maxframe 1.0.0rc1__cp39-cp39-win32.whl → 1.0.0rc3__cp39-cp39-win32.whl

maxframe/dataframe/misc/apply.py

@@ -319,6 +319,7 @@ def df_apply(
     skip_infer=False,
     **kwds,
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/50
     """
     Apply a function along an axis of the DataFrame.
 
@@ -444,20 +445,12 @@ def df_apply(
     B    27
     dtype: int64
 
-    >>> df.apply(np.sum, axis=1).execute()
+    >>> df.apply(lambda row: int(np.sum(row)), axis=1).execute()
     0    13
     1    13
     2    13
     dtype: int64
 
-    Returning a list-like will result in a Series
-
-    >>> df.apply(lambda x: [1, 2], axis=1).execute()
-    0    [1, 2]
-    1    [1, 2]
-    2    [1, 2]
-    dtype: object
-
     Passing ``result_type='expand'`` will expand list-like results
     to columns of a Dataframe
 
@@ -471,7 +464,7 @@ def df_apply(
     ``result_type='expand'``. The resulting column names
     will be the Series index.
 
-    >>> df.apply(lambda x: md.Series([1, 2], index=['foo', 'bar']), axis=1).execute()
+    >>> df.apply(lambda x: pd.Series([1, 2], index=['foo', 'bar']), axis=1).execute()
        foo  bar
     0    1    2
     1    1    2

maxframe/dataframe/misc/case_when.py

@@ -99,7 +99,7 @@ def case_when(series, caselist):
     >>> b = md.Series([0, 3, 4, 5])
 
     >>> c.case_when(caselist=[(a.gt(0), a),  # condition, replacement
-    ...                       (b.gt(0), b)])
+    ...                       (b.gt(0), b)]).execute()
     0    6
     1    3
     2    1

maxframe/dataframe/misc/describe.py

@@ -15,7 +15,7 @@
 import numpy as np
 import pandas as pd
 
-from ... import opcodes as OperandDef
+from ... import opcodes
 from ...serialization.serializables import AnyField, FieldTypes, KeyField, ListField
 from ..core import SERIES_TYPE
 from ..operators import DataFrameOperator, DataFrameOperatorMixin
@@ -23,7 +23,7 @@ from ..utils import build_empty_df, parse_index
 
 
 class DataFrameDescribe(DataFrameOperator, DataFrameOperatorMixin):
-    _op_type_ = OperandDef.DESCRIBE
+    _op_type_ = opcodes.DESCRIBE
 
     input = KeyField("input", default=None)
     percentiles = ListField("percentiles", FieldTypes.float64, default=None)

maxframe/dataframe/misc/drop_duplicates.py

@@ -37,16 +37,15 @@ class DataFrameDropDuplicates(DuplicateOperand):
             shape += (3,)
         return shape
 
-    @classmethod
-    def _gen_tileable_params(cls, op: "DataFrameDropDuplicates", input_params):
+    def _gen_tileable_params(self, op: "DataFrameDropDuplicates", input_params):
         params = input_params.copy()
-        if op.ignore_index:
+        if op.ignore_index and self._output_types[0] != OutputType.index:
             params["index_value"] = parse_index(pd.RangeIndex(-1))
         else:
             params["index_value"] = gen_unknown_index_value(
                 input_params["index_value"], op.keep, op.subset, type(op).__name__
             )
-        params["shape"] = cls._get_shape(input_params["shape"], op)
+        params["shape"] = self._get_shape(input_params["shape"], op)
         return params
 
     def __call__(self, inp, inplace=False):
@@ -105,6 +104,7 @@ def df_drop_duplicates(
 def series_drop_duplicates(
     series, keep="first", inplace=False, ignore_index=False, method="auto"
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/12
     """
     Return Series with duplicate values removed.
 
@@ -148,27 +148,6 @@ def series_drop_duplicates(
     5     hippo
     Name: animal, dtype: object
 
-    With the 'keep' parameter, the selection behaviour of duplicated values
-    can be changed. The value 'first' keeps the first occurrence for each
-    set of duplicated entries. The default value of keep is 'first'.
-
-    >>> s.drop_duplicates().execute()
-    0      lame
-    1       cow
-    3    beetle
-    5     hippo
-    Name: animal, dtype: object
-
-    The value 'last' for parameter 'keep' keeps the last occurrence for
-    each set of duplicated entries.
-
-    >>> s.drop_duplicates(keep='last').execute()
-    1       cow
-    3    beetle
-    4      lame
-    5     hippo
-    Name: animal, dtype: object
-
     The value ``False`` for parameter 'keep' discards all sets of
     duplicated entries. Setting the value of 'inplace' to ``True`` performs
     the operation inplace and returns ``None``.

maxframe/dataframe/misc/eval.py

@@ -120,6 +120,10 @@ class CollectionVisitor(ast.NodeVisitor):
         if obj_name in self.env:
             self.referenced_vars.add(obj_name)
             return self.env[obj_name]
+        try:
+            return self.target[obj_name]
+        except KeyError:
+            pass
         raise KeyError(f"name {obj_name} is not defined")
 
     def visit(self, node):

maxframe/dataframe/misc/pct_change.py

@@ -18,6 +18,7 @@ from ..utils import validate_axis
 def pct_change(
     df_or_series, periods=1, fill_method="pad", limit=None, freq=None, **kwargs
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/32
     """
     Percentage change between the current and a prior element.
 
@@ -50,89 +51,6 @@ def pct_change(
     DataFrame.diff : Compute the difference of two elements in a DataFrame.
     Series.shift : Shift the index by some number of periods.
     DataFrame.shift : Shift the index by some number of periods.
-
-    Examples
-    --------
-    **Series**
-
-    >>> import maxframe.dataframe as md
-
-    >>> s = md.Series([90, 91, 85])
-    >>> s.execute()
-    0    90
-    1    91
-    2    85
-    dtype: int64
-
-    >>> s.pct_change().execute()
-    0         NaN
-    1    0.011111
-    2   -0.065934
-    dtype: float64
-
-    >>> s.pct_change(periods=2).execute()
-    0         NaN
-    1         NaN
-    2   -0.055556
-    dtype: float64
-
-    See the percentage change in a Series where filling NAs with last
-    valid observation forward to next valid.
-
-    >>> s = md.Series([90, 91, None, 85])
-    >>> s.execute()
-    0    90.0
-    1    91.0
-    2     NaN
-    3    85.0
-    dtype: float64
-
-    >>> s.pct_change(fill_method='ffill').execute()
-    0         NaN
-    1    0.011111
-    2    0.000000
-    3   -0.065934
-    dtype: float64
-
-    **DataFrame**
-
-    Percentage change in French franc, Deutsche Mark, and Italian lira from
-    1980-01-01 to 1980-03-01.
-
-    >>> df = md.DataFrame({
-    ...     'FR': [4.0405, 4.0963, 4.3149],
-    ...     'GR': [1.7246, 1.7482, 1.8519],
-    ...     'IT': [804.74, 810.01, 860.13]},
-    ...     index=['1980-01-01', '1980-02-01', '1980-03-01'])
-    >>> df.execute()
-                    FR      GR      IT
-    1980-01-01  4.0405  1.7246  804.74
-    1980-02-01  4.0963  1.7482  810.01
-    1980-03-01  4.3149  1.8519  860.13
-
-    >>> df.pct_change().execute()
-                      FR        GR        IT
-    1980-01-01       NaN       NaN       NaN
-    1980-02-01  0.013810  0.013684  0.006549
-    1980-03-01  0.053365  0.059318  0.061876
-
-    Percentage of change in GOOG and APPL stock volume. Shows computing
-    the percentage change between columns.
-
-    >>> df = md.DataFrame({
-    ...     '2016': [1769950, 30586265],
-    ...     '2015': [1500923, 40912316],
-    ...     '2014': [1371819, 41403351]},
-    ...     index=['GOOG', 'APPL'])
-    >>> df.execute()
-              2016      2015      2014
-    GOOG   1769950   1500923   1371819
-    APPL  30586265  40912316  41403351
-
-    >>> df.pct_change(axis='columns').execute()
-          2016      2015      2014
-    GOOG   NaN -0.151997 -0.086016
-    APPL   NaN  0.337604  0.012002
     """
 
