maxframe 1.2.0__cp311-cp311-macosx_10_9_x86_64.whl → 1.2.1__cp311-cp311-macosx_10_9_x86_64.whl

maxframe/dataframe/datasource/read_odps_query.py

@@ -262,7 +262,7 @@ class DataFrameReadODPSQuery(
     column_renames = DictField("column_renames", default=None)
 
     def get_columns(self):
-        return self.columns
+        return self.columns or list(self.dtypes.index)
 
     def set_pruned_columns(self, columns, *, keep_order=None):  # pragma: no cover
         self.columns = columns

maxframe/dataframe/datasource/tests/test_datasource.py

@@ -364,6 +364,7 @@ def test_from_odps_query():
             index=["col1", "col2", "col3"],
         ),
     )
+    assert df.op.get_columns() == ["col1", "col2", "col3"]
 
     df = read_odps_query(query1, skip_schema=True)
     assert df.dtypes is None
@@ -373,6 +374,7 @@ def test_from_odps_query():
     df = read_odps_query(query1, index_col="col1")
     assert df.op.query == query1
     assert df.index_value.name == "col1"
+    assert df.op.get_columns() == ["col2", "col3"]
     assert isinstance(df.index_value.value, IndexValue.Index)
     pd.testing.assert_series_equal(
         df.dtypes,
@@ -389,6 +391,7 @@ def test_from_odps_query():
     df = read_odps_query(query2, index_col=["col1", "col2"])
     assert df.op.query == query2
     assert df.index_value.names == ["col1", "col2"]
+    assert df.op.get_columns() == ["c31", "c32"]
     assert isinstance(df.index_value.value, IndexValue.MultiIndex)
     pd.testing.assert_series_equal(
         df.dtypes,
@@ -405,6 +408,7 @@ def test_from_odps_query():
     assert df.op.query == query3
     assert df.op.extra_params.no_split_sql is False
     assert df.index_value.names == ["c1"]
+    assert df.op.get_columns() == ["c32"]
     pd.testing.assert_series_equal(
         df.dtypes,
         pd.Series([np.dtype("float64")], index=["c32"]),

maxframe/lib/dtypes_extension/__init__.py

@@ -11,4 +11,4 @@
 # 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 .dtypes import ArrowDtype, dict_, infer_arrow_dtype, is_map_dtype
+from .dtypes import ArrowDtype, dict_, is_map_dtype

maxframe/lib/dtypes_extension/dtypes.py

@@ -13,10 +13,8 @@
 # limitations under the License.
 from typing import Union
 
-import numpy as np
 import pandas as pd
 import pyarrow as pa
-from pandas.api.extensions import ExtensionDtype
 
 try:
     from pandas import ArrowDtype
@@ -45,47 +43,3 @@ def is_map_dtype(dtype: ArrowDtype) -> bool:
     if ArrowDtype is None:
         raise ImportError("ArrowDtype is not supported in current environment")
     return isinstance(dtype, ArrowDtype) and isinstance(dtype.pyarrow_dtype, pa.MapType)
-
-
-_dtype_mapping = {
-    pd.Int8Dtype(): lambda x: pa.int8(),
-    pd.Int16Dtype(): lambda x: pa.int16(),
-    pd.Int32Dtype(): lambda x: pa.int32(),
-    pd.Int64Dtype(): lambda x: pa.int64(),
-    pd.UInt8Dtype(): lambda x: pa.uint8(),
-    pd.UInt16Dtype(): lambda x: pa.uint16(),
-    pd.UInt32Dtype(): lambda x: pa.uint32(),
-    pd.UInt64Dtype(): lambda x: pa.uint64(),
-    pd.BooleanDtype(): lambda x: pa.bool_(),
-    pd.Float32Dtype(): lambda x: pa.float32(),
-    pd.Float64Dtype(): lambda x: pa.float64(),
-    pd.StringDtype(): lambda x: pa.string(),
-}
-
-
-def infer_arrow_dtype(
-    dtype: Union[np.dtype, pa.DataType, ExtensionDtype]
-) -> Union[ArrowDtype, ExtensionDtype]:
-    """
-    Convert any pandas accepted dtype to arrow type in a best effort way.
-
-    Parameters
-    ----------
-    dtype : Union[np.dtype, pa.DataType, ExtensionDtype]
-        The dtype instance, can be np.dtype, pa.DataType or ExtensionDtype
-
-    Returns
-    -------
-    Union[pd.ArrowDtype, ExtensionDtype]: The converted pd.ArrowDtype, or ExtensionDtype if conversion failed.
-    """
-    if isinstance(dtype, ArrowDtype):
-        return dtype
-
-    if isinstance(dtype, np.dtype):
-        return ArrowDtype(pa.from_numpy_dtype(dtype))
-    if isinstance(dtype, pd.DatetimeTZDtype):
-        return pa.timestamp(dtype.unit, dtype.tz)
-
-    if dtype in _dtype_mapping:
-        return ArrowDtype(_dtype_mapping[dtype](dtype))
-    return dtype

maxframe/lib/dtypes_extension/tests/test_dtypes.py

@@ -12,13 +12,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import numpy as np
 import pandas as pd
 import pyarrow as pa
 import pytest
 
 from ....utils import ARROW_DTYPE_NOT_SUPPORTED
-from ..dtypes import dict_, infer_arrow_dtype, is_map_dtype
+from ..dtypes import dict_, is_map_dtype
 
 try:
     from pandas import ArrowDtype
@@ -37,32 +36,3 @@ def test_map_dtype():
     dt = pd.ArrowDtype(pa.list_(pa.int64()))
     assert not is_map_dtype(dt)
     assert not is_map_dtype(pd.Int64Dtype)
-
-
-@pytest.mark.skipif(
-    ARROW_DTYPE_NOT_SUPPORTED,
-    reason="pandas doesn't support ArrowDtype",
-)
-@pytest.mark.parametrize(
-    "input_dtype, expected_type, expected_pa_dtype",
-    [
-        (
-            ArrowDtype(pa.int64()) if ArrowDtype else None,
-            ArrowDtype,
-            pa.int64(),
-        ),  # pd.ArrowDtype
-        (np.dtype("int64"), ArrowDtype, pa.int64()),  # np.dtype
-        (pd.CategoricalDtype(), pd.CategoricalDtype, None),  # pa.DataType
-        (pd.Int64Dtype(), ArrowDtype, pa.int64()),  # pd.ExtensionDtype
-        (
-            pd.DatetimeTZDtype("ns", "Asia/Shanghai"),
-            pa.TimestampType,
-            pa.timestamp("ns", "Asia/Shanghai"),
-        ),
-    ],
-)
-def test_infer_arrow_dtype(input_dtype, expected_type, expected_pa_dtype):
-    result = infer_arrow_dtype(input_dtype)
-    assert isinstance(result, expected_type)
-    if expected_type == ArrowDtype:
-        assert result.pyarrow_dtype == expected_pa_dtype

{maxframe-1.2.0.dist-info → maxframe-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: maxframe
-Version: 1.2.0
+Version: 1.2.1
 Summary: MaxFrame operator-based data analyze framework
 Requires-Dist: numpy<2.0.0,>=1.19.0
 Requires-Dist: pandas>=1.0.0

{maxframe-1.2.0.dist-info → maxframe-1.2.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
-maxframe-1.2.0.dist-info/RECORD,,
-maxframe-1.2.0.dist-info/WHEEL,sha256=rRBe8gNEhotozzxgrO95hZ3LAl74f9an5Xo4YRYFmgA,110
-maxframe-1.2.0.dist-info/top_level.txt,sha256=64x-fc2q59c_vXwNUkehyjF1vb8JWqFSdYmUqIFqoTM,31
-maxframe-1.2.0.dist-info/METADATA,sha256=PjQFUBd0dAx18iad3K42kn8KOfV2UpIVSLyaE3A7Rlo,3043
+maxframe-1.2.1.dist-info/RECORD,,
+maxframe-1.2.1.dist-info/WHEEL,sha256=rRBe8gNEhotozzxgrO95hZ3LAl74f9an5Xo4YRYFmgA,110
+maxframe-1.2.1.dist-info/top_level.txt,sha256=64x-fc2q59c_vXwNUkehyjF1vb8JWqFSdYmUqIFqoTM,31
+maxframe-1.2.1.dist-info/METADATA,sha256=ski2284d_beMcw3qHjoS9U9jnovYKyzNw40qYZ9rX0Q,3043
 maxframe_client/conftest.py,sha256=JkQKlLZqd9uJekiO8HvMvEegidF-6KlCVFcg-KmQLLY,643
 maxframe_client/__init__.py,sha256=z4QT02esANpxtSVZPO_96693bqSvhG82e4suaD6Ll1E,689
 maxframe_client/fetcher.py,sha256=9zIq_mNGlk8DcTVH0f1-dgNmH72X0edRM9a8muwko6Y,9172
@@ -19,7 +19,7 @@ maxframe_client/session/tests/test_task.py,sha256=o0I10u6oX8e6vLt35xxxvZfcpb6F3o
 maxframe_client/session/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
 maxframe/_utils.pyx,sha256=v1fcebb-o5Hee2xzMBMKLIXV9NHThYrS3SND6Sik24U,17017
 maxframe/conftest.py,sha256=Jr7kv1m7VfJaDlfUW9pTKTfa9m9pkW_3jwNdmqB0zt4,6293
-maxframe/_utils.cpython-311-darwin.so,sha256=iQZP3nduFY0uOVbEx9CpYKokOlGQptNYCz_Bnw2QnWw,415312
+maxframe/_utils.cpython-311-darwin.so,sha256=DGZXoGwThplp7XO55kFQyGBh1gub0pLbCJpx7oVGo0Y,415312
 maxframe/opcodes.py,sha256=mL1_p_2Qofwl-9aZw52dsUciPab41O_A-dN6_NUsDz0,10487
 maxframe/env.py,sha256=9sJWTeOWuP6KRRYEejJgYa4FoZyAeSuXFd_A8_xl6YM,1402
 maxframe/mixin.py,sha256=FnjS9bFlcg6LV8L62pyTVF29qgSJupFn9DZv8cv6MiI,3524
@@ -81,14 +81,14 @@ maxframe/dataframe/datasource/from_index.py,sha256=c7jX1Vq4C4ZOXiL3MbRayJ3Jl0JEA
 maxframe/dataframe/datasource/dataframe.py,sha256=-V8qjEhRwaFeOYeFzjf8h5A1gqpgH_-GbNCf4Au7VRM,2023
 maxframe/dataframe/datasource/series.py,sha256=Sou6J9hg3JJdSxuTcJjsD5EWPmvVB1J5I_ys24IkBe4,1909
 maxframe/dataframe/datasource/__init__.py,sha256=LaVpAg_oMJ2OofTlyjw-v9YLRQNfPQYHNVkWnCXPRCc,640
-maxframe/dataframe/datasource/read_odps_query.py,sha256=nXz-wROVmmFCP-Axfy5M8y-gGHiAWflw0NKy1aXlOe8,14621
+maxframe/dataframe/datasource/read_odps_query.py,sha256=bpwKPQOoMLWJ8D5F44rBZAvU7CDkyQ5CXH72BkX80e0,14648
 maxframe/dataframe/datasource/core.py,sha256=W9AMhDsmlp4jl4T4iBsqTlMsdLNPCjcJbTi7SivsiFU,2687
 maxframe/dataframe/datasource/date_range.py,sha256=TNfvRWgfwkpIhm52RbMZDxvBAdbWbbwGAUnbwFJRRAE,17227
 maxframe/dataframe/datasource/read_odps_table.py,sha256=P-m8aqFCG3avt2MzpAReAiCewoT9H_VLrtjF7y7fMwA,9409
 maxframe/dataframe/datasource/read_parquet.py,sha256=Pk3c1eQ0l8pJdhhvE7jfPI2IG933OZv8_k4e72ULEx0,14531
 maxframe/dataframe/datasource/from_tensor.py,sha256=GrBxy0e-Vng640Z9kWnyshGsI9vkkmyowkRQvwDGsWs,14727
 maxframe/dataframe/datasource/from_records.py,sha256=VB4rO5evF1_EUN6_GJq3xHrsvFxInW1TZH1AvtzPAis,3442
-maxframe/dataframe/datasource/tests/test_datasource.py,sha256=q9Oao7HMoTJhvlhAeMkaUihSofWyvj0I4yFQEOPgE00,18576
+maxframe/dataframe/datasource/tests/test_datasource.py,sha256=bpIS9Kz5tM2HPO5yIh_ztiWjFbgU5x4n50xuuXekiWw,18777
 maxframe/dataframe/datasource/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
 maxframe/dataframe/sort/sort_index.py,sha256=gmv55CmKkAsWrA9bWf45JfX8IvMc0FuFloqb6D3cziI,5412
 maxframe/dataframe/sort/__init__.py,sha256=E76aFGW1nejyX-_YV4AXlbl3vj0gSANgif5kbrmMWL4,1160
@@ -324,7 +324,7 @@ maxframe/core/entity/objects.py,sha256=XgeJHAFg9CT3i76kUkxiAhn0hByNLCo1Jr8C_CFC5
 maxframe/core/entity/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
 maxframe/core/entity/tests/test_objects.py,sha256=o0_ntvlp1u3eObNwf-WpomK-AeZcIbdUf3CGit1K1Es,1349
 maxframe/core/graph/__init__.py,sha256=qlKFvg4JNTmNOOvidxwOQOZofw5WePSWphkYpZ7hVoc,765
-maxframe/core/graph/core.cpython-311-darwin.so,sha256=PFrL4EGT5lnlrFV38W68mZZzVs3Q8q0apFcEYzl9aOE,321272
+maxframe/core/graph/core.cpython-311-darwin.so,sha256=dUpV_U5uV7gIfULRcQydX33RJqg9A7_V9cIVUlPlS4E,321272
 maxframe/core/graph/entity.py,sha256=feXajqZBbPTsZID8FcRzhDCll3LW-S5Lf3UGObSA_fw,4863
 maxframe/core/graph/core.pyx,sha256=trOWJOlAn1bwMuErZwugqGXO1loCuhLBupYBxxmlHaI,15923
 maxframe/core/graph/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
@@ -359,7 +359,7 @@ maxframe/serialization/__init__.py,sha256=psw8R-cCgEO7f5TB0ivKQHQcSYGmVZhdX62qGd
 maxframe/serialization/maxframe_objects.py,sha256=Ha2pFpBivutH_YES1EQN-zpWu3TbKtotJHiuc8Cs8S8,1365
 maxframe/serialization/numpy.py,sha256=i6t8mI_pe34QQMxTEH23DrvPisRP6KxE2qLQ99MwjNI,3213
 maxframe/serialization/scipy.py,sha256=W4P_r-4tAGGfVAFhwqcaHBxdW-dpZ6rIMLuppQzMXjo,2427
-maxframe/serialization/core.cpython-311-darwin.so,sha256=6gjlMFAk9qDzxN7gDEFeNL0h5flWfg4Aq0tVLKjouc0,617112
+maxframe/serialization/core.cpython-311-darwin.so,sha256=afxBBhrbCdnBNHseI31lUasezcuH6qC5qhyQ9l5rCCQ,617112
 maxframe/serialization/core.pyx,sha256=9xb7LsnSZiaNGpkx61OWeVUyCHyL0u8xDmzvOLgqyP8,35945
 maxframe/serialization/tests/test_serial.py,sha256=fsn5h9628eN-S3tPjzyhGtZtx_TEmTUdcNNJs-dSXXc,13163
 maxframe/serialization/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
@@ -396,7 +396,7 @@ maxframe/lib/version.py,sha256=krhgFvMhLdoNCJk3d9U-yyIAHixCR4S9-NggKdqrnHQ,18321
 maxframe/lib/compression.py,sha256=QPxWRp0Q2q33EQzY-Jfx_iz7SELax6fu3GTmyIVyjGY,1442
 maxframe/lib/__init__.py,sha256=spk1N3D3EL-0RyJDNlnwqHfQEW47lXL-rNDukcF6qlk,642
 maxframe/lib/mmh3.pyi,sha256=R_MzTIyUSTn8TF4Gs2hRP7NSWfWi0SeuUauh4eZJc-g,1494
-maxframe/lib/mmh3.cpython-311-darwin.so,sha256=hdAvoFDjMcInK3MfvtuwgIfdDvNd6JHTCtS4CxaG6rA,37256
+maxframe/lib/mmh3.cpython-311-darwin.so,sha256=Rhr0Wq_nD7DQ2CtzPL3ZVzJp84OCVKWZNQCC78XssSE,37256
 maxframe/lib/functools_compat.py,sha256=c3gOw--FLvQNbamt0V8oqsTNRhPlASPEOzhMrzA2was,2616
 maxframe/lib/mmh3_src/mmh3module.cpp,sha256=9J9eA42eKWTl546fvfQPNuIM3B2jpWSADpgIw3tr2jg,11604
 maxframe/lib/mmh3_src/MurmurHash3.h,sha256=lg5uXUFyMBge2BWRn0FgrqaCFCMfDWoTXD4PQtjHrMA,1263
@@ -431,10 +431,10 @@ maxframe/lib/filesystem/_oss_lib/handle.py,sha256=EqXngu4ScEvEzWoVhk8SdcFHVd3eth
 maxframe/lib/filesystem/_oss_lib/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
 maxframe/lib/filesystem/_oss_lib/glob.py,sha256=ZAOPflY2zomCM7fKkrhG9qdULoyhHliBmbbmFaPvCKM,4837
 maxframe/lib/filesystem/_oss_lib/common.py,sha256=zbhcqv_UKLHmk9cPT7T_9i43Uf2iz1DH_Uis8DJPOfs,6615
-maxframe/lib/dtypes_extension/__init__.py,sha256=jfQ-njtVH6QSBqWeane16jm0KqOXjIQ7_MwXh9Pr5ew,667
-maxframe/lib/dtypes_extension/dtypes.py,sha256=1vOMTMj8RRcjZw44cL4XtVUs--i64QdVzmu-V5K82r8,3019
+maxframe/lib/dtypes_extension/__init__.py,sha256=vDReFX8FP-k9sqHKkFdV58KUfR-Rf5KnUB1fX9qY62M,648
+maxframe/lib/dtypes_extension/dtypes.py,sha256=9TGEqLqAbVwyfujyLYG5Sk3jF28qxlkDfweFB-eHpa8,1534
 maxframe/lib/dtypes_extension/tests/__init__.py,sha256=YsJxv7HbG4YYJmqAJZPYb8iHFRQX5JGpGn2PInDXvY8,596
-maxframe/lib/dtypes_extension/tests/test_dtypes.py,sha256=YryIHQBTeeaMTB-m17PDH9FeUr8Sf1XXKBzyjeCT1a8,2133
+maxframe/lib/dtypes_extension/tests/test_dtypes.py,sha256=qr73aCmmIJo-UlawSrCz6o_LkY8nfHgGRBwz8gNgfFA,1127
 maxframe/lib/sparse/matrix.py,sha256=EjPVR8s8DgXnE7mMqAyZngNbFhobrrMbZLSYGHYzTVY,7154
 maxframe/lib/sparse/vector.py,sha256=a7q1uMWlF8rs_2lNYvWzFmpWsnOlF_FjWAsPjIUutk4,4809
 maxframe/lib/sparse/__init__.py,sha256=V2akd93BuaxrSMURjikfbOmlCD5C_wyzkuwqfvzaYlM,18058