def test_series_corr(setup):
rs = np.random.RandomState(0)
raw = rs.rand(20)
raw = pd.Series(np.where(raw > 0.4, raw, np.nan))
raw2 = rs.rand(20)
raw2 = pd.Series(np.where(raw2 > 0.4, raw2, np.nan))
s = Series(raw)
s2 = Series(raw2)
result = s.corr(s2)
assert result.execute().fetch() == raw.corr(raw2)
result = s.corr(s2, method='kendall')
assert result.execute().fetch() == raw.corr(raw2, method='kendall')
result = s.autocorr(2)
assert result.execute().fetch() == raw.autocorr(2)
s = Series(raw, chunk_size=6)
s2 = Series(raw2, chunk_size=4)
with pytest.raises(Exception):
s.corr(s2, method='kendall').execute()
result = s.corr(s2)
assert pytest.approx(result.execute().fetch()) == raw.corr(raw2)
result = s.corr(s2, min_periods=7)
assert pytest.approx(result.execute().fetch()) == raw.corr(raw2,
min_periods=7)
result = s.autocorr(2)
assert pytest.approx(result.execute().fetch()) == raw.autocorr(2)
def test_dataframe_corr_with(setup):
rs = np.random.RandomState(0)
raw_df = rs.rand(20, 10)
raw_df = pd.DataFrame(np.where(raw_df > 0.4, raw_df, np.nan),
columns=list('ABCDEFGHIJ'))
raw_df2 = rs.rand(20, 10)
raw_df2 = pd.DataFrame(np.where(raw_df2 > 0.4, raw_df2, np.nan),
columns=list('ACDEGHIJKL'))
raw_s = rs.rand(20)
raw_s = pd.Series(np.where(raw_s > 0.4, raw_s, np.nan))
raw_s2 = rs.rand(10)
raw_s2 = pd.Series(np.where(raw_s2 > 0.4, raw_s2, np.nan),
index=raw_df2.columns)
df = DataFrame(raw_df)
df2 = DataFrame(raw_df2)
result = df.corrwith(df2)
pd.testing.assert_series_equal(result.execute().fetch(),
raw_df.corrwith(raw_df2))
result = df.corrwith(df2, axis=1)
pd.testing.assert_series_equal(result.execute().fetch(),
raw_df.corrwith(raw_df2, axis=1))
result = df.corrwith(df2, method='kendall')
pd.testing.assert_series_equal(result.execute().fetch(),
raw_df.corrwith(raw_df2, method='kendall'))
df = DataFrame(raw_df, chunk_size=4)
df2 = DataFrame(raw_df2, chunk_size=6)
s = Series(raw_s, chunk_size=5)
s2 = Series(raw_s2, chunk_size=5)
with pytest.raises(Exception):
df.corrwith(df2, method='kendall').execute()
result = df.corrwith(df2)
pd.testing.assert_series_equal(result.execute().fetch().sort_index(),
raw_df.corrwith(raw_df2).sort_index())
result = df.corrwith(df2, axis=1)
pd.testing.assert_series_equal(
result.execute().fetch().sort_index(),
raw_df.corrwith(raw_df2, axis=1).sort_index())
result = df.corrwith(s)
pd.testing.assert_series_equal(result.execute().fetch().sort_index(),
raw_df.corrwith(raw_s).sort_index())
result = df.corrwith(s2, axis=1)
pd.testing.assert_series_equal(
result.execute().fetch().sort_index(),
raw_df.corrwith(raw_s2, axis=1).sort_index())
def testSeriesQuantileExecution(self):
raw = pd.Series(np.random.rand(10), name='a')
a = Series(raw, chunk_size=3)
# q = 0.5, scalar
r = a.quantile()
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile()
self.assertEqual(result, expected)
# q is a list
r = a.quantile([0.3, 0.7])
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
# test interpolation
r = a.quantile([0.3, 0.7], interpolation='midpoint')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile([0.3, 0.7], interpolation='midpoint')
pd.testing.assert_series_equal(result, expected)
ctx, executor = self._create_test_context(self.executor)
with ctx:
q = tensor([0.3, 0.7])
# q is a tensor
r = a.quantile(q)
result = executor.execute_dataframes([r])[0]
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
def test_series_quantile_execution(setup):
raw = pd.Series(np.random.rand(10), name='a')
a = Series(raw, chunk_size=3)
# q = 0.5, scalar
r = a.quantile()
result = r.execute().fetch()
expected = raw.quantile()
assert result == expected
# q is a list
r = a.quantile([0.3, 0.7])
result = r.execute().fetch()
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
# test interpolation
r = a.quantile([0.3, 0.7], interpolation='midpoint')
result = r.execute().fetch()
expected = raw.quantile([0.3, 0.7], interpolation='midpoint')
pd.testing.assert_series_equal(result, expected)
q = tensor([0.3, 0.7])
# q is a tensor
r = a.quantile(q)
result = r.execute().fetch()
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
def testSeriesCorr(self):
rs = np.random.RandomState(0)
raw = rs.rand(20)
raw = pd.Series(np.where(raw > 0.4, raw, np.nan))
raw2 = rs.rand(20)
raw2 = pd.Series(np.where(raw2 > 0.4, raw2, np.nan))
s = Series(raw)
s2 = Series(raw2)
result = s.corr(s2)
self.assertEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.corr(raw2))