     axis = validate_axis(kwargs.pop("axis", 0))

maxframe/dataframe/misc/transform.py

@@ -228,21 +228,6 @@ def df_transform(df, func, axis=0, *args, dtypes=None, skip_infer=False, **kwarg
     0  1  2
     1  2  3
     2  3  4
-
-    Even though the resulting DataFrame must have the same length as the
-    input DataFrame, it is possible to provide several input functions:
-
-    >>> s = md.Series(range(3))
-    >>> s.execute()
-    0    0
-    1    1
-    2    2
-    dtype: int64
-    >>> s.transform([mt.sqrt, mt.exp]).execute()
-           sqrt        exp
-    0  0.000000   1.000000
-    1  1.000000   2.718282
-    2  1.414214   7.389056
     """
     op = TransformOperator(
         func=func,
@@ -265,6 +250,7 @@ def series_transform(
     dtype=None,
     **kwargs
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/10
     """
     Call ``func`` on self producing a Series with transformed values.
 
@@ -332,21 +318,6 @@ def series_transform(
     0  1  2
     1  2  3
     2  3  4
-
-    Even though the resulting Series must have the same length as the
-    input Series, it is possible to provide several input functions:
-
-    >>> s = md.Series(range(3))
-    >>> s.execute()
-    0    0
-    1    1
-    2    2
-    dtype: int64
-    >>> s.transform([mt.sqrt, mt.exp]).execute()
-       sqrt        exp
-    0  0.000000   1.000000
-    1  1.000000   2.718282
-    2  1.414214   7.389056
     """
     op = TransformOperator(
         func=func,

maxframe/dataframe/misc/value_counts.py

@@ -85,6 +85,7 @@ def value_counts(
     dropna=True,
     method="auto",
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/33
     """
     Return a Series containing counts of unique values.
 
@@ -125,9 +126,8 @@ def value_counts(
     Examples
     --------
     >>> import maxframe.dataframe as md
-    >>> import maxframe.tensor as mt
-
-    >>> s = md.Series([3, 1, 2, 3, 4, mt.nan])
+    >>> import numpy as np
+    >>> s = md.Series([3, 1, 2, 3, 4, np.nan])
     >>> s.value_counts().execute()
     3.0    2
     4.0    1
@@ -138,7 +138,7 @@ def value_counts(
     With `normalize` set to `True`, returns the relative frequency by
     dividing all values by the sum of values.
 
-    >>> s = md.Series([3, 1, 2, 3, 4, mt.nan])
+    >>> s = md.Series([3, 1, 2, 3, 4, np.nan])
     >>> s.value_counts(normalize=True).execute()
     3.0    0.4
     4.0    0.2
@@ -146,19 +146,6 @@ def value_counts(
     1.0    0.2
     dtype: float64
 
-    **bins**
-
-    Bins can be useful for going from a continuous variable to a
-    categorical variable; instead of counting unique
-    apparitions of values, divide the index in the specified
-    number of half-open bins.
-
-    >>> s.value_counts(bins=3).execute()
-    (2.0, 3.0]      2
-    (0.996, 2.0]    2
-    (3.0, 4.0]      1
-    dtype: int64
-
     **dropna**
 
     With `dropna` set to `False` we can also see NaN index values.

maxframe/dataframe/missing/dropna.py

@@ -234,7 +234,7 @@ def series_dropna(series, axis=0, inplace=False, how=None):
     Empty strings are not considered NA values. ``None`` is considered an
     NA value.
 
