),
+     defaultdict(<class 'list'>, {'col1': 2, 'col2': 0.75})]
+    """
+    fetch_kwargs = dict(batch_size=batch_size)
+    to_dict_kw = dict(orient=orient, into=into)
+    if _to_dict_has_index:
+        to_dict_kw["index"] = index
+    return df.to_pandas(session=session, fetch_kwargs=fetch_kwargs).to_dict(
+        **to_dict_kw
+    )
+
+
+def series_to_dict(series, into=dict, batch_size=10000, session=None):
+    """
+    Convert Series to {label -> value} dict or dict-like object.
+
+    Parameters
+    ----------
+    into : class, default dict
+        The collections.abc.Mapping subclass to use as the return
+        object. Can be the actual class or an empty
+        instance of the mapping type you want.  If you want a
+        collections.defaultdict, you must pass it initialized.
+
+    Returns
+    -------
+    collections.abc.Mapping
+        Key-value representation of Series.
+
+    Examples
+    --------
+    >>> import maxframe.dataframe as md
+    >>> s = md.Series([1, 2, 3, 4])
+    >>> s.to_dict()
+    {0: 1, 1: 2, 2: 3, 3: 4}
+    >>> from collections import OrderedDict, defaultdict
+    >>> s.to_dict(OrderedDict)
+    OrderedDict([(0, 1), (1, 2), (2, 3), (3, 4)])
+    >>> dd = defaultdict(list)
+    >>> s.to_dict(dd)
+    defaultdict(<class 'list'>, {0: 1, 1: 2, 2: 3, 3: 4})
+    """
+    fetch_kwargs = dict(batch_size=batch_size)
+    return series.to_pandas(session=session, fetch_kwargs=fetch_kwargs).to_dict(
+        into=into
+    )
+
+
+def series_to_list(series, batch_size=10000, session=None):
+    """
+    Return a list of the values.
+
+    These are each a scalar type, which is a Python scalar
+    (for str, int, float) or a pandas scalar
+    (for Timestamp/Timedelta/Interval/Period)
+
+    Returns
+    -------
+    list
+
+    See Also
+    --------
+    numpy.ndarray.tolist : Return the array as an a.ndim-levels deep
+        nested list of Python scalars.
+
+    Examples
+    --------
+    For Series
+
+    >>> import maxframe.dataframe as md
+    >>> s = md.Series([1, 2, 3])
+    >>> s.to_list()
+    [1, 2, 3]
+
+    For Index:
+
+    >>> idx = md.Index([1, 2, 3])
+    >>> idx.execute()
+    Index([1, 2, 3], dtype='int64')
+
+    >>> idx.to_list()
+    [1, 2, 3]
+    """
+    fetch_kwargs = dict(batch_size=batch_size)
+    return series.to_pandas(session=session, fetch_kwargs=fetch_kwargs).to_list()
+
+
+def to_clipboard(
+    obj, *, excel=True, sep=None, batch_size=10000, session=None, **kwargs
+):
+    """
+    Copy object to the system clipboard.
+
+    Write a text representation of object to the system clipboard.
+    This can be pasted into Excel, for example.
+
+    Parameters
+    ----------
+    excel : bool, default True
+        Produce output in a csv format for easy pasting into excel.
+
+        - True, use the provided separator for csv pasting.
+        - False, write a string representation of the object to the clipboard.
+
+    sep : str, default ``'\t'``
+        Field delimiter.
+    **kwargs
+        These parameters will be passed to DataFrame.to_csv.
+
+    See Also
+    --------
+    DataFrame.to_csv : Write a DataFrame to a comma-separated values
+        (csv) file.
+    read_clipboard : Read text from clipboard and pass to read_csv.
+
+    Notes
+    -----
+    Requirements for your platform.
+
+      - Linux : `xclip`, or `xsel` (with `PyQt4` modules)
+      - Windows : none
+      - macOS : none
+
+    This method uses the processes developed for the package `pyperclip`. A
+    solution to render any output string format is given in the examples.
+
+    Examples
+    --------
+    Copy the contents of a DataFrame to the clipboard.
+
+    >>> import maxframe.dataframe as md
+    >>> df = md.DataFrame([[1, 2, 3], [4, 5, 6]], columns=['A', 'B', 'C'])
+
+    >>> df.to_clipboard(sep=',')  # doctest: +SKIP
+    ... # Wrote the following to the system clipboard:
+    ... # ,A,B,C
+    ... # 0,1,2,3
+    ... # 1,4,5,6
+
+    We can omit the index by passing the keyword `index` and setting
+    it to false.
+
+    >>> df.to_clipboard(sep=',', index=False)  # doctest: +SKIP
+    ... # Wrote the following to the system clipboard:
+    ... # A,B,C
+    ... # 1,2,3
+    ... # 4,5,6
+    """
+    fetch_kwargs = dict(batch_size=batch_size)
+    return obj.to_pandas(session=session, fetch_kwargs=fetch_kwargs).to_clipboard(
+        excel=excel, sep=sep, **kwargs
+    )

maxframe/dataframe/datastore/to_odps.py

@@ -57,10 +57,16 @@ class DataFrameToODPSTable(DataFrameDataStore):
     lifecycle = Int64Field("lifecycle", default=None)
     table_properties = DictField("table_properties", default=None)
     primary_key = ListField("primary_key", FieldTypes.string, default=None)
+    use_generated_table_meta = BoolField("use_generated_table_meta", default=False)
 
     def __init__(self, **kw):
         super().__init__(_output_types=[OutputType.dataframe], **kw)
 
+    def check_inputs(self, inputs: List[TileableType]):
+        if self.use_generated_table_meta:
+            return None
+        return super().check_inputs(inputs)
+
     def __call__(self, x):
         shape = (0,) * len(x.shape)
         index_value = parse_index(x.index_value.to_pandas()[:0], x.key, "index")

maxframe/dataframe/extensions/flatjson.py

@@ -39,12 +39,13 @@ class SeriesFlatJSONOperator(DataFrameOperator, DataFrameOperatorMixin):
                 name=name,
                 dtype=make_dtype(dtype),
             )
+        dtypes = make_dtypes(dtypes)
         return self.new_dataframe(
             [series],
             shape=(series.shape[0], len(dtypes)),
             index_value=series.index_value,
             columns_value=parse_index(dtypes.index, store_data=True),
-            dtypes=make_dtypes(dtypes),
+            dtypes=dtypes,
         )
 
 

maxframe/dataframe/groupby/__init__.py

@@ -14,7 +14,7 @@
 
 # noinspection PyUnresolvedReferences
 from ..core import DataFrameGroupBy, GroupBy, SeriesGroupBy
-from .core import NamedAgg
+from .core import _make_named_agg_compat
 from .expanding import ExpandingGroupby
 from .rolling import RollingGroupby
 
@@ -99,3 +99,7 @@ def _install():
 
 _install()
 del _install
+
+
+__getattr__ = _make_named_agg_compat
+del _make_named_agg_compat

maxframe/dataframe/groupby/aggregation.py

@@ -21,7 +21,7 @@ import pandas as pd
 
 from ... import opcodes
 from ...config import options
-from ...core import ENTITY_TYPE, EntityData, OutputType
+from ...core import ENTITY_TYPE, EntityData, OutputType, enter_mode
 from ...serialization import PickleContainer
 from ...serialization.serializables import (
     AnyField,
@@ -34,7 +34,7 @@ from ...serialization.serializables import (
     StringField,
 )
 from ...udf import BuiltinFunction
-from ...utils import find_objects, lazy_import, pd_release_version
+from ...utils import find_objects, get_pd_option, lazy_import, pd_release_version
 from ..core import GROUPBY_TYPE
 from ..operators import DataFrameOperator, DataFrameOperatorMixin
 from ..reduction.aggregation import (
@@ -116,7 +116,10 @@ def build_mock_agg_result(
     **raw_func_kw,
 ):
     try:
-        agg_result = groupby.op.build_mock_groupby().aggregate(raw_func, **raw_func_kw)
+        with enter_mode(mock=True):
+            agg_result = groupby.op.build_mock_groupby().aggregate(
+                raw_func, **raw_func_kw
+            )
     except ValueError:
         if (
             groupby_params.get("as_index") or _support_get_group_without_as_index
@@ -377,9 +380,10 @@ def agg(groupby, func=None, method="auto", *args, **kwargs):
     1   1   2  0.590715
     2   3   4  0.704907
 
-    To control the output names with different aggregations per column, pandas supports “named aggregation”
+    To control the output names with different aggregations per column,
+    MaxFrame supports “named aggregation”
 
-    >>> from maxframe.dataframe.groupby import NamedAgg
+    >>> from maxframe.dataframe import NamedAgg
     >>> df.groupby("A").agg(
     ...  b_min=NamedAgg(column="B", aggfunc="min"),
     ...  c_sum=NamedAgg(column="C", aggfunc="sum")).execute()
@@ -432,6 +436,6 @@ def agg(groupby, func=None, method="auto", *args, **kwargs):
         groupby_params=groupby.op.groupby_params,
         combine_size=combine_size,
         chunk_store_limit=options.chunk_store_limit,
-        use_inf_as_na=pd.get_option("mode.use_inf_as_na"),
+        use_inf_as_na=get_pd_option("mode.use_inf_as_na", False),
     )
     return agg_op(groupby)

maxframe/dataframe/groupby/apply_chunk.py

@@ -29,7 +29,7 @@ from ...serialization.serializables import (
     TupleField,
 )
 from ...udf import BuiltinFunction, MarkedFunction
-from ...utils import copy_if_possible
+from ...utils import copy_if_possible, make_dtype, make_dtypes
 from ..core import (
     DATAFRAME_GROUPBY_TYPE,
     GROUPBY_TYPE,
@@ -45,8 +45,6 @@ from ..utils import (
     copy_func_scheduling_hints,
     infer_dataframe_return_value,
     make_column_list,
-    make_dtype,
-    make_dtypes,
     parse_index,
     validate_output_types,
 )

maxframe/dataframe/groupby/core.py

@@ -12,7 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from collections import namedtuple
+import os
+import warnings
 from typing import Any, Dict, List
 
 import pandas as pd
@@ -20,6 +21,7 @@ import pandas as pd
 from ... import opcodes
 from ...core import ENTITY_TYPE, Entity, EntityData, OutputType
 from ...core.operator import MapReduceOperator
+from ...env import MAXFRAME_INSIDE_TASK
 from ...serialization import PickleContainer
 from ...serialization.serializables import AnyField, BoolField, DictField, Int32Field
 from ...udf import BuiltinFunction
@@ -38,9 +40,6 @@ from ..utils import (
 cudf = lazy_import("cudf")
 
 
-NamedAgg = namedtuple("NamedAgg", ["column", "aggfunc"])
-
-
 class DataFrameGroupByOp(MapReduceOperator, DataFrameOperatorMixin):
     _op_type_ = opcodes.GROUPBY
     _legacy_name = "DataFrameGroupByOperator"  # since v2.0.0
@@ -324,3 +323,20 @@ class BaseGroupByWindowOp(DataFrameOperatorMixin, DataFrameOperator):
             name, dtype = out_dtypes
             kw.update(dtype=dtype, name=name, shape=(groupby.shape[0],))
         return self.new_tileable([in_df], **kw)
+
+
+def _make_named_agg_compat(name):  # pragma: no cover
+    # to make imports compatible
+    from ..reduction import NamedAgg
+
+    if name == "NamedAgg":
+        if MAXFRAME_INSIDE_TASK not in os.environ:
+            warnings.warn(
+                "Please import NamedAgg from maxframe.dataframe",
+                DeprecationWarning,
+            )
+        return NamedAgg
+    raise AttributeError(f"module {__name__} has no attribute {name}")
+
+
+__getattr__ = _make_named_agg_compat

maxframe/dataframe/indexing/__init__.py

@@ -29,7 +29,7 @@ def _install():
     from .getitem import dataframe_getitem, series_getitem
     from .iat import iat
     from .iloc import head, iloc, index_getitem, index_setitem, tail
-    from .insert import df_insert
+    from .insert import df_insert, index_insert
     from .loc import loc
     from .reindex import reindex, reindex_like
     from .rename import df_rename, index_rename, index_set_names, series_rename
@@ -94,6 +94,7 @@ def _install():
         setattr(cls, "droplevel", index_droplevel)
         setattr(cls, "get_level_values", get_level_values)
         setattr(cls, "__getitem__", index_getitem)
+        setattr(cls, "insert", index_insert)
         setattr(cls, "rename", index_rename)
         setattr(cls, "__setitem__", index_setitem)
         setattr(cls, "set_names", index_set_names)