snowpark-connect 0.23.0__py3-none-any.whl → 0.25.0__py3-none-any.whl

snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_cov.py

@@ -1,151 +0,0 @@
-#
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements.  See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You 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 distutils.version import LooseVersion
-import unittest
-import decimal
-
-
-import numpy as np
-import pandas as pd
-
-from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
-from pyspark.testing.sqlutils import SQLTestUtils
-
-
-class FrameCovMixin:
-    @unittest.skipIf(
-        LooseVersion(pd.__version__) >= LooseVersion("2.0.0"),
-        "TODO(SPARK-43809): Enable DataFrameSlowTests.test_cov for pandas 2.0.0.",
-    )
-    def test_cov(self):
-        # SPARK-36396: Implement DataFrame.cov
-
-        # int
-        pdf = pd.DataFrame([(1, 2), (0, 3), (2, 0), (1, 1)], columns=["a", "b"])
-        psdf = ps.from_pandas(pdf)
-        self.assert_eq(pdf.cov(), psdf.cov(), almost=True)
-        self.assert_eq(pdf.cov(min_periods=4), psdf.cov(min_periods=4), almost=True)
-        self.assert_eq(pdf.cov(min_periods=5), psdf.cov(min_periods=5))
-
-        # ddof
-        with self.assertRaisesRegex(TypeError, "ddof must be integer"):
-            psdf.cov(ddof="ddof")
-        for ddof in [-1, 0, 2]:
-            self.assert_eq(pdf.cov(ddof=ddof), psdf.cov(ddof=ddof), almost=True)
-            self.assert_eq(
-                pdf.cov(min_periods=4, ddof=ddof), psdf.cov(min_periods=4, ddof=ddof), almost=True
-            )
-            self.assert_eq(pdf.cov(min_periods=5, ddof=ddof), psdf.cov(min_periods=5, ddof=ddof))
-
-        # bool
-        pdf = pd.DataFrame(
-            {
-                "a": [1, np.nan, 3, 4],
-                "b": [True, False, False, True],
-                "c": [True, True, False, True],
-            }
-        )
-        psdf = ps.from_pandas(pdf)
-        self.assert_eq(pdf.cov(), psdf.cov(), almost=True)
-        self.assert_eq(pdf.cov(min_periods=4), psdf.cov(min_periods=4), almost=True)
-        self.assert_eq(pdf.cov(min_periods=5), psdf.cov(min_periods=5))
-
-        # extension dtype
-        if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
-            numeric_dtypes = ["Int8", "Int16", "Int32", "Int64", "Float32", "Float64", "float"]
-            boolean_dtypes = ["boolean", "bool"]
-        else:
-            numeric_dtypes = ["Int8", "Int16", "Int32", "Int64", "float"]
-            boolean_dtypes = ["boolean", "bool"]
-
-        sers = [pd.Series([1, 2, 3, None], dtype=dtype) for dtype in numeric_dtypes]
-        sers += [pd.Series([True, False, True, None], dtype=dtype) for dtype in boolean_dtypes]
-        sers.append(pd.Series([decimal.Decimal(1), decimal.Decimal(2), decimal.Decimal(3), None]))
-
-        pdf = pd.concat(sers, axis=1)
-        pdf.columns = [dtype for dtype in numeric_dtypes + boolean_dtypes] + ["decimal"]
-        psdf = ps.from_pandas(pdf)
-
-        if LooseVersion(pd.__version__) >= LooseVersion("1.2"):
-            self.assert_eq(pdf.cov(), psdf.cov(), almost=True)
-            self.assert_eq(pdf.cov(min_periods=3), psdf.cov(min_periods=3), almost=True)
-            self.assert_eq(pdf.cov(min_periods=4), psdf.cov(min_periods=4))
-        else:
-            test_types = [
-                "Int8",
-                "Int16",
-                "Int32",
-                "Int64",
-                "float",
-                "boolean",
-                "bool",
-            ]
-            expected = pd.DataFrame(
-                data=[
-                    [1.0, 1.0, 1.0, 1.0, 1.0, 0.0000000, 0.0000000],
-                    [1.0, 1.0, 1.0, 1.0, 1.0, 0.0000000, 0.0000000],
-                    [1.0, 1.0, 1.0, 1.0, 1.0, 0.0000000, 0.0000000],
-                    [1.0, 1.0, 1.0, 1.0, 1.0, 0.0000000, 0.0000000],
-                    [1.0, 1.0, 1.0, 1.0, 1.0, 0.0000000, 0.0000000],
-                    [0.0, 0.0, 0.0, 0.0, 0.0, 0.3333333, 0.3333333],
-                    [0.0, 0.0, 0.0, 0.0, 0.0, 0.3333333, 0.3333333],
-                ],
-                index=test_types,
-                columns=test_types,
-            )
-            self.assert_eq(expected, psdf.cov(), almost=True)
-
-        # string column
-        pdf = pd.DataFrame(
-            [(1, 2, "a", 1), (0, 3, "b", 1), (2, 0, "c", 9), (1, 1, "d", 1)],
-            columns=["a", "b", "c", "d"],
-        )
-        psdf = ps.from_pandas(pdf)
-        self.assert_eq(pdf.cov(), psdf.cov(), almost=True)
-        self.assert_eq(pdf.cov(min_periods=4), psdf.cov(min_periods=4), almost=True)
-        self.assert_eq(pdf.cov(min_periods=5), psdf.cov(min_periods=5))
-
-        # nan
-        np.random.seed(42)
-        pdf = pd.DataFrame(np.random.randn(20, 3), columns=["a", "b", "c"])
-        pdf.loc[pdf.index[:5], "a"] = np.nan
-        pdf.loc[pdf.index[5:10], "b"] = np.nan
-        psdf = ps.from_pandas(pdf)
-        self.assert_eq(pdf.cov(min_periods=11), psdf.cov(min_periods=11), almost=True)
-        self.assert_eq(pdf.cov(min_periods=10), psdf.cov(min_periods=10), almost=True)
-
-        # return empty DataFrame
-        pdf = pd.DataFrame([("1", "2"), ("0", "3"), ("2", "0"), ("1", "1")], columns=["a", "b"])
-        psdf = ps.from_pandas(pdf)
-        self.assert_eq(pdf.cov(), psdf.cov())
-
-
-class FrameCovTests(FrameCovMixin, ComparisonTestBase, SQLTestUtils):
-    pass
-
-
-if __name__ == "__main__":
-    from pyspark.pandas.tests.computation.test_cov import *  # noqa: F401
-
-    try:
-        import xmlrunner
-
-        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
-    except ImportError:
-        testRunner = None
-    unittest.main(testRunner=testRunner, verbosity=2)

snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_cumulative.py

@@ -1,139 +0,0 @@
-#
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements.  See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You 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.
-#
-import unittest
-
-import numpy as np
-import pandas as pd
-
-from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
-from pyspark.testing.sqlutils import SQLTestUtils
-
-
-class FrameCumulativeMixin:
-    @property
-    def pdf(self):
-        return pd.DataFrame(
-            {"a": [1, 2, 3, 4, 5, 6, 7, 8, 9], "b": [4, 5, 6, 3, 2, 1, 0, 0, 0]},
-            index=np.random.rand(9),
-        )
-
-    @property
-    def df_pair(self):
-        pdf = self.pdf
-        psdf = ps.from_pandas(pdf)
-        return pdf, psdf
-
-    def _test_cummin(self, pdf, psdf):
-        self.assert_eq(pdf.cummin(), psdf.cummin())
-        self.assert_eq(pdf.cummin(skipna=False), psdf.cummin(skipna=False))
-        self.assert_eq(pdf.cummin().sum(), psdf.cummin().sum())
-
-    def test_cummin(self):
-        pdf = pd.DataFrame(
-            [[2.0, 1.0], [5, None], [1.0, 0.0], [2.0, 4.0], [4.0, 9.0]],
-            columns=list("AB"),
-            index=np.random.rand(5),
-        )
-        psdf = ps.from_pandas(pdf)
-        self._test_cummin(pdf, psdf)
-
-    def test_cummin_multiindex_columns(self):
-        arrays = [np.array(["A", "A", "B", "B"]), np.array(["one", "two", "one", "two"])]
-        pdf = pd.DataFrame(np.random.randn(3, 4), index=["A", "C", "B"], columns=arrays)
-        pdf.at["C", ("A", "two")] = None
-        psdf = ps.from_pandas(pdf)
-        self._test_cummin(pdf, psdf)
-
-    def _test_cummax(self, pdf, psdf):
-        self.assert_eq(pdf.cummax(), psdf.cummax())
-        self.assert_eq(pdf.cummax(skipna=False), psdf.cummax(skipna=False))
-        self.assert_eq(pdf.cummax().sum(), psdf.cummax().sum())
-
-    def test_cummax(self):
-        pdf = pd.DataFrame(
-            [[2.0, 1.0], [5, None], [1.0, 0.0], [2.0, 4.0], [4.0, 9.0]],
-            columns=list("AB"),
-            index=np.random.rand(5),
-        )
-        psdf = ps.from_pandas(pdf)
-        self._test_cummax(pdf, psdf)
-
-    def test_cummax_multiindex_columns(self):
-        arrays = [np.array(["A", "A", "B", "B"]), np.array(["one", "two", "one", "two"])]
-        pdf = pd.DataFrame(np.random.randn(3, 4), index=["A", "C", "B"], columns=arrays)
-        pdf.at["C", ("A", "two")] = None
-        psdf = ps.from_pandas(pdf)
-        self._test_cummax(pdf, psdf)
-
-    def _test_cumsum(self, pdf, psdf):
-        self.assert_eq(pdf.cumsum(), psdf.cumsum())
-        self.assert_eq(pdf.cumsum(skipna=False), psdf.cumsum(skipna=False))
-        self.assert_eq(pdf.cumsum().sum(), psdf.cumsum().sum())
-
-    def test_cumsum(self):
-        pdf = pd.DataFrame(
-            [[2.0, 1.0], [5, None], [1.0, 0.0], [2.0, 4.0], [4.0, 9.0]],
-            columns=list("AB"),
-            index=np.random.rand(5),
-        )
-        psdf = ps.from_pandas(pdf)
-        self._test_cumsum(pdf, psdf)
-
-    def test_cumsum_multiindex_columns(self):
-        arrays = [np.array(["A", "A", "B", "B"]), np.array(["one", "two", "one", "two"])]
-        pdf = pd.DataFrame(np.random.randn(3, 4), index=["A", "C", "B"], columns=arrays)
-        pdf.at["C", ("A", "two")] = None
-        psdf = ps.from_pandas(pdf)
-        self._test_cumsum(pdf, psdf)
-
-    def _test_cumprod(self, pdf, psdf):
-        self.assert_eq(pdf.cumprod(), psdf.cumprod(), almost=True)
-        self.assert_eq(pdf.cumprod(skipna=False), psdf.cumprod(skipna=False), almost=True)
-        self.assert_eq(pdf.cumprod().sum(), psdf.cumprod().sum(), almost=True)
-
-    def test_cumprod(self):
-        pdf = pd.DataFrame(
-            [[2.0, 1.0, 1], [5, None, 2], [1.0, -1.0, -3], [2.0, 0, 4], [4.0, 9.0, 5]],
-            columns=list("ABC"),
-            index=np.random.rand(5),
-        )
-        psdf = ps.from_pandas(pdf)
-        self._test_cumprod(pdf, psdf)
-
-    def test_cumprod_multiindex_columns(self):
-        arrays = [np.array(["A", "A", "B", "B"]), np.array(["one", "two", "one", "two"])]
-        pdf = pd.DataFrame(np.random.rand(3, 4), index=["A", "C", "B"], columns=arrays)
-        pdf.at["C", ("A", "two")] = None
-        psdf = ps.from_pandas(pdf)
-        self._test_cumprod(pdf, psdf)
-
-
-class FrameCumulativeTests(FrameCumulativeMixin, ComparisonTestBase, SQLTestUtils):
-    pass
-
-
-if __name__ == "__main__":
-    from pyspark.pandas.tests.computation.test_cumulative import *  # noqa: F401
-
-    try:
-        import xmlrunner
-
-        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
-    except ImportError:
-        testRunner = None
-    unittest.main(testRunner=testRunner, verbosity=2)