maxframe 1.2.0__cp38-cp38-win_amd64.whl → 1.2.1__cp38-cp38-win_amd64.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: 2.1
 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

@@ -1,5 +1,5 @@
 maxframe/__init__.py,sha256=6Y3yW67GtpKOGqMC1prt4yxqUTc0twHA3yjMEH-5WTw,1036
-maxframe/_utils.cp38-win_amd64.pyd,sha256=DKWajJzJdM-FwJGYuUg_Uh1PHBUiOJ__MHKwZcL-S3I,308736
+maxframe/_utils.cp38-win_amd64.pyd,sha256=fEOuuP0AThCNtAqPbAp5UFAm2cu4zv9bVzcKzyPvCyA,308736
 maxframe/_utils.pxd,sha256=ckEN1J8rXAtNYW7CictnSVYamH-sQx-uIuWrQts_OT4,1187
 maxframe/_utils.pyx,sha256=oOBAUIaOM0mkKY_dzymY75Vit8bW64vbFrtwzqQpUA8,17564
 maxframe/codegen.py,sha256=H4daLJbkmFxdwgDBcvRTXE51VynKzaMDlwCM810BLZw,18858
@@ -34,7 +34,7 @@ maxframe/core/entity/utils.py,sha256=Cx7bfNQTbYZjAxNP-1AXjBozZ1mGqJ1KCz7rwDlxn6w
 maxframe/core/entity/tests/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oci5W5Y,609
 maxframe/core/entity/tests/test_objects.py,sha256=UwJTYFSUr61E255tPrGwnJlhHDGlkpSugFk0kRsJG8Q,1392
 maxframe/core/graph/__init__.py,sha256=h7zLVFfnmRPrzaiO7zbuOTMZ0iSNZN5TaD5fB7vuxxA,782
-maxframe/core/graph/core.cp38-win_amd64.pyd,sha256=SlNeuKE6E2l29ZzSHMmzM1N7Ud0bBJUX5GmhR1vSoU8,252416
+maxframe/core/graph/core.cp38-win_amd64.pyd,sha256=Who1ZZaheeZYMRyk9stZ4RymXwriNj3MCmzslPiZPwI,252416
 maxframe/core/graph/core.pyx,sha256=DJ3RV_5W1lNDRj113ewpSLosiiHCqXYQNuPVR5mBaVU,16390
 maxframe/core/graph/entity.py,sha256=zfijVHeCTOJynagcPSEBEIi194mjMwXcW9p4jopwoZ8,5010
 maxframe/core/graph/builder/__init__.py,sha256=NjIcWQ1ZtEbRJalz8XH1UKaQLpsvOqouRPeRBaul5cA,655
@@ -143,12 +143,12 @@ maxframe/dataframe/datasource/from_records.py,sha256=5PWL2uGCwdoOjGzpL52O7Yg_mNB
 maxframe/dataframe/datasource/from_tensor.py,sha256=kd59E9xEaLzOdsOennQyDkfJlS6eg26gjfn_VrqfdTs,15146
 maxframe/dataframe/datasource/index.py,sha256=LUOaSY3jScY65h4TSryXMfQJGdUWWXmnoS1IP9ah5aw,4518
 maxframe/dataframe/datasource/read_csv.py,sha256=RyjHDs5eVzti9G6HgHm61QgqvqC8XN1opMTT_98YywE,24668
-maxframe/dataframe/datasource/read_odps_query.py,sha256=mwimNXzA0cihS8HIiCwaiTk3pQJmVa4jWQFu-1eOP-Q,15044
+maxframe/dataframe/datasource/read_odps_query.py,sha256=xk7KDrD3rz-j-wHK_oX81fR8rwLmYz2qpZApoA8qD_I,15071
 maxframe/dataframe/datasource/read_odps_table.py,sha256=GztSJFV-vQl20mleqCMWGhMd0tXJ1mSMDm2kI89KS7g,9667
 maxframe/dataframe/datasource/read_parquet.py,sha256=dt1PE06wfvnbXxQXWXxVe69jBClIP3bDz6OnkjfVjfE,14952
 maxframe/dataframe/datasource/series.py,sha256=9GmE-UVQ_eeFI53UuWiF6rQSqQ1mp4RkBVRWIhKNw2k,1964
 maxframe/dataframe/datasource/tests/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oci5W5Y,609
-maxframe/dataframe/datasource/tests/test_datasource.py,sha256=FEtjUGk6SS2YABxed4w9GWN-SoQu0Gzynh76zIVdYMk,19119
+maxframe/dataframe/datasource/tests/test_datasource.py,sha256=8Dq5EJOmyfH9YqErP-6i39R-MeOj-bf97so1iGcRfLU,19324
 maxframe/dataframe/datastore/__init__.py,sha256=KbGUgDoSvqGe_6Jm89Mh3KxU2N4mmMrn4prA4Jk933g,810
 maxframe/dataframe/datastore/core.py,sha256=uNAcFyUgjn_LxUHk7IjqRlAWNeru77Ub-dZ15M5WDjA,762
 maxframe/dataframe/datastore/to_csv.py,sha256=gWPz0fcKmJA-2cyDJDhbL9C_CSOq79GTNHq9-qAkkek,7974
@@ -350,7 +350,7 @@ maxframe/learn/utils/core.py,sha256=JmuEV8O_tEXI-nBwRK2j1CPYSFlJJyrFhYh83df29L4,
 maxframe/lib/__init__.py,sha256=ZxIRETECrnrJcfRmGQTTNwrCxwqTVLNaM9nCzBNPo1k,657
 maxframe/lib/compression.py,sha256=8F0QEOlrgrFz8Yzeyap4ud3PYe1I5LUWUHWvQg1YKq0,1497
 maxframe/lib/functools_compat.py,sha256=1a-R_fcKQo7gUZnyk6L-qt_Ozhm3Gb0y86Fd3ROeTcw,2697
-maxframe/lib/mmh3.cp38-win_amd64.pyd,sha256=_bsvt4jJGTE-48yjhBR9OVGzIgAojtQGVzEe5PlQ0R4,17920
+maxframe/lib/mmh3.cp38-win_amd64.pyd,sha256=EOzfdtzO9cBqzWovBVCfTQnY8fwf2fwD5UCeESeP3Fo,17920
 maxframe/lib/mmh3.pyi,sha256=ad6KZrDA7dznE5Qv0lnGB32rw1Zl2DBwNIH0BI_bFQU,1537
 maxframe/lib/version.py,sha256=NqxzCX2pLHIMTj-7HTA6xU3iyd_DVeqyyW1n-Rk8MCQ,18941
 maxframe/lib/wrapped_pickle.py,sha256=Yazeydh6vOAd4ibsv_tn_8LgAC7kVkoResQYFW8RXNw,3976
@@ -366,10 +366,10 @@ maxframe/lib/aio/tests/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oc
 maxframe/lib/aio/tests/test_aio_file.py,sha256=WnU2jQMZ1jVPT8l9m3h4lytLUDhAHTIa9_mTMHpo224,1713
 maxframe/lib/cython/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oci5W5Y,609
 maxframe/lib/cython/libcpp.pxd,sha256=lNA9YvEGLS0xMarsmvllh2qMdPxu-_Tl2ymT2EQw14c,1130
-maxframe/lib/dtypes_extension/__init__.py,sha256=IiNUhMYa_fWIEyjOyemyUMevbEiN19re1b8hh8ZXNZo,681
-maxframe/lib/dtypes_extension/dtypes.py,sha256=Qs5hu-kJSexioMuPOpQleMr5M4Hc_RV-51RAMykaKO4,3110
+maxframe/lib/dtypes_extension/__init__.py,sha256=F2HSAnbE502wzvJZDiiTTB-m7cByZwrT7CaB8BX0GJM,662
+maxframe/lib/dtypes_extension/dtypes.py,sha256=mPtU8uoazTC-0ar-w1MQ0MIVTy6eNLR2MR5bocFrVQw,1579
 maxframe/lib/dtypes_extension/tests/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oci5W5Y,609