-    >>> ser = md.Series([np.NaN, 2, md.NaT, '', None, 'I stay'])
+    >>> ser = md.Series([np.NaN, '2', md.NaT, '', None, 'I stay'])
     >>> ser.execute()
     0       NaN
     1         2

maxframe/dataframe/missing/fillna.py

@@ -132,11 +132,11 @@ def fillna(
     --------
     >>> import maxframe.tensor as mt
     >>> import maxframe.dataframe as md
-    >>> df = md.DataFrame([[mt.nan, 2, mt.nan, 0],
-    ...                    [3, 4, mt.nan, 1],
-    ...                    [mt.nan, mt.nan, mt.nan, 5],
-    ...                    [mt.nan, 3, mt.nan, 4]],
-    ...                   columns=list('ABCD'))
+    >>> df = md.DataFrame([[np.nan, 2, np.nan, 0],
+                           [3, 4, np.nan, 1],
+                           [np.nan, np.nan, np.nan, 5],
+                           [np.nan, 3, np.nan, 4]],
+                          columns=list('ABCD'))
     >>> df.execute()
          A    B   C  D
     0  NaN  2.0 NaN  0

maxframe/dataframe/operators.py

@@ -16,13 +16,7 @@ import numpy as np
 import pandas as pd
 
 from ..core import ENTITY_TYPE, OutputType
-from ..core.operator import (
-    Fuse,
-    FuseChunkMixin,
-    Operator,
-    ShuffleProxy,
-    TileableOperatorMixin,
-)
+from ..core.operator import Operator, ShuffleProxy, TileableOperatorMixin
 from ..tensor.core import TENSOR_TYPE
 from ..tensor.datasource import tensor as astensor
 from .core import DATAFRAME_TYPE, SERIES_TYPE
@@ -261,13 +255,3 @@ DataFrameOperator = Operator
 class DataFrameShuffleProxy(ShuffleProxy, DataFrameOperatorMixin):
     def __init__(self, sparse=None, output_types=None, **kwargs):
         super().__init__(sparse=sparse, _output_types=output_types, **kwargs)
-
-
-class DataFrameFuseChunkMixin(FuseChunkMixin, DataFrameOperatorMixin):
-    __slots__ = ()
-
-
-class DataFrameFuseChunk(Fuse, DataFrameFuseChunkMixin):
-    @property
-    def output_types(self):
-        return self.outputs[-1].chunk.op.output_types

maxframe/dataframe/reduction/core.py

@@ -552,7 +552,7 @@ class ReductionCompiler:
     @enter_mode(build=True)
     def _compile_function(self, func, func_name=None, ndim=1) -> ReductionSteps:
         from ...tensor.arithmetic.core import TensorBinOp, TensorUnaryOp
-        from ...tensor.base import TensorWhere
+        from ...tensor.misc import TensorWhere
         from ..arithmetic.core import DataFrameBinOp, DataFrameUnaryOp
         from ..datasource.dataframe import DataFrameDataSource
         from ..datasource.series import SeriesDataSource
@@ -679,8 +679,8 @@ class ReductionCompiler:
         ]
         """
         from ...tensor.arithmetic.core import TensorBinOp, TensorUnaryOp
-        from ...tensor.base import TensorWhere
         from ...tensor.datasource import Scalar
+        from ...tensor.misc import TensorWhere
         from ..arithmetic.core import DataFrameBinOp, DataFrameUnaryOp
         from ..datasource.dataframe import DataFrameDataSource
         from ..datasource.series import SeriesDataSource

maxframe/dataframe/sort/sort_values.py

@@ -67,6 +67,7 @@ def dataframe_sort_values(
     parallel_kind="PSRS",
     psrs_kinds=None,
 ):
+    # FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/15
     """
     Sort by the values along either axis.
 
@@ -152,17 +153,6 @@ def dataframe_sort_values(
     0   A    2    0
     1   A    1    1
     3   NaN  8    4
-
-    Putting NAs first
-
-    >>> df.sort_values(by='col1', ascending=False, na_position='first').execute()
-        col1 col2 col3
-    3   NaN  8    4
-    4   D    7    2
-    5   C    4    3
-    2   B    9    9
-    0   A    2    0
-    1   A    1    1
     """
 
     if na_position not in ["last", "first"]:  # pragma: no cover

maxframe/dataframe/statistics/quantile.py

@@ -14,8 +14,9 @@
 
 import numpy as np
 import pandas as pd
+from pandas.core.dtypes.cast import find_common_type
 
-from ... import opcodes as OperandDef
+from ... import opcodes
 from ...core import ENTITY_TYPE
 from ...serialization.serializables import (
     AnyField,
@@ -32,11 +33,11 @@ from ...tensor.datasource import tensor as astensor
 from ...tensor.statistics.quantile import quantile as tensor_quantile
 from ..core import DATAFRAME_TYPE
 from ..operators import DataFrameOperator, DataFrameOperatorMixin
-from ..utils import build_empty_df, find_common_type, parse_index, validate_axis
+from ..utils import build_empty_df, parse_index, validate_axis
 
 
 class DataFrameQuantile(DataFrameOperator, DataFrameOperatorMixin):
-    _op_type_ = OperandDef.QUANTILE
+    _op_type_ = opcodes.QUANTILE
 
     input = KeyField("input", default=None)
     q = AnyField("q", default=None)
@@ -259,6 +260,7 @@ def quantile_series(series, q=0.5, interpolation="linear"):
 
 
 def quantile_dataframe(df, q=0.5, axis=0, numeric_only=True, interpolation="linear"):
+    # FIXME: Timedelta not support. Data invalid: ODPS-0010000:InvalidArgument:duration[ns] is not equal to string
     """
     Return values at the given quantile over requested axis.
 
@@ -309,20 +311,6 @@ def quantile_dataframe(df, q=0.5, axis=0, numeric_only=True, interpolation="line
            a     b
     0.1  1.3   3.7
     0.5  2.5  55.0
-
-    Specifying `numeric_only=False` will also compute the quantile of
-    datetime and timedelta data.
-
-    >>> df = md.DataFrame({'A': [1, 2],
-    ...                    'B': [md.Timestamp('2010'),
-    ...                          md.Timestamp('2011')],
-    ...                    'C': [md.Timedelta('1 days'),
-    ...                          md.Timedelta('2 days')]})
-    >>> df.quantile(0.5, numeric_only=False).execute()
-    A                    1.5
-    B    2010-07-02 12:00:00
-    C        1 days 12:00:00
-    Name: 0.5, dtype: object
     """
     if isinstance(q, ENTITY_TYPE):
         q = astensor(q)

maxframe/dataframe/utils.py

@@ -26,7 +26,6 @@ import numpy as np
 import pandas as pd
 from pandas.api.extensions import ExtensionDtype
 from pandas.api.types import is_string_dtype
-from pandas.core.dtypes.cast import find_common_type
 from pandas.core.dtypes.inference import is_dict_like, is_list_like
 
 from ..core import Entity, ExecutableTuple
@@ -477,11 +476,11 @@ def build_df(df_obj, fill_value=1, size=1, ensure_string=False):
     else:
         fill_values = fill_value
 
-    from .core import SERIES_TYPE
+    from .core import INDEX_TYPE, SERIES_TYPE
 
     dtypes = (
         pd.Series([df_obj.dtype], index=[df_obj.name])
-        if isinstance(df_obj, SERIES_TYPE)
+        if isinstance(df_obj, (INDEX_TYPE, SERIES_TYPE))
         else df_obj.dtypes
     )
     for size, fill_value in zip(sizes, fill_values):
@@ -593,7 +592,7 @@ def build_series(
     return ret_series
 
 
-def infer_index_value(left_index_value, right_index_value):
+def infer_index_value(left_index_value, right_index_value, level=None):
     from .core import IndexValue
 
     if isinstance(left_index_value.value, IndexValue.RangeIndex) and isinstance(
@@ -616,9 +615,7 @@ def infer_index_value(left_index_value, right_index_value):
 
     left_index = left_index_value.to_pandas()
     right_index = right_index_value.to_pandas()
-    out_index = pd.Index(
-        [], dtype=find_common_type([left_index.dtype, right_index.dtype])
-    )
+    out_index = left_index.join(right_index, level=level)[:0]
     return parse_index(out_index, left_index_value, right_index_value)
 
 

maxframe/io/objects/__init__.py

@@ -0,0 +1,24 @@
+# Copyright 1999-2024 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 .core import (
+    AbstractObjectIOHandler,
+    get_object_io_handler,
+    register_object_io_handler,
+)
+
+# isort: off
+from . import tensor
+
+del tensor