maxframe 1.0.0rc1__tar.gz → 1.0.0rc2__tar.gz

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/MANIFEST.in

@@ -4,6 +4,7 @@ global-include *.pxd
 global-exclude *.c
 global-exclude *.cpp
 include pyproject.toml
+include README.rst
 include maxframe/lib/mmh3_src/*
 exclude **/tests/**/*
 exclude **/tests/*

maxframe-1.0.0rc2/PKG-INFO

@@ -0,0 +1,177 @@
+Metadata-Version: 2.1
+Name: maxframe
+Version: 1.0.0rc2
+Summary: MaxFrame operator-based data analyze framework
+Requires-Dist: numpy<2.0.0,>=1.19.0
+Requires-Dist: pandas>=1.0.0
+Requires-Dist: pyodps>=0.11.6.1
+Requires-Dist: scipy>=1.0
+Requires-Dist: pyarrow>=1.0.0
+Requires-Dist: msgpack>=1.0.0
+Requires-Dist: traitlets>=5.0
+Requires-Dist: cloudpickle>=1.5.0
+Requires-Dist: pyyaml>=5.1
+Requires-Dist: pickle5; python_version < "3.8"
+Requires-Dist: tornado>=6.0
+Requires-Dist: defusedxml>=0.5.0
+Requires-Dist: tqdm>=4.1.0
+Requires-Dist: importlib_metadata>=1.4
+Provides-Extra: dev
+Requires-Dist: black>=22.3.0; extra == "dev"
+Requires-Dist: flake8>=5.0.4; extra == "dev"
+Requires-Dist: pre-commit>=2.15.0; extra == "dev"
+Requires-Dist: graphviz>=0.20.1; extra == "dev"
+Provides-Extra: test
+Requires-Dist: mock; extra == "test"
+Requires-Dist: pytest>=7.3.1; extra == "test"
+Requires-Dist: pytest-cov>=4.1.0; extra == "test"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "test"
+Requires-Dist: pytest-timeout>=2.1.0; extra == "test"
+Requires-Dist: matplotlib>=2.0.0; extra == "test"
+
+MaxCompute MaxFrame Client
+==========================
+
+MaxFrame is a computational framework created by Alibaba Cloud to
+provide a way for Python developers to parallelize their code with
+MaxCompute. It creates a runnable computation graph locally, submits it
+to MaxCompute to execute and obtains results from MaxCompute.
+
+MaxFrame client is the client of MaxFrame. Currently it provides a
+DataFrame-based SDK with compatible APIs for pandas. In future, other
+common Python libraries like numpy and scikit-learn will be added as
+well. Python 3.7 is recommended for MaxFrame client to enable all
+functionalities while supports for higher Python versions are on the
+way.
+
+Installation
+------------
+
+You may install MaxFrame client through PIP:
+
+.. code:: bash
+
+   pip install maxframe
+
+Latest beta version can be installed with ``--pre`` argument:
+
+.. code:: bash
+
+   pip install --pre maxframe
+
+You can also install MaxFrame client from source code:
+
+.. code:: bash
+
+   pip install git+https://github.com/aliyun/alibabacloud-odps-maxframe-client.git
+
+Getting started
+---------------
+
+We show a simple code example of MaxFrame client which read data from a
+MaxCompute table, performs some simple data transform and writes back
+into MaxCompute.
+
+.. code:: python
+
+   import maxframe.dataframe as md
+   import os
+   from maxframe import new_session
+   from odps import ODPS
+
+   o = ODPS(
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
+       project='your-default-project',
+       endpoint='your-end-point',
+   )
+   session = new_session(o)
+
+   df = md.read_odps_table("source_table")
+   df["A"] = "prefix_" + df["A"]
+   md.to_odps_table(df, "prefix_source_table")
+
+Documentation
+-------------
+
+Detailed documentations can be found
+`here <https://maxframe.readthedocs.io>`__.
+
+License
+-------
+
+Licensed under the `Apache License
+2.0 <https://www.apache.org/licenses/LICENSE-2.0.html>`__.
+MaxCompute MaxFrame Client
+==========================
+
+MaxFrame is a computational framework created by Alibaba Cloud to
+provide a way for Python developers to parallelize their code with
+MaxCompute. It creates a runnable computation graph locally, submits it
+to MaxCompute to execute and obtains results from MaxCompute.
+
+MaxFrame client is the client of MaxFrame. Currently it provides a
+DataFrame-based SDK with compatible APIs for pandas. In future, other
+common Python libraries like numpy and scikit-learn will be added as
+well. Python 3.7 is recommended for MaxFrame client to enable all
+functionalities while supports for higher Python versions are on the
+way.
+
+Installation
+------------
+
+You may install MaxFrame client through PIP:
+
+.. code:: bash
+
+   pip install maxframe
+
+Latest beta version can be installed with ``--pre`` argument:
+
+.. code:: bash
+
+   pip install --pre maxframe
+
+You can also install MaxFrame client from source code:
+
+.. code:: bash
+
+   pip install git+https://github.com/aliyun/alibabacloud-odps-maxframe-client.git
+
+Getting started
+---------------
+
+We show a simple code example of MaxFrame client which read data from a
+MaxCompute table, performs some simple data transform and writes back
+into MaxCompute.
+
+.. code:: python
+
+   import maxframe.dataframe as md
+   import os
+   from maxframe import new_session
+   from odps import ODPS
+
+   o = ODPS(
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
+       project='your-default-project',
+       endpoint='your-end-point',
+   )
+   session = new_session(o)
+
+   df = md.read_odps_table("source_table")
+   df["A"] = "prefix_" + df["A"]
+   md.to_odps_table(df, "prefix_source_table")
+
+Documentation
+-------------
+
+Detailed documentations can be found
+`here <https://maxframe.readthedocs.io>`__.
+
+License
+-------
+
+Licensed under the `Apache License
+2.0 <https://www.apache.org/licenses/LICENSE-2.0.html>`__.

maxframe-1.0.0rc1/PKG-INFO → maxframe-1.0.0rc2/README.rst

@@ -1,10 +1,76 @@
-Metadata-Version: 2.1
-Name: maxframe
-Version: 1.0.0rc1
-Summary: MaxFrame operator-based data analyze framework
-Provides-Extra: dev
-Provides-Extra: test
+MaxCompute MaxFrame Client
+==========================
+
+MaxFrame is a computational framework created by Alibaba Cloud to
+provide a way for Python developers to parallelize their code with
+MaxCompute. It creates a runnable computation graph locally, submits it
+to MaxCompute to execute and obtains results from MaxCompute.
+
+MaxFrame client is the client of MaxFrame. Currently it provides a
+DataFrame-based SDK with compatible APIs for pandas. In future, other
+common Python libraries like numpy and scikit-learn will be added as
+well. Python 3.7 is recommended for MaxFrame client to enable all
+functionalities while supports for higher Python versions are on the
+way.
+
+Installation
+------------
+
+You may install MaxFrame client through PIP:
+
+.. code:: bash
+
+   pip install maxframe
+
+Latest beta version can be installed with ``--pre`` argument:
+
+.. code:: bash
+
+   pip install --pre maxframe
+
+You can also install MaxFrame client from source code:
+
+.. code:: bash
+
+   pip install git+https://github.com/aliyun/alibabacloud-odps-maxframe-client.git
+
+Getting started
+---------------
+
+We show a simple code example of MaxFrame client which read data from a
+MaxCompute table, performs some simple data transform and writes back
+into MaxCompute.
+
+.. code:: python
+
+   import maxframe.dataframe as md
+   import os
+   from maxframe import new_session
+   from odps import ODPS
+
+   o = ODPS(
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
+       os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
+       project='your-default-project',
+       endpoint='your-end-point',
+   )
+   session = new_session(o)
+
+   df = md.read_odps_table("source_table")
+   df["A"] = "prefix_" + df["A"]
+   md.to_odps_table(df, "prefix_source_table")
+
+Documentation
+-------------
 
+Detailed documentations can be found
+`here <https://maxframe.readthedocs.io>`__.
+
+License
+-------
+
+Licensed under the `Apache License
+2.0 <https://www.apache.org/licenses/LICENSE-2.0.html>`__.
 MaxCompute MaxFrame Client
 ==========================
 

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/codegen.py

@@ -205,12 +205,8 @@ class BigDagCodeContext(metaclass=abc.ABCMeta):
         return self._session_id
 
     def register_udf(self, udf: AbstractUDF):
-        from maxframe_framedriver.services.session import SessionManager
-
         udf.session_id = self._session_id
         self._udfs[udf.name] = udf
-        if self._session_id and SessionManager.initialized():
-            SessionManager.instance().register_udf(self._session_id, udf)
 
     def get_udfs(self) -> List[AbstractUDF]:
         return list(self._udfs.values())

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/config/config.py

@@ -19,6 +19,15 @@ import warnings
 from copy import deepcopy
 from typing import Any, Dict, Optional, Union
 
+from odps.lib import tzlocal
+
+try:
+    from zoneinfo import available_timezones
+except ImportError:
+    from pytz import all_timezones
+
+    available_timezones = lambda: all_timezones
+
 from ..utils import get_python_tag
 from .validators import (
     ValidatorType,
@@ -28,6 +37,7 @@ from .validators import (
     is_dict,
     is_in,
     is_integer,
+    is_non_negative_integer,
     is_null,
     is_numeric,
     is_string,
@@ -37,11 +47,12 @@ _DEFAULT_REDIRECT_WARN = "Option {source} has been replaced by {target} and migh
 _DEFAULT_MAX_ALIVE_SECONDS = 3 * 24 * 3600
 _DEFAULT_MAX_IDLE_SECONDS = 3600
 _DEFAULT_SPE_OPERATION_TIMEOUT_SECONDS = 120
+_DEFAULT_SPE_FAILURE_RETRY_TIMES = 5
 _DEFAULT_UPLOAD_BATCH_SIZE = 4096
 _DEFAULT_TEMP_LIFECYCLE = 1
 _DEFAULT_TASK_START_TIMEOUT = 60
 _DEFAULT_TASK_RESTART_TIMEOUT = 300
-_DEFAULT_LOGVIEW_HOURS = 24 * 60
+_DEFAULT_LOGVIEW_HOURS = 24 * 30
 
 
 class OptionError(Exception):
@@ -297,13 +308,28 @@ class Config:
         return {k: v for k, v in res.items() if k in self._remote_options}
 
 
+def _get_legal_local_tz_name() -> Optional[str]:
+    """Sometimes we may get illegal tz name from tzlocal.get_localzone()"""
+    tz_name = str(tzlocal.get_localzone())
+    if tz_name not in available_timezones():
+        return None
+    return tz_name
+
+
 default_options = Config()
 default_options.register_option(
     "execution_mode", "trigger", validator=is_in(["trigger", "eager"])
 )
+default_options.register_option("use_common_table", False, validator=is_bool)
 default_options.register_option(
     "python_tag", get_python_tag(), validator=is_string, remote=True
 )
+default_options.register_option(
+    "local_timezone",
+    _get_legal_local_tz_name(),
+    validator=any_validator(is_null, is_in(set(available_timezones()))),
+    remote=True,
+)
 default_options.register_option(
     "session.logview_hours", _DEFAULT_LOGVIEW_HOURS, validator=is_integer, remote=True
 )
@@ -378,7 +404,13 @@ default_options.register_option(
 default_options.register_option(
     "spe.operation_timeout_seconds",
     _DEFAULT_SPE_OPERATION_TIMEOUT_SECONDS,
-    validator=is_integer,
+    validator=is_non_negative_integer,
+    remote=True,
+)
+default_options.register_option(
+    "spe.failure_retry_times",
+    _DEFAULT_SPE_FAILURE_RETRY_TIMES,
+    validator=is_non_negative_integer,
     remote=True,
 )
 

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/config/validators.py

@@ -40,6 +40,7 @@ is_numeric = lambda x: isinstance(x, (int, float))
 is_string = lambda x: isinstance(x, str)
 is_dict = lambda x: isinstance(x, dict)
 is_positive_integer = lambda x: is_integer(x) and x > 0
+is_non_negative_integer = lambda x: is_integer(x) and x >= 0
 
 
 def is_in(vals):