result = s.corr(s2, method='kendall')
self.assertEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.corr(raw2, method='kendall'))
result = s.autocorr(2)
self.assertEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.autocorr(2))
s = Series(raw, chunk_size=6)
s2 = Series(raw2, chunk_size=4)
with self.assertRaises(Exception):
self.executor.execute_dataframe(s.corr(s2, method='kendall'),
concat=True)
result = s.corr(s2)
self.assertAlmostEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.corr(raw2))
result = s.corr(s2, min_periods=7)
self.assertAlmostEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.corr(raw2, min_periods=7))
result = s.autocorr(2)
self.assertAlmostEqual(
self.executor.execute_dataframe(result, concat=True)[0],
raw.autocorr(2))
def testGPUExecution(self):
# test sort_values
distinct_opts = ['0'] if sys.platform.lower().startswith('win') else [
'0', '1'
]
for add_distinct in distinct_opts:
os.environ['PSRS_DISTINCT_COL'] = add_distinct
# test dataframe
raw = pd.DataFrame(np.random.rand(100, 10),
columns=['a' + str(i) for i in range(10)])
mdf = DataFrame(raw, chunk_size=30).to_gpu()
result = self.executor.execute_dataframe(mdf.sort_values(by='a0'),
concat=True)[0]
expected = raw.sort_values(by='a0')
pd.testing.assert_frame_equal(result.to_pandas(), expected)
# test series
raw = pd.Series(np.random.rand(10))
series = Series(raw).to_gpu()
result = self.executor.execute_dataframe(series.sort_values(),
concat=True)[0]
expected = raw.sort_values()
pd.testing.assert_series_equal(result.to_pandas(), expected)
# test DataFrame.sort_index
raw = pd.DataFrame(np.random.rand(10, 10), columns=np.random.rand(10))
mdf = DataFrame(raw).to_gpu()
result = self.executor.execute_dataframe(mdf.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_frame_equal(result.to_pandas(), expected)
# test Series.sort_index
raw = pd.Series(np.random.rand(10, ), index=np.random.rand(10))
series = Series(raw).to_gpu()
result = self.executor.execute_dataframe(series.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_series_equal(result.to_pandas(), expected)
def testSeriesQuantileExecution(self):
raw = pd.Series(np.random.rand(10), name='a')
a = Series(raw, chunk_size=3)
# q = 0.5, scalar
r = a.quantile()
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile()
self.assertEqual(result, expected)
# q is a list
r = a.quantile([0.3, 0.7])
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
# test interpolation
r = a.quantile([0.3, 0.7], interpolation='midpoint')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = raw.quantile([0.3, 0.7], interpolation='midpoint')
pd.testing.assert_series_equal(result, expected)
this = self
class MockSession:
def __init__(self):
self.executor = this.executor
ctx = LocalContext(MockSession())
executor = ExecutorForTest('numpy', storage=ctx)
with ctx:
q = tensor([0.3, 0.7])
# q is a tensor
r = a.quantile(q)
result = executor.execute_dataframes([r])[0]
expected = raw.quantile([0.3, 0.7])
pd.testing.assert_series_equal(result, expected)
def testToDatetimeExecution(self):
# scalar
r = to_datetime(1490195805, unit='s')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(1490195805, unit='s')
self.assertEqual(pd.to_datetime(result.item()), expected)
# test list like
raw = ['3/11/2000', '3/12/2000', '3/13/2000']
t = tensor(raw, chunk_size=2)
r = to_datetime(t, infer_datetime_format=True)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw, infer_datetime_format=True)
pd.testing.assert_index_equal(result, expected)
# test series
raw_series = pd.Series(raw)
s = Series(raw_series, chunk_size=2)
r = to_datetime(s)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_series)
pd.testing.assert_series_equal(result, expected)
# test DataFrame
raw_df = pd.DataFrame({
'year': [2015, 2016],
'month': [2, 3],
'day': [4, 5]
})
df = DataFrame(raw_df, chunk_size=(1, 2))
r = to_datetime(df)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_df)
pd.testing.assert_series_equal(result, expected)
# test Index
raw_index = pd.Index([1, 2, 3])
s = Index(raw_index, chunk_size=2)
r = to_datetime(s)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_index)
pd.testing.assert_index_equal(result, expected)
# test raises == 'ignore'
raw = ['13000101']
r = to_datetime(raw, format='%Y%m%d', errors='ignore')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw, format='%Y%m%d', errors='ignore')
pd.testing.assert_index_equal(result, expected)
# test unit
r = to_datetime([1490195805], unit='s')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime([1490195805], unit='s')
pd.testing.assert_index_equal(result, expected)
# test origin
r = to_datetime([1, 2, 3], unit='D', origin=pd.Timestamp('1960-01-01'))
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime([1, 2, 3],
unit='D',
origin=pd.Timestamp('1960-01-01'))
pd.testing.assert_index_equal(result, expected)
def testDotExecution(self):
df1_raw = pd.DataFrame(np.random.rand(4, 7))
df2_raw = pd.DataFrame(np.random.rand(7, 5), columns=list('efghi'))
s1_raw = pd.Series(np.random.rand(7))
s2_raw = pd.Series(np.random.rand(7))
df1 = DataFrame(df1_raw, chunk_size=(3, 2))
df2 = DataFrame(df2_raw, chunk_size=(3, 4))
# df.dot(df)
r = df1.dot(df2)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = df1_raw.dot(df2_raw)
pd.testing.assert_frame_equal(result, expected)
# test @
r = df1 @ df2
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = df1_raw @ df2_raw
pd.testing.assert_frame_equal(result, expected)
series1 = Series(s1_raw, chunk_size=5)
# df.dot(series)
r = df1.dot(series1)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = df1_raw.dot(s1_raw)
pd.testing.assert_series_equal(result, expected)
# df.dot(2d_array)
r = df1.dot(df2_raw.to_numpy())
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = df1_raw.dot(df2_raw.to_numpy())
pd.testing.assert_frame_equal(result, expected)
# df.dot(1d_array)
r = df1.dot(s1_raw.to_numpy())
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = df1_raw.dot(s1_raw.to_numpy())
pd.testing.assert_series_equal(result, expected)
series2 = Series(s2_raw, chunk_size=4)
# series.dot(series)
r = series1.dot(series2)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = s1_raw.dot(s2_raw)
self.assertAlmostEqual(result, expected)
# series.dot(df)
r = series1.dot(df2)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = s1_raw.dot(df2_raw)
pd.testing.assert_series_equal(result, expected)
# series.dot(2d_array)
r = series1.dot(df2_raw.to_numpy())
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = s1_raw.dot(df2_raw.to_numpy())
np.testing.assert_almost_equal(result, expected)
# series.dot(1d_array)
r = series1.dot(s2_raw.to_numpy())
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = s1_raw.dot(s2_raw.to_numpy())
self.assertAlmostEqual(result, expected)
def test_sort_values_execution(setup):
distinct_opts = ['0'] if sys.platform.lower().startswith('win') else [
'0', '1'
]
for add_distinct in distinct_opts:
os.environ['PSRS_DISTINCT_COL'] = add_distinct
df = pd.DataFrame(np.random.rand(100, 10),
columns=['a' + str(i) for i in range(10)])
# test one chunk
mdf = DataFrame(df)
result = mdf.sort_values('a0').execute().fetch()
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = mdf.sort_values(['a6', 'a7'],
ascending=False).execute().fetch()
expected = df.sort_values(['a6', 'a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test psrs
mdf = DataFrame(df, chunk_size=10)
result = mdf.sort_values('a0').execute().fetch()
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = mdf.sort_values(['a3', 'a4']).execute().fetch()
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test ascending=False
result = mdf.sort_values(['a0', 'a1'],
ascending=False).execute().fetch()
expected = df.sort_values(['a0', 'a1'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
result = mdf.sort_values(['a7'], ascending=False).execute().fetch()
expected = df.sort_values(['a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test multiindex
df2 = df.copy(deep=True)
df2.columns = pd.MultiIndex.from_product([list('AB'), list('CDEFG')])
mdf = DataFrame(df2, chunk_size=10)
result = mdf.sort_values([('A', 'C')]).execute().fetch()
expected = df2.sort_values([('A', 'C')])
pd.testing.assert_frame_equal(result, expected)
# test rechunk
mdf = DataFrame(df, chunk_size=3)
result = mdf.sort_values('a0').execute().fetch()
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = mdf.sort_values(['a3', 'a4']).execute().fetch()
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test other types
raw = pd.DataFrame(
{
'a': np.random.rand(10),
'b': np.random.randint(1000, size=10),
'c': np.random.rand(10),
'd': [np.random.bytes(10) for _ in range(10)],
'e': [pd.Timestamp(f'201{i}') for i in range(10)],
'f': [pd.Timedelta(f'{i} days') for i in range(10)]
}, )
mdf = DataFrame(raw, chunk_size=3)
for label in raw.columns:
result = mdf.sort_values(label).execute().fetch()
expected = raw.sort_values(label)
pd.testing.assert_frame_equal(result, expected)
result = mdf.sort_values(['a', 'b', 'e'],
ascending=False).execute().fetch()
expected = raw.sort_values(['a', 'b', 'e'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test nan
df = pd.DataFrame({
'col1': ['A', 'A', 'B', 'B', 'D', 'C'],
'col2': [2, 1, 9, np.nan, 7, 4],
'col3': [0, 1, 9, 4, 2, 3],
})
mdf = DataFrame(df)
result = mdf.sort_values(['col2']).execute().fetch()
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(df, chunk_size=3)
result = mdf.sort_values(['col2']).execute().fetch()
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
# test None (issue #1885)
df = pd.DataFrame(np.random.rand(1000, 10))
df[0][df[0] < 0.5] = 'A'
df[0][df[0] != 'A'] = None
mdf = DataFrame(df)
result = mdf.sort_values([0, 1]).execute().fetch()
expected = df.sort_values([0, 1])
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(df, chunk_size=100)
result = mdf.sort_values([0, 1]).execute().fetch()
expected = df.sort_values([0, 1])
pd.testing.assert_frame_equal(result, expected)
# test ignore_index
df = pd.DataFrame(np.random.rand(10, 3),
columns=['a' + str(i) for i in range(3)])
mdf = DataFrame(df, chunk_size=3)
result = mdf.sort_values(['a0', 'a1'],
ignore_index=True).execute().fetch()
try: # for python3.5
expected = df.sort_values(['a0', 'a1'], ignore_index=True)
except TypeError:
expected = df.sort_values(['a0', 'a1'])
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test inplace
mdf = DataFrame(df)
mdf.sort_values('a0', inplace=True)
result = mdf.execute().fetch()
df.sort_values('a0', inplace=True)
pd.testing.assert_frame_equal(result, df)
# test unknown shape
df = pd.DataFrame({'a': list(range(10)), 'b': np.random.random(10)})
mdf = DataFrame(df, chunk_size=4)
filtered = mdf[mdf['a'] > 2]
result = filtered.sort_values(by='b').execute().fetch()
pd.testing.assert_frame_equal(result,
df[df['a'] > 2].sort_values(by='b'))
# test empty dataframe
df = pd.DataFrame({'a': list(range(10)), 'b': np.random.random(10)})
mdf = DataFrame(df, chunk_size=4)
filtered = mdf[mdf['b'] > 100]
result = filtered.sort_values(by='b').execute().fetch()
pd.testing.assert_frame_equal(result,
df[df['b'] > 100].sort_values(by='b'))
# test chunks with zero length
df = pd.DataFrame({'a': list(range(10)), 'b': np.random.random(10)})
df.iloc[4:8, 1] = 0
mdf = DataFrame(df, chunk_size=4)
filtered = mdf[mdf['b'] != 0]
result = filtered.sort_values(by='b').execute().fetch()
pd.testing.assert_frame_equal(result,
df[df['b'] != 0].sort_values(by='b'))
# test Series.sort_values
raw = pd.Series(np.random.rand(10))
series = Series(raw)
result = series.sort_values().execute().fetch()
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=3)
result = series.sort_values().execute().fetch()
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=2)
result = series.sort_values(ascending=False).execute().fetch()
expected = raw.sort_values(ascending=False)
pd.testing.assert_series_equal(result, expected)
# test empty series
series = pd.Series(list(range(10)), name='a')
mseries = Series(series, chunk_size=4)
filtered = mseries[mseries > 100]
result = filtered.sort_values().execute().fetch()
pd.testing.assert_series_equal(result,
series[series > 100].sort_values())
# test series with None
series = pd.Series(np.arange(1000, ))
series[series < 500] = 'A'
series[series != 'A'] = None
mseries = Series(series, chunk_size=100)
result = mseries.sort_values().execute().fetch()
expected = series.sort_values()
pd.testing.assert_series_equal(result.reset_index(drop=True),
expected.reset_index(drop=True))
def test_sort_index_execution(setup):
raw = pd.DataFrame(np.random.rand(100, 20), index=np.random.rand(100))
mdf = DataFrame(raw)
result = mdf.sort_index().execute().fetch()
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw)
mdf.sort_index(inplace=True)
result = mdf.execute().fetch()
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=30)
result = mdf.sort_index().execute().fetch()
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=20)
result = mdf.sort_index(ascending=False).execute().fetch()
expected = raw.sort_index(ascending=False)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=10)
result = mdf.sort_index(ignore_index=True).execute().fetch()
try: # for python3.5
expected = raw.sort_index(ignore_index=True)
except TypeError:
expected = raw.sort_index()