-maxframe/lib/dtypes_extension/tests/test_dtypes.py,sha256=ik77K1dQhYXpq_qpz0qBYKkzScrB41h06LHqMs2BnxM,2201
+maxframe/lib/dtypes_extension/tests/test_dtypes.py,sha256=dWJTqACn_tzsrZ4jWp3X7_gn0viIg38Kcbl-osTIq48,1165
 maxframe/lib/filesystem/__init__.py,sha256=1LjZ5ZPdXZHKaJ5TZY34dnoLgYMy1qiB3DcE5k9YjaU,855
 maxframe/lib/filesystem/_glob.py,sha256=H1wRnnhFAK6PqshJf6ALo0jxVZ9em1zhi3d9Q5rXpLk,6708
 maxframe/lib/filesystem/arrow.py,sha256=QKH1gtjx-0jUyBNMKBF0nLJZCKuOwDIGko8biBBgQkQ,8647
@@ -408,7 +408,7 @@ maxframe/remote/core.py,sha256=4K33fOPX6f1v_c1yZ7Z9MRICHtmwkqbiuujfwplZicw,6733
 maxframe/remote/run_script.py,sha256=mibruTktWFh62ye9AtjKG7UG7g3_ZLxmXWLWCWY0le8,3677
 maxframe/serialization/__init__.py,sha256=0naXxktD3hjxZBVvV_mnvslPL5Azu4SeoW7KkFy4sbE,963
 maxframe/serialization/arrow.py,sha256=DUq7e9V8kJrpj_Z67F767jo_wxgkkXygSPByzMqfB4M,3513
-maxframe/serialization/core.cp38-win_amd64.pyd,sha256=AVL95f7xVvLNHh-gL2UVxl5QiKV9AYFvxBkiH178nzQ,416768
+maxframe/serialization/core.cp38-win_amd64.pyd,sha256=tmGIcmw4Q06kE0-_HmMCu3jfWUlgFo4EkqTJ5NNs6cI,416768
 maxframe/serialization/core.pxd,sha256=tFsBg4SxvMgaKHNr6Pqxcw4uRes1NmoITq2igPtozDM,1548
 maxframe/serialization/core.pyi,sha256=oYh_n-2-cV8BaacM9kFev1rSC_OfEgWOUHjwdXBeY78,2206
 maxframe/serialization/core.pyx,sha256=KmeHc9A-NLZcMqVjyRxPDoKtVcvLmMOb57QsrsucncI,37083
@@ -691,7 +691,7 @@ maxframe_client/session/tests/test_task.py,sha256=HVLZUSUgzzJmim3d0rBw5mH2j-4HoA
 maxframe_client/tests/__init__.py,sha256=4LpNXO11JAdLjSut3p036oEEXlDEB-6AURW9oci5W5Y,609
 maxframe_client/tests/test_fetcher.py,sha256=-KG_OshShJEa66Hg_RKuT745AxadH2LMWasHo5hhIow,4265
 maxframe_client/tests/test_session.py,sha256=7-oNldT5YAnzWxSixWJH3VuBMwzFO7C38fNODINMi-M,11542
-maxframe-1.2.0.dist-info/METADATA,sha256=yjACwCuq9KVBUCAaE-A5W1bWY4qxsctZIuaJbde8xuQ,3126
-maxframe-1.2.0.dist-info/WHEEL,sha256=rTcqimtzpX3smAWAhGmiRSWAxTY4PqYPNE-p4kscHDQ,99
-maxframe-1.2.0.dist-info/top_level.txt,sha256=64x-fc2q59c_vXwNUkehyjF1vb8JWqFSdYmUqIFqoTM,31
-maxframe-1.2.0.dist-info/RECORD,,
+maxframe-1.2.1.dist-info/METADATA,sha256=61VvcvqHcKtpGuHCTTDaJxN1YV-pv4ZNBBAe8Vdnu5A,3126
+maxframe-1.2.1.dist-info/WHEEL,sha256=rTcqimtzpX3smAWAhGmiRSWAxTY4PqYPNE-p4kscHDQ,99
+maxframe-1.2.1.dist-info/top_level.txt,sha256=64x-fc2q59c_vXwNUkehyjF1vb8JWqFSdYmUqIFqoTM,31
+maxframe-1.2.1.dist-info/RECORD,,