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/core/entity/objects.py

@@ -23,7 +23,7 @@ class ObjectData(TileableData, _ToObjectMixin):
     __slots__ = ()
     type_name = "Object"
     # workaround for removed field since v0.1.0b5
-    # todo remove this when all versions below v0.1.0b5 is eliminated
+    # todo remove this when all versions below v1.0.0rc1 is eliminated
     _legacy_deprecated_non_primitives = ["_chunks"]
 
     def __init__(self, op=None, nsplits=None, **kw):

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/__init__.py

@@ -54,7 +54,7 @@ from .reduction import CustomReduction, unique
 from .tseries.to_datetime import to_datetime
 
 try:
-    from pandas import NA, Timestamp
+    from pandas import NA, NaT, Timestamp
 except ImportError:  # pragma: no cover
     pass
 

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/arithmetic/around.py

@@ -43,20 +43,20 @@ def around(df, decimals=0, *args, **kwargs):
     return op(df)
 
 
+# FIXME Series input of decimals not supported yet
 around.__frame_doc__ = """
 Round a DataFrame to a variable number of decimal places.
 
 Parameters
 ----------
-decimals : int, dict, Series
+decimals : int, dict
     Number of decimal places to round each column to. If an int is
     given, round each column to the same number of places.
     Otherwise dict and Series round to variable numbers of places.
     Column names should be in the keys if `decimals` is a
-    dict-like, or in the index if `decimals` is a Series. Any
-    columns not included in `decimals` will be left as is. Elements
-    of `decimals` which are not columns of the input will be
-    ignored.
+    dict-like. Any columns not included in `decimals` will be left
+    as is. Elements of `decimals` which are not columns of the
+    input will be ignored.
 *args
     Additional keywords have no effect but might be accepted for
     compatibility with numpy.
@@ -107,18 +107,6 @@ places as value
 1   0.0   1.0
 2   0.7   0.0
 3   0.2   0.0
-
-Using a Series, the number of places for specific columns can be
-specified with the column names as index and the number of
-decimal places as value
-
->>> decimals = md.Series([0, 1], index=['cats', 'dogs'])
->>> df.round(decimals).execute()
-    dogs  cats
-0   0.2   0.0
-1   0.0   1.0
-2   0.7   0.0
-3   0.2   0.0
 """
 around.__series_doc__ = """
 Round each value in a Series to the given number of decimals.

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/arithmetic/core.py

@@ -39,7 +39,7 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
         raise NotImplementedError
 
     @classmethod
-    def _calc_properties(cls, x1, x2=None, axis="columns"):
+    def _calc_properties(cls, x1, x2=None, axis="columns", level=None):
         if isinstance(x1, DATAFRAME_TYPE) and (
             x2 is None or pd.api.types.is_scalar(x2) or isinstance(x2, TENSOR_TYPE)
         ):
@@ -108,7 +108,9 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
                     index = copy.copy(x1.index_value)
                     index_shape = x1.shape[0]
                 else:
-                    index = infer_index_value(x1.index_value, x2.index_value)
+                    index = infer_index_value(
+                        x1.index_value, x2.index_value, level=level
+                    )
                     if index.key == x1.index_value.key == x2.index_value.key and (
                         not np.isnan(x1.shape[0]) or not np.isnan(x2.shape[0])
                     ):
@@ -141,7 +143,9 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
                         column_shape = len(dtypes)
                     else:  # pragma: no cover
                         dtypes = x1.dtypes  # FIXME
-                        columns = infer_index_value(x1.columns_value, x2.index_value)
+                        columns = infer_index_value(
+                            x1.columns_value, x2.index_value, level=level
+                        )
                         column_shape = np.nan
             else:
                 assert axis == "index" or axis == 0
@@ -169,7 +173,9 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
                                 ],
                                 index=x1.dtypes.index,
                             )
-                        index = infer_index_value(x1.index_value, x2.index_value)
+                        index = infer_index_value(
+                            x1.index_value, x2.index_value, level=level
+                        )
                         index_shape = np.nan
             return {
                 "shape": (index_shape, column_shape),
@@ -187,7 +193,9 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
                     index = copy.copy(x1.index_value)
                     index_shape = x1.shape[0]
                 else:
-                    index = infer_index_value(x1.index_value, x2.index_value)
+                    index = infer_index_value(
+                        x1.index_value, x2.index_value, level=level
+                    )
                     if index.key == x1.index_value.key == x2.index_value.key and (
                         not np.isnan(x1.shape[0]) or not np.isnan(x2.shape[0])
                     ):
@@ -237,14 +245,14 @@ class DataFrameBinOpMixin(DataFrameOperatorMixin):
         self._check_inputs(x1, x2)
         if isinstance(x1, DATAFRAME_TYPE) or isinstance(x2, DATAFRAME_TYPE):
             df1, df2 = (x1, x2) if isinstance(x1, DATAFRAME_TYPE) else (x2, x1)
-            kw = self._calc_properties(df1, df2, axis=self.axis)
+            kw = self._calc_properties(df1, df2, axis=self.axis, level=self.level)
             if not pd.api.types.is_scalar(df2):
                 return self.new_dataframe([x1, x2], **kw)
             else:
                 return self.new_dataframe([df1], **kw)
         if isinstance(x1, SERIES_TYPE) or isinstance(x2, SERIES_TYPE):
             s1, s2 = (x1, x2) if isinstance(x1, SERIES_TYPE) else (x2, x1)
-            kw = self._calc_properties(s1, s2)
+            kw = self._calc_properties(s1, s2, level=self.level)
             if not pd.api.types.is_scalar(s2):
                 return self.new_series([x1, x2], **kw)
             else:

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/arithmetic/docstring.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+# FIXME：https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/17
 _flex_doc_FRAME = """
 Get {desc} of dataframe and other, element-wise (binary operator `{op_name}`).
 Equivalent to ``{equiv}``, but with support to substitute a fill_value
@@ -127,44 +128,15 @@ circle          0
 triangle        3
 rectangle       4
 
->>> (df * other).execute()
-           angles  degrees
-circle          0      NaN
-triangle        9      NaN
-rectangle      16      NaN
-
 >>> df.mul(other, fill_value=0).execute()
            angles  degrees
 circle          0      0.0
 triangle        9      0.0
 rectangle      16      0.0
 
-Divide by a MultiIndex by level.
-
->>> df_multindex = md.DataFrame({{'angles': [0, 3, 4, 4, 5, 6],
-...                              'degrees': [360, 180, 360, 360, 540, 720]}},
-...                             index=[['A', 'A', 'A', 'B', 'B', 'B'],
-...                                    ['circle', 'triangle', 'rectangle',
-...                                     'square', 'pentagon', 'hexagon']])
->>> df_multindex.execute()
-             angles  degrees
-A circle          0      360
-  triangle        3      180
-  rectangle       4      360
-B square          4      360
-  pentagon        5      540
-  hexagon         6      720
-
->>> df.div(df_multindex, level=1, fill_value=0).execute()
-             angles  degrees
-A circle        NaN      1.0
-  triangle      1.0      1.0
-  rectangle     1.0      1.0
-B square        0.0      0.0
-  pentagon      0.0      0.0
-  hexagon       0.0      0.0
 """
 
+# FIXME：https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/28
 _flex_doc_SERIES = """
 Return {desc} of series and other, element-wise (binary operator `{op_name}`).
 
@@ -213,6 +185,7 @@ e    NaN
 dtype: float64
 """
 
+# FIXME: https://github.com/aliyun/alibabacloud-odps-maxframe-client/issues/48
 _flex_comp_doc_FRAME = """
 Get {desc} of dataframe and other, element-wise (binary operator `{op_name}`).
 Among flexible wrappers (`eq`, `ne`, `le`, `lt`, `ge`, `gt`) to comparison
@@ -257,7 +230,8 @@ Mismatched indices will be unioned together.
 
 Examples
 --------
->>> df = pd.DataFrame({{'cost': [250, 150, 100],
+>>> import maxframe.dataframe as md
+>>> df = md.DataFrame({{'cost': [250, 150, 100],
 ...                    'revenue': [100, 250, 300]}},
 ...                   index=['A', 'B', 'C'])
 >>> df.execute()
@@ -332,30 +306,6 @@ A  False    False
 B  False    False
 C  False     True
 D  False    False
-
-Compare to a MultiIndex by level.
-
->>> df_multindex = pd.DataFrame({{'cost': [250, 150, 100, 150, 300, 220],
-...                              'revenue': [100, 250, 300, 200, 175, 225]}},
-...                             index=[['Q1', 'Q1', 'Q1', 'Q2', 'Q2', 'Q2'],
-...                                    ['A', 'B', 'C', 'A', 'B', 'C']])
->>> df_multindex.execute()
-      cost  revenue
-Q1 A   250      100
-   B   150      250
-   C   100      300
-Q2 A   150      200
-   B   300      175
-   C   220      225
-
->>> df.le(df_multindex, level=1).execute()
-       cost  revenue
-Q1 A   True     True
-   B   True     True
-   C   True     True
-Q2 A  False     True
-   B   True    False
-   C   True    False
 """
 
 

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/core.py

@@ -1086,11 +1086,11 @@ class Series(HasShapeTileable, _ToPandasMixin):
         --------
         >>> import maxframe.dataframe as md
         >>> s = md.Series({'a': 1, 'b': 2, 'c': 3})
-        >>> s.ndim.execute()
+        >>> s.ndim
         1
 
         >>> df = md.DataFrame({'col1': [1, 2], 'col2': [3, 4]})
-        >>> df.ndim.execute()
+        >>> df.ndim
         2
         """
         return super().ndim
@@ -1520,7 +1520,7 @@ class BaseDataFrameData(HasShapeTileableData, _ToPandasMixin):
         self._columns_value = parse_index(dtypes.index, store_data=True)
         self._dtypes_value = DtypesValue(key=tokenize(dtypes), value=dtypes)
         new_shape = list(self._shape)
-        new_shape[0] = len(dtypes)
+        new_shape[-1] = len(dtypes)
         self._shape = tuple(new_shape)
 
     @property
@@ -1761,11 +1761,11 @@ class DataFrame(HasShapeTileable, _ToPandasMixin):
         --------
         >>> import maxframe.dataframe as md
         >>> s = md.Series({'a': 1, 'b': 2, 'c': 3})
-        >>> s.ndim.execute()
+        >>> s.ndim
         1
 
         >>> df = md.DataFrame({'col1': [1, 2], 'col2': [3, 4]})
-        >>> df.ndim.execute()
+        >>> df.ndim
         2
         """
         return super().ndim

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/datasource/date_range.py

@@ -22,7 +22,7 @@ from pandas._libs.tslibs import timezones
 from pandas.tseries.frequencies import to_offset
 from pandas.tseries.offsets import Tick
 
-from ... import opcodes as OperandDef
+from ... import opcodes
 from ...core import OutputType
 from ...serialization.serializables import AnyField, BoolField, Int64Field, StringField
 from ...utils import no_default, pd_release_version
@@ -117,7 +117,7 @@ def generate_range_count(
 
 
 class DataFrameDateRange(DataFrameOperator, DataFrameOperatorMixin):
-    _op_type_ = OperandDef.DATE_RANGE
+    _op_type_ = opcodes.DATE_RANGE
 
     start = AnyField("start")
     end = AnyField("end")

{maxframe-1.0.0rc1 → maxframe-1.0.0rc2}/maxframe/dataframe/datasource/read_odps_query.py

@@ -47,6 +47,7 @@ _EXPLAIN_TASK_SCHEMA_REGEX = re.compile(
     re.MULTILINE,
 )
 _EXPLAIN_COLUMN_REGEX = re.compile(r"([^\(]+) \(([^)]+)\)(?:| AS ([^ ]+))(?:\n|$)")
+_ANONYMOUS_COL_REGEX = re.compile(r"^_c\d+$")
 
 
 @dataclasses.dataclass
@@ -272,6 +273,11 @@ def read_odps_query(
     explain_str = list(inst.get_task_results().values())[0]
 
     odps_schema = _parse_explained_schema(explain_str)
+
+    for col in odps_schema.columns:
+        if _ANONYMOUS_COL_REGEX.match(col.name) and col.name not in query:
+            raise ValueError("Need to specify names for all columns in SELECT clause.")
+
     dtypes = odps_schema_to_pandas_dtypes(odps_schema)
 
     if not index_col: