maxframe 1.0.0rc1__cp311-cp311-win_amd64.whl → 1.0.0rc2__cp311-cp311-win_amd64.whl

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/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/learn/contrib/xgboost/dmatrix.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-from .... import opcodes as OperandDef
+from .... import opcodes
 from ....core.entity.output_types import get_output_types
 from ....core.operator.base import Operator
 from ....core.operator.core import TileableOperatorMixin
@@ -27,7 +27,7 @@ from ...utils import convert_to_tensor_or_dataframe
 
 
 class ToDMatrix(Operator, TileableOperatorMixin):
-    _op_type_ = OperandDef.TO_DMATRIX
+    _op_type_ = opcodes.TO_DMATRIX
 
     data = KeyField("data", default=None)
     label = KeyField("label", default=None)

maxframe/learn/contrib/xgboost/predict.py

@@ -17,7 +17,7 @@ import pickle
 import numpy as np
 import pandas as pd
 
-from .... import opcodes as OperandDef
+from .... import opcodes
 from ....core.entity.output_types import OutputType
 from ....core.operator.base import Operator
 from ....core.operator.core import TileableOperatorMixin
@@ -28,7 +28,7 @@ from .dmatrix import check_data
 
 
 class XGBPredict(Operator, TileableOperatorMixin):
-    _op_type_ = OperandDef.XGBOOST_PREDICT
+    _op_type_ = opcodes.XGBOOST_PREDICT
     output_dtype = np.dtype(np.float32)
 
     data = KeyField("data", default=None)

maxframe/learn/contrib/xgboost/train.py

@@ -15,7 +15,7 @@
 import logging
 from collections import OrderedDict
 
-from .... import opcodes as OperandDef
+from .... import opcodes
 from ....core import OutputType
 from ....core.operator.base import Operator
 from ....core.operator.core import TileableOperatorMixin
@@ -41,7 +41,7 @@ def _on_serialize_evals(evals_val):
 
 
 class XGBTrain(Operator, TileableOperatorMixin):
-    _op_type_ = OperandDef.XGBOOST_TRAIN
+    _op_type_ = opcodes.XGBOOST_TRAIN
 
     params = DictField("params", key_type=FieldTypes.string, default=None)
     dtrain = KeyField("dtrain", default=None)

maxframe/odpsio/__init__.py

@@ -18,4 +18,4 @@ from .schema import (
     odps_schema_to_pandas_dtypes,
     pandas_to_odps_schema,
 )
-from .tableio import HaloTableIO
+from .tableio import HaloTableIO, ODPSTableIO

maxframe/odpsio/arrow.py

@@ -45,9 +45,13 @@ def _rebuild_dataframe(
 
 def _rebuild_index(df: pd.DataFrame, table_meta: DataFrameTableMeta) -> pd.Index:
     if df.shape[1] > 1:
-        df.columns = pd.Index(table_meta.pd_index_level_names)
-        return pd.MultiIndex.from_frame(df)
-    return pd.Index(df.iloc[:, 0], name=table_meta.pd_index_level_names[0])
+        idx = pd.MultiIndex.from_frame(df)
+        idx.names = table_meta.pd_index_level_names
+    else:
+        # make sure even if None names are updated properly
+        idx = pd.Index(df.iloc[:, 0])
+        idx.name = table_meta.pd_index_level_names[0]
+    return idx
 
 
 def arrow_to_pandas(
@@ -75,7 +79,7 @@ def pandas_to_arrow(
         df.columns = pd.Index(table_meta.table_column_names)
         if not ignore_index:
             df = df.rename_axis(table_meta.table_index_column_names).reset_index()
-    elif ignore_index:
+    elif ignore_index and table_meta.type != OutputType.index:
         df = pd.DataFrame([], columns=[])
     elif table_meta.type == OutputType.index:
         names = [f"_idx_{idx}" for idx in range(len(df.names))]

maxframe/odpsio/schema.py

@@ -126,10 +126,15 @@ def odps_type_to_arrow_type(
             ]
             col_type = pa.struct(fields)
         elif isinstance(odps_type, odps_types.Decimal):
-            col_type = pa.decimal128(
-                odps_type.precision or odps_types.Decimal._max_precision,
-                odps_type.scale or odps_types.Decimal._max_scale,
-            )
+            if odps_type.name == "decimal":
+                # legacy decimal data without precision or scale
+                # precision data from internal compat mode
+                col_type = pa.decimal128(38, 18)
+            else:
+                col_type = pa.decimal128(
+                    odps_type.precision or odps_types.Decimal._max_precision,
+                    odps_type.scale or odps_types.Decimal._max_scale,
+                )
         elif isinstance(odps_type, (odps_types.Varchar, odps_types.Char)):
             col_type = pa.string()
         else:
@@ -289,8 +294,6 @@ def build_dataframe_table_meta(
     else:  # pragma: no cover
         raise TypeError(f"Cannot accept type {type(df_obj)}")
 
-    assert not ignore_index or obj_type in (OutputType.dataframe, OutputType.series)
-
     if obj_type == OutputType.scalar:
         pd_dtypes = pd.Series([])
         column_index_names = []
@@ -346,7 +349,7 @@ def build_dataframe_table_meta(
     else:
         index_dtypes = pd.Series([pd_index_val.dtype], index=pd_index_val.names)
 
-    if ignore_index:
+    if ignore_index and obj_type != OutputType.index:
         table_index_column_names = []
         pd_index_dtypes = pd.Series([], index=[])
     else: