def testToCPUExecution(self):
pdf = pd.DataFrame(np.random.rand(20, 30), index=np.arange(20, 0, -1))
df = from_pandas_df(pdf, chunk_size=(13, 21))
cdf = to_gpu(df)
df2 = to_cpu(cdf)
res = self.executor.execute_dataframe(df2, concat=True)[0]
self.assertIsInstance(res, pd.DataFrame)
pd.testing.assert_frame_equal(res, pdf)
pseries = pdf.iloc[:, 0]
series = from_pandas_series(pseries, chunk_size=(13, 21))
cseries = to_gpu(series)
series2 = to_cpu(cseries)
res = self.executor.execute_dataframe(series2, concat=True)[0]
self.assertIsInstance(res, pd.Series)
pd.testing.assert_series_equal(res, pseries)
def testToGPU(self):
# test dataframe
data = pd.DataFrame(np.random.rand(10, 10),
index=np.random.randint(-100, 100, size=(10, )),
columns=[np.random.bytes(10) for _ in range(10)])
df = from_pandas_df(data)
cdf = to_gpu(df)
self.assertEqual(df.index_value, cdf.index_value)
self.assertEqual(df.columns_value, cdf.columns_value)
self.assertTrue(cdf.op.gpu)
pd.testing.assert_series_equal(df.dtypes, cdf.dtypes)
cdf = cdf.tiles()
df = get_tiled(df)
self.assertEqual(df.nsplits, cdf.nsplits)
self.assertEqual(df.chunks[0].index_value, cdf.chunks[0].index_value)
self.assertEqual(df.chunks[0].columns_value,
cdf.chunks[0].columns_value)
self.assertTrue(cdf.chunks[0].op.gpu)
pd.testing.assert_series_equal(df.chunks[0].dtypes,
cdf.chunks[0].dtypes)
self.assertIs(cdf, to_gpu(cdf))
# test series
sdata = data.iloc[:, 0]
series = from_pandas_series(sdata)
cseries = to_gpu(series)
self.assertEqual(series.index_value, cseries.index_value)
self.assertTrue(cseries.op.gpu)
cseries = cseries.tiles()
series = get_tiled(series)
self.assertEqual(series.nsplits, cseries.nsplits)
self.assertEqual(series.chunks[0].index_value,
cseries.chunks[0].index_value)
self.assertTrue(cseries.chunks[0].op.gpu)
self.assertIs(cseries, to_gpu(cseries))
def testGPUExecution(self):
df_raw = pd.DataFrame(np.random.rand(30, 3), columns=list('abc'))
df = to_gpu(md.DataFrame(df_raw, chunk_size=6))
r = df.sum()
res = self.executor.execute_dataframe(r, concat=True)[0]
pd.testing.assert_series_equal(res.to_pandas(), df_raw.sum())
r = df.kurt()
res = self.executor.execute_dataframe(r, concat=True)[0]
pd.testing.assert_series_equal(res.to_pandas(), df_raw.kurt())
r = df.agg(['sum', 'var'])
res = self.executor.execute_dataframe(r, concat=True)[0]
pd.testing.assert_frame_equal(res.to_pandas(),
df_raw.agg(['sum', 'var']))
s_raw = pd.Series(np.random.rand(30))
s = to_gpu(md.Series(s_raw, chunk_size=6))
r = s.sum()
res = self.executor.execute_dataframe(r, concat=True)[0]
self.assertAlmostEqual(res, s_raw.sum())
r = s.kurt()
res = self.executor.execute_dataframe(r, concat=True)[0]
self.assertAlmostEqual(res, s_raw.kurt())
r = s.agg(['sum', 'var'])
res = self.executor.execute_dataframe(r, concat=True)[0]
pd.testing.assert_series_equal(res.to_pandas(),
s_raw.agg(['sum', 'var']))
s_raw = pd.Series(
np.random.randint(0, 3, size=(30, )) *
np.random.randint(0, 5, size=(30, )))
s = to_gpu(md.Series(s_raw, chunk_size=6))
r = s.unique()
res = self.executor.execute_dataframe(r, concat=True)[0]
np.testing.assert_array_equal(
cp.asnumpy(res).sort(),
s_raw.unique().sort())
def test_gpu_execution(setup, check_ref_counts):
df_raw = pd.DataFrame(np.random.rand(30, 3), columns=list('abc'))
df = to_gpu(md.DataFrame(df_raw, chunk_size=6))
r = df.sum()
res = r.execute().fetch()
pd.testing.assert_series_equal(res.to_pandas(), df_raw.sum())
r = df.kurt()
res = r.execute().fetch()
pd.testing.assert_series_equal(res.to_pandas(), df_raw.kurt())
r = df.agg(['sum', 'var'])
res = r.execute().fetch()
pd.testing.assert_frame_equal(res.to_pandas(), df_raw.agg(['sum', 'var']))
s_raw = pd.Series(np.random.rand(30))
s = to_gpu(md.Series(s_raw, chunk_size=6))
r = s.sum()
res = r.execute().fetch()
assert pytest.approx(res) == s_raw.sum()
r = s.kurt()
res = r.execute().fetch()
assert pytest.approx(res) == s_raw.kurt()
r = s.agg(['sum', 'var'])
res = r.execute().fetch()
pd.testing.assert_series_equal(res.to_pandas(), s_raw.agg(['sum', 'var']))
s_raw = pd.Series(
np.random.randint(0, 3, size=(30, )) *
np.random.randint(0, 5, size=(30, )))
s = to_gpu(md.Series(s_raw, chunk_size=6))
r = s.unique()
res = r.execute().fetch()
np.testing.assert_array_equal(
cp.asnumpy(res).sort(),
s_raw.unique().sort())
def test_to_gpu():
# test dataframe
data = pd.DataFrame(np.random.rand(10, 10),
index=np.random.randint(-100, 100, size=(10, )),
columns=[np.random.bytes(10) for _ in range(10)])
df = from_pandas_df(data)
cdf = to_gpu(df)
assert df.index_value == cdf.index_value
assert df.columns_value == cdf.columns_value
assert cdf.op.gpu is True
pd.testing.assert_series_equal(df.dtypes, cdf.dtypes)
df, cdf = tile(df, cdf)
assert df.nsplits == cdf.nsplits
assert df.chunks[0].index_value == cdf.chunks[0].index_value
assert df.chunks[0].columns_value == cdf.chunks[0].columns_value
assert cdf.chunks[0].op.gpu is True
pd.testing.assert_series_equal(df.chunks[0].dtypes, cdf.chunks[0].dtypes)
assert cdf is to_gpu(cdf)
# test series
sdata = data.iloc[:, 0]
series = from_pandas_series(sdata)
cseries = to_gpu(series)
assert series.index_value == cseries.index_value
assert cseries.op.gpu is True
series, cseries = tile(series, cseries)
assert series.nsplits == cseries.nsplits
assert series.chunks[0].index_value == cseries.chunks[0].index_value
assert cseries.chunks[0].op.gpu is True
assert cseries is to_gpu(cseries)
def testToCPU(self):
data = pd.DataFrame(np.random.rand(10, 10), index=np.random.randint(-100, 100, size=(10,)),
columns=[np.random.bytes(10) for _ in range(10)])
df = from_pandas_df(data)
cdf = to_gpu(df)
df2 = to_cpu(cdf)
self.assertEqual(df.index_value, df2.index_value)
self.assertEqual(df.columns_value, df2.columns_value)
self.assertFalse(df2.op.gpu)
pd.testing.assert_series_equal(df.dtypes, df2.dtypes)
df2.tiles()
self.assertEqual(df.nsplits, df2.nsplits)
self.assertEqual(df.chunks[0].index_value, df2.chunks[0].index_value)
self.assertEqual(df.chunks[0].columns_value, df2.chunks[0].columns_value)
self.assertFalse(df2.chunks[0].op.gpu)
pd.testing.assert_series_equal(df.chunks[0].dtypes, df2.chunks[0].dtypes)
self.assertIs(df2, to_cpu(df2))
def test_to_cpu():
data = pd.DataFrame(np.random.rand(10, 10),
index=np.random.randint(-100, 100, size=(10, )),
columns=[np.random.bytes(10) for _ in range(10)])
df = from_pandas_df(data)
cdf = to_gpu(df)
df2 = to_cpu(cdf)
assert df.index_value == df2.index_value
assert df.columns_value == df2.columns_value
assert df2.op.gpu is False
pd.testing.assert_series_equal(df.dtypes, df2.dtypes)
df, df2 = tile(df, df2)
assert df.nsplits == df2.nsplits
assert df.chunks[0].index_value == df2.chunks[0].index_value
assert df.chunks[0].columns_value == df2.chunks[0].columns_value
assert df2.chunks[0].op.gpu is False
pd.testing.assert_series_equal(df.chunks[0].dtypes, df2.chunks[0].dtypes)
assert df2 is to_cpu(df2)
