7ff9d2e3ee
### What changes were proposed in this pull request? This PR proposes to rename Koalas to pandas-on-Spark in main codes ### Why are the changes needed? To have the correct name in PySpark. NOTE that the official name in the main documentation will be pandas APIs on Spark to be extra clear. pandas-on-Spark is not the official term. ### Does this PR introduce _any_ user-facing change? No, it's master-only change. It changes the docstring and class names. ### How was this patch tested? Manually tested via: ```bash ./python/run-tests --python-executable=python3 --modules pyspark-pandas ``` Closes #32166 from HyukjinKwon/rename-koalas. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
211 lines
8.4 KiB
Python
211 lines
8.4 KiB
Python
#
|
|
# 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 numpy as np
|
|
import pandas as pd
|
|
|
|
from pyspark import pandas as ps
|
|
from pyspark.pandas import set_option, reset_option
|
|
from pyspark.pandas.numpy_compat import unary_np_spark_mappings, binary_np_spark_mappings
|
|
from pyspark.pandas.testing.utils import ReusedSQLTestCase, SQLTestUtils
|
|
|
|
|
|
class NumPyCompatTest(ReusedSQLTestCase, SQLTestUtils):
|
|
blacklist = [
|
|
# Koalas does not currently support
|
|
"conj",
|
|
"conjugate",
|
|
"isnat",
|
|
"matmul",
|
|
"frexp",
|
|
# Values are close enough but tests failed.
|
|
"arccos",
|
|
"exp",
|
|
"expm1",
|
|
"log", # flaky
|
|
"log10", # flaky
|
|
"log1p", # flaky
|
|
"modf",
|
|
"floor_divide", # flaky
|
|
# Results seem inconsistent in a different version of, I (Hyukjin) suspect, PyArrow.
|
|
# From PyArrow 0.15, seems it returns the correct results via PySpark. Probably we
|
|
# can enable it later when Koalas switches to PyArrow 0.15 completely.
|
|
"left_shift",
|
|
]
|
|
|
|
@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=[0, 1, 3, 5, 6, 8, 9, 9, 9],
|
|
)
|
|
|
|
@property
|
|
def kdf(self):
|
|
return ps.from_pandas(self.pdf)
|
|
|
|
def test_np_add_series(self):
|
|
kdf = self.kdf
|
|
pdf = self.pdf
|
|
|
|
if LooseVersion(pd.__version__) < LooseVersion("0.25"):
|
|
self.assert_eq(np.add(kdf.a, kdf.b), np.add(pdf.a, pdf.b).rename())
|
|
else:
|
|
self.assert_eq(np.add(kdf.a, kdf.b), np.add(pdf.a, pdf.b))
|
|
|
|
kdf = self.kdf
|
|
pdf = self.pdf
|
|
self.assert_eq(np.add(kdf.a, 1), np.add(pdf.a, 1))
|
|
|
|
def test_np_add_index(self):
|
|
k_index = self.kdf.index
|
|
p_index = self.pdf.index
|
|
self.assert_eq(np.add(k_index, k_index), np.add(p_index, p_index))
|
|
|
|
def test_np_unsupported_series(self):
|
|
kdf = self.kdf
|
|
with self.assertRaisesRegex(NotImplementedError, "pandas.*not.*support.*sqrt.*"):
|
|
np.sqrt(kdf.a, kdf.b)
|
|
|
|
def test_np_unsupported_frame(self):
|
|
kdf = self.kdf
|
|
with self.assertRaisesRegex(NotImplementedError, "on-Spark.*not.*support.*sqrt.*"):
|
|
np.sqrt(kdf, kdf)
|
|
|
|
def test_np_spark_compat_series(self):
|
|
# Use randomly generated dataFrame
|
|
pdf = pd.DataFrame(
|
|
np.random.randint(-100, 100, size=(np.random.randint(100), 2)), columns=["a", "b"]
|
|
)
|
|
pdf2 = pd.DataFrame(
|
|
np.random.randint(-100, 100, size=(len(pdf), len(pdf.columns))), columns=["a", "b"]
|
|
)
|
|
kdf = ps.from_pandas(pdf)
|
|
kdf2 = ps.from_pandas(pdf2)
|
|
|
|
for np_name, spark_func in unary_np_spark_mappings.items():
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# unary ufunc
|
|
self.assert_eq(np_func(pdf.a), np_func(kdf.a), almost=True)
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
|
|
for np_name, spark_func in binary_np_spark_mappings.items():
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# binary ufunc
|
|
if LooseVersion(pd.__version__) < LooseVersion("0.25"):
|
|
self.assert_eq(
|
|
np_func(pdf.a, pdf.b).rename(), np_func(kdf.a, kdf.b), almost=True
|
|
)
|
|
else:
|
|
self.assert_eq(np_func(pdf.a, pdf.b), np_func(kdf.a, kdf.b), almost=True)
|
|
self.assert_eq(np_func(pdf.a, 1), np_func(kdf.a, 1), almost=True)
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
|
|
# Test only top 5 for now. 'compute.ops_on_diff_frames' option increases too much time.
|
|
try:
|
|
set_option("compute.ops_on_diff_frames", True)
|
|
for np_name, spark_func in list(binary_np_spark_mappings.items())[:5]:
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# binary ufunc
|
|
if LooseVersion(pd.__version__) < LooseVersion("0.25"):
|
|
self.assert_eq(
|
|
np_func(pdf.a, pdf2.b).sort_index().rename(),
|
|
np_func(kdf.a, kdf2.b).sort_index(),
|
|
almost=True,
|
|
)
|
|
else:
|
|
self.assert_eq(
|
|
np_func(pdf.a, pdf2.b).sort_index(),
|
|
np_func(kdf.a, kdf2.b).sort_index(),
|
|
almost=True,
|
|
)
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
finally:
|
|
reset_option("compute.ops_on_diff_frames")
|
|
|
|
def test_np_spark_compat_frame(self):
|
|
# Use randomly generated dataFrame
|
|
pdf = pd.DataFrame(
|
|
np.random.randint(-100, 100, size=(np.random.randint(100), 2)), columns=["a", "b"]
|
|
)
|
|
pdf2 = pd.DataFrame(
|
|
np.random.randint(-100, 100, size=(len(pdf), len(pdf.columns))), columns=["a", "b"]
|
|
)
|
|
kdf = ps.from_pandas(pdf)
|
|
kdf2 = ps.from_pandas(pdf2)
|
|
|
|
for np_name, spark_func in unary_np_spark_mappings.items():
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# unary ufunc
|
|
self.assert_eq(np_func(pdf), np_func(kdf), almost=True)
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
|
|
for np_name, spark_func in binary_np_spark_mappings.items():
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# binary ufunc
|
|
self.assert_eq(np_func(pdf, pdf), np_func(kdf, kdf), almost=True)
|
|
self.assert_eq(np_func(pdf, 1), np_func(kdf, 1), almost=True)
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
|
|
# Test only top 5 for now. 'compute.ops_on_diff_frames' option increases too much time.
|
|
try:
|
|
set_option("compute.ops_on_diff_frames", True)
|
|
for np_name, spark_func in list(binary_np_spark_mappings.items())[:5]:
|
|
np_func = getattr(np, np_name)
|
|
if np_name not in self.blacklist:
|
|
try:
|
|
# binary ufunc
|
|
self.assert_eq(
|
|
np_func(pdf, pdf2).sort_index(),
|
|
np_func(kdf, kdf2).sort_index(),
|
|
almost=True,
|
|
)
|
|
|
|
except Exception as e:
|
|
raise AssertionError("Test in '%s' function was failed." % np_name) from e
|
|
finally:
|
|
reset_option("compute.ops_on_diff_frames")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.pandas.tests.test_numpy_compat import * # noqa: F401
|
|
|
|
try:
|
|
import xmlrunner # type: ignore[import]
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|