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test axis=1
raw = pd.DataFrame(np.random.rand(10, 10), columns=np.random.rand(10))
mdf = DataFrame(raw)
result = mdf.sort_index(axis=1).execute().fetch()
expected = raw.sort_index(axis=1)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=3)
result = mdf.sort_index(axis=1).execute().fetch()
expected = raw.sort_index(axis=1)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=4)
result = mdf.sort_index(axis=1, ascending=False).execute().fetch()
expected = raw.sort_index(axis=1, ascending=False)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=4)
result = mdf.sort_index(axis=1, ignore_index=True).execute().fetch()
try: # for python3.5
expected = raw.sort_index(axis=1, ignore_index=True)
except TypeError:
expected = raw.sort_index(axis=1)
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test series
raw = pd.Series(np.random.rand(10, ), index=np.random.rand(10))
series = Series(raw)
result = series.sort_index().execute().fetch()
expected = raw.sort_index()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=2)
result = series.sort_index().execute().fetch()
expected = raw.sort_index()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=3)
result = series.sort_index(ascending=False).execute().fetch()
expected = raw.sort_index(ascending=False)
pd.testing.assert_series_equal(result, expected)
def testSortValuesExecution(self):
df = pd.DataFrame(np.random.rand(100, 10),
columns=['a' + str(i) for i in range(10)])
# test one chunk
mdf = DataFrame(df)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a6', 'a7'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a6', 'a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test psrs
mdf = DataFrame(df, chunk_size=10)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(['a3', 'a4']),
concat=True)[0]
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test ascending=False
result = self.executor.execute_dataframe(mdf.sort_values(
['a0', 'a1'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a0', 'a1'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a7'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test rechunk
mdf = DataFrame(df, chunk_size=3)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(['a3', 'a4']),
concat=True)[0]
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test other types
raw = pd.DataFrame(
{
'a': np.random.rand(10),
'b': np.random.randint(1000, size=10),
'c': np.random.rand(10),
'd': [np.random.bytes(10) for _ in range(10)],
'e': [pd.Timestamp('201{}'.format(i)) for i in range(10)],
'f': [pd.Timedelta('{} days'.format(i)) for i in range(10)]
}, )
mdf = DataFrame(raw, chunk_size=3)
for label in raw.columns:
result = self.executor.execute_dataframe(mdf.sort_values(label),
concat=True)[0]
expected = raw.sort_values(label)
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a', 'b', 'e'], ascending=False),
concat=True)[0]
expected = raw.sort_values(['a', 'b', 'e'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test nan
df = pd.DataFrame({
'col1': ['A', 'A', 'B', 'B', 'D', 'C'],
'col2': [2, 1, 9, np.nan, 7, 4],
'col3': [0, 1, 9, 4, 2, 3],
})
mdf = DataFrame(df)
result = self.executor.execute_dataframe(mdf.sort_values(['col2']),
concat=True)[0]
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(df, chunk_size=3)
result = self.executor.execute_dataframe(mdf.sort_values(['col2']),
concat=True)[0]
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
# test ignore_index
executor = ExecutorForTest(storage=new_session().context)
df = pd.DataFrame(np.random.rand(10, 3),
columns=['a' + str(i) for i in range(3)])
mdf = DataFrame(df, chunk_size=3)
result = executor.execute_dataframe(mdf.sort_values(['a0', 'a1'],
ignore_index=True),
concat=True)[0]
try: # for python3.5
expected = df.sort_values(['a0', 'a1'], ignore_index=True)
except TypeError:
expected = df.sort_values(['a0', 'a1'])
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test inplace
mdf = DataFrame(df)
mdf.sort_values('a0', inplace=True)
result = self.executor.execute_dataframe(mdf, concat=True)[0]
df.sort_values('a0', inplace=True)
pd.testing.assert_frame_equal(result, df)
# test unknown shape
df = pd.DataFrame({'a': list(range(10)), 'b': np.random.random(10)})
mdf = DataFrame(df, chunk_size=4)
filtered = mdf[mdf['a'] > 2]
result = self.executor.execute_dataframe(filtered.sort_values(by='b'),
concat=True)[0]
pd.testing.assert_frame_equal(result,
df[df['a'] > 2].sort_values(by='b'))
# test Sereis.sort_values
raw = pd.Series(np.random.rand(10))
series = Series(raw)
result = self.executor.execute_dataframe(series.sort_values(),
concat=True)[0]
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=3)
result = self.executor.execute_dataframe(series.sort_values(),
concat=True)[0]
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=2)
result = self.executor.execute_dataframe(
series.sort_values(ascending=False), concat=True)[0]
expected = raw.sort_values(ascending=False)
pd.testing.assert_series_equal(result, expected)
def test_dot_execution(setup):
df1_raw = pd.DataFrame(np.random.rand(4, 7))
df2_raw = pd.DataFrame(np.random.rand(7, 5), columns=list('efghi'))
s1_raw = pd.Series(np.random.rand(7))
s2_raw = pd.Series(np.random.rand(7))
df1 = DataFrame(df1_raw, chunk_size=(3, 2))
df2 = DataFrame(df2_raw, chunk_size=(3, 4))
# df.dot(df)
r = df1.dot(df2)
result = r.execute().fetch()
expected = df1_raw.dot(df2_raw)
pd.testing.assert_frame_equal(result, expected)
# test @
r = df1 @ df2
result = r.execute().fetch()
expected = df1_raw @ df2_raw
pd.testing.assert_frame_equal(result, expected)
series1 = Series(s1_raw, chunk_size=5)
# df.dot(series)
r = df1.dot(series1)
result = r.execute().fetch()
expected = df1_raw.dot(s1_raw)
pd.testing.assert_series_equal(result, expected)
# df.dot(2d_array)
r = df1.dot(df2_raw.to_numpy())
result = r.execute().fetch()
expected = df1_raw.dot(df2_raw.to_numpy())
pd.testing.assert_frame_equal(result, expected)
# df.dot(1d_array)
r = df1.dot(s1_raw.to_numpy())
result = r.execute().fetch()
expected = df1_raw.dot(s1_raw.to_numpy())
pd.testing.assert_series_equal(result, expected)
series2 = Series(s2_raw, chunk_size=4)
# series.dot(series)
r = series1.dot(series2)
result = r.execute().fetch()
expected = s1_raw.dot(s2_raw)
assert pytest.approx(result) == expected
# series.dot(df)
r = series1.dot(df2)
result = r.execute().fetch()
expected = s1_raw.dot(df2_raw)
pd.testing.assert_series_equal(result, expected)
# series.dot(2d_array)
r = series1.dot(df2_raw.to_numpy())
result = r.execute().fetch()
expected = s1_raw.dot(df2_raw.to_numpy())
np.testing.assert_almost_equal(result, expected)
# series.dot(1d_array)
r = series1.dot(s2_raw.to_numpy())
result = r.execute().fetch()
expected = s1_raw.dot(s2_raw.to_numpy())
assert pytest.approx(result) == expected
def testSortIndexExecution(self):
raw = pd.DataFrame(np.random.rand(100, 20), index=np.random.rand(100))
mdf = DataFrame(raw)
result = self.executor.execute_dataframe(mdf.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw)
mdf.sort_index(inplace=True)
result = self.executor.execute_dataframe(mdf, concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=30)
result = self.executor.execute_dataframe(mdf.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=20)
result = self.executor.execute_dataframe(
mdf.sort_index(ascending=False), concat=True)[0]
expected = raw.sort_index(ascending=False)
pd.testing.assert_frame_equal(result, expected)
executor = ExecutorForTest(storage=new_session().context)
mdf = DataFrame(raw, chunk_size=10)
result = executor.execute_dataframe(mdf.sort_index(ignore_index=True),
concat=True)[0]
try: # for python3.5
expected = raw.sort_index(ignore_index=True)
except TypeError:
expected = raw.sort_index()
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test axis=1
raw = pd.DataFrame(np.random.rand(10, 10), columns=np.random.rand(10))
mdf = DataFrame(raw)
result = self.executor.execute_dataframe(mdf.sort_index(axis=1),
concat=True)[0]
expected = raw.sort_index(axis=1)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=3)
result = self.executor.execute_dataframe(mdf.sort_index(axis=1),
concat=True)[0]
expected = raw.sort_index(axis=1)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=4)
result = self.executor.execute_dataframe(mdf.sort_index(
axis=1, ascending=False),
concat=True)[0]
expected = raw.sort_index(axis=1, ascending=False)
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(raw, chunk_size=4)
executor = ExecutorForTest(storage=new_session().context)
result = executor.execute_dataframe(mdf.sort_index(axis=1,
ignore_index=True),
concat=True)[0]
try: # for python3.5
expected = raw.sort_index(axis=1, ignore_index=True)
except TypeError:
expected = raw.sort_index(axis=1)
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test series
raw = pd.Series(np.random.rand(10, ), index=np.random.rand(10))
series = Series(raw)
result = self.executor.execute_dataframe(series.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=2)
result = self.executor.execute_dataframe(series.sort_index(),
concat=True)[0]
expected = raw.sort_index()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=3)
result = self.executor.execute_dataframe(
series.sort_index(ascending=False), concat=True)[0]
expected = raw.sort_index(ascending=False)
pd.testing.assert_series_equal(result, expected)
def test_to_datetime_execution(setup):
# scalar
r = to_datetime(1490195805, unit='s')
result = r.execute().fetch(extra_config={
'check_dtypes': False,
'check_shape': False
})
expected = pd.to_datetime(1490195805, unit='s')
assert pd.to_datetime(result) == expected
# test list like
raw = ['3/11/2000', '3/12/2000', '3/13/2000']
t = tensor(raw, chunk_size=2)
r = to_datetime(t, infer_datetime_format=True)
result = r.execute().fetch()
expected = pd.to_datetime(raw, infer_datetime_format=True)
pd.testing.assert_index_equal(result, expected)
# test series
raw_series = pd.Series(raw)
s = Series(raw_series, chunk_size=2)
r = to_datetime(s)
result = r.execute().fetch()
expected = pd.to_datetime(raw_series)
pd.testing.assert_series_equal(result, expected)
# test DataFrame
raw_df = pd.DataFrame({
'year': [2015, 2016],
'month': [2, 3],
'day': [4, 5]
})
df = DataFrame(raw_df, chunk_size=(1, 2))
r = to_datetime(df)
result = r.execute().fetch()
expected = pd.to_datetime(raw_df)
pd.testing.assert_series_equal(result, expected)
# test Index
raw_index = pd.Index([1, 2, 3])
s = Index(raw_index, chunk_size=2)
r = to_datetime(s)
result = r.execute().fetch()
expected = pd.to_datetime(raw_index)
pd.testing.assert_index_equal(result, expected)
# test raises == 'ignore'
raw = ['13000101']
r = to_datetime(raw, format='%Y%m%d', errors='ignore')
result = r.execute().fetch()
expected = pd.to_datetime(raw, format='%Y%m%d', errors='ignore')
pd.testing.assert_index_equal(result, expected)
# test unit
r = to_datetime([1490195805], unit='s')
result = r.execute().fetch()
expected = pd.to_datetime([1490195805], unit='s')
pd.testing.assert_index_equal(result, expected)
# test origin
r = to_datetime([1, 2, 3], unit='D', origin=pd.Timestamp('1960-01-01'))
result = r.execute().fetch()
expected = pd.to_datetime([1, 2, 3],
unit='D',
origin=pd.Timestamp('1960-01-01'))
pd.testing.assert_index_equal(result, expected)
def testSortValuesExecution(self):
distinct_opts = ['0'] if sys.platform.lower().startswith('win') else [
'0', '1'
]
for add_distinct in distinct_opts:
os.environ['PSRS_DISTINCT_COL'] = add_distinct
df = pd.DataFrame(np.random.rand(100, 10),
columns=['a' + str(i) for i in range(10)])
# test one chunk
mdf = DataFrame(df)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a6', 'a7'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a6', 'a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test psrs
mdf = DataFrame(df, chunk_size=10)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a3', 'a4']),
concat=True)[0]
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test ascending=False
result = self.executor.execute_dataframe(mdf.sort_values(
['a0', 'a1'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a0', 'a1'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a7'], ascending=False),
concat=True)[0]
expected = df.sort_values(['a7'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test multiindex
df2 = df.copy(deep=True)
df2.columns = pd.MultiIndex.from_product(
[list('AB'), list('CDEFG')])
mdf = DataFrame(df2, chunk_size=10)
result = self.executor.execute_dataframe(mdf.sort_values([('A',
'C')]),
concat=True)[0]
expected = df2.sort_values([('A', 'C')])
pd.testing.assert_frame_equal(result, expected)
# test rechunk
mdf = DataFrame(df, chunk_size=3)
result = self.executor.execute_dataframe(mdf.sort_values('a0'),
concat=True)[0]
expected = df.sort_values('a0')
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a3', 'a4']),
concat=True)[0]
expected = df.sort_values(['a3', 'a4'])
pd.testing.assert_frame_equal(result, expected)
# test other types
raw = pd.DataFrame(
{
'a': np.random.rand(10),
'b': np.random.randint(1000, size=10),
'c': np.random.rand(10),
'd': [np.random.bytes(10) for _ in range(10)],
'e': [pd.Timestamp(f'201{i}') for i in range(10)],
'f': [pd.Timedelta(f'{i} days') for i in range(10)]
}, )
mdf = DataFrame(raw, chunk_size=3)
for label in raw.columns:
result = self.executor.execute_dataframe(
mdf.sort_values(label), concat=True)[0]
expected = raw.sort_values(label)
pd.testing.assert_frame_equal(result, expected)
result = self.executor.execute_dataframe(mdf.sort_values(
['a', 'b', 'e'], ascending=False),
concat=True)[0]
expected = raw.sort_values(['a', 'b', 'e'], ascending=False)
pd.testing.assert_frame_equal(result, expected)
# test nan
df = pd.DataFrame({
'col1': ['A', 'A', 'B', 'B', 'D', 'C'],
'col2': [2, 1, 9, np.nan, 7, 4],
'col3': [0, 1, 9, 4, 2, 3],
})
mdf = DataFrame(df)
result = self.executor.execute_dataframe(mdf.sort_values(['col2']),
concat=True)[0]
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
mdf = DataFrame(df, chunk_size=3)
result = self.executor.execute_dataframe(mdf.sort_values(['col2']),
concat=True)[0]
expected = df.sort_values(['col2'])
pd.testing.assert_frame_equal(result, expected)
# test ignore_index
executor = ExecutorForTest(storage=new_session().context)
df = pd.DataFrame(np.random.rand(10, 3),
columns=['a' + str(i) for i in range(3)])
mdf = DataFrame(df, chunk_size=3)
result = executor.execute_dataframe(mdf.sort_values(
['a0', 'a1'], ignore_index=True),
concat=True)[0]
try: # for python3.5
expected = df.sort_values(['a0', 'a1'], ignore_index=True)
except TypeError:
expected = df.sort_values(['a0', 'a1'])
expected.index = pd.RangeIndex(len(expected))
pd.testing.assert_frame_equal(result, expected)
# test inplace
mdf = DataFrame(df)
mdf.sort_values('a0', inplace=True)
result = self.executor.execute_dataframe(mdf, concat=True)[0]
df.sort_values('a0', inplace=True)
pd.testing.assert_frame_equal(result, df)
# test unknown shape
df = pd.DataFrame({
'a': list(range(10)),
'b': np.random.random(10)
})
mdf = DataFrame(df, chunk_size=4)
filtered = mdf[mdf['a'] > 2]
result = self.executor.execute_dataframe(
filtered.sort_values(by='b'), concat=True)[0]
pd.testing.assert_frame_equal(result,
df[df['a'] > 2].sort_values(by='b'))
# test Series.sort_values
raw = pd.Series(np.random.rand(10))
series = Series(raw)
result = self.executor.execute_dataframe(series.sort_values(),
concat=True)[0]
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=3)
result = self.executor.execute_dataframe(series.sort_values(),
concat=True)[0]
expected = raw.sort_values()
pd.testing.assert_series_equal(result, expected)
series = Series(raw, chunk_size=2)
result = self.executor.execute_dataframe(
series.sort_values(ascending=False), concat=True)[0]
expected = raw.sort_values(ascending=False)
pd.testing.assert_series_equal(result, expected)
def testDataFrameCorrWith(self):
rs = np.random.RandomState(0)
raw_df = rs.rand(20, 10)
raw_df = pd.DataFrame(np.where(raw_df > 0.4, raw_df, np.nan),
columns=list('ABCDEFGHIJ'))
raw_df2 = rs.rand(20, 10)
raw_df2 = pd.DataFrame(np.where(raw_df2 > 0.4, raw_df2, np.nan),
columns=list('ACDEGHIJKL'))
raw_s = rs.rand(20)
raw_s = pd.Series(np.where(raw_s > 0.4, raw_s, np.nan))
raw_s2 = rs.rand(10)
raw_s2 = pd.Series(np.where(raw_s2 > 0.4, raw_s2, np.nan),
index=raw_df2.columns)
df = DataFrame(raw_df)
df2 = DataFrame(raw_df2)
result = df.corrwith(df2)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result, concat=True)[0],
raw_df.corrwith(raw_df2))
result = df.corrwith(df2, axis=1)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result, concat=True)[0],
raw_df.corrwith(raw_df2, axis=1))
result = df.corrwith(df2, method='kendall')
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result, concat=True)[0],
raw_df.corrwith(raw_df2, method='kendall'))
df = DataFrame(raw_df, chunk_size=4)
df2 = DataFrame(raw_df2, chunk_size=6)
s = Series(raw_s, chunk_size=5)
s2 = Series(raw_s2, chunk_size=5)
with self.assertRaises(Exception):
self.executor.execute_dataframe(df.corrwith(df2, method='kendall'),
concat=True)
result = df.corrwith(df2)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result,
concat=True)[0].sort_index(),
raw_df.corrwith(raw_df2).sort_index())
result = df.corrwith(df2, axis=1)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result,
concat=True)[0].sort_index(),
raw_df.corrwith(raw_df2, axis=1).sort_index())
result = df.corrwith(s)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result,
concat=True)[0].sort_index(),
raw_df.corrwith(raw_s).sort_index())
result = df.corrwith(s2, axis=1)
pd.testing.assert_series_equal(
self.executor.execute_dataframe(result,
concat=True)[0].sort_index(),
raw_df.corrwith(raw_s2, axis=1).sort_index())