def test_dataframe_to_string():
with set_options(formatting={'nrows': 5, 'ncols': 8}):
# Test basic
df = DataFrame([('a', [1, 2, 3, 4, 5, 6]),
('b', [11, 12, 13, 14, 15, 16])])
string = str(df)
print(string)
assert string.splitlines()[-1] == '[1 more rows]'
# Test skipped columns
df = DataFrame([('a', [1, 2, 3, 4, 5, 6]),
('b', [11, 12, 13, 14, 15, 16]),
('c', [11, 12, 13, 14, 15, 16]),
('d', [11, 12, 13, 14, 15, 16])])
string = df.to_string(ncols=3)
print(string)
assert string.splitlines()[-2] == '[1 more rows]'
assert string.splitlines()[-1] == '[1 more columns]'
# Test masked
df = DataFrame([('a', [1, 2, 3, 4, 5, 6]),
('b', [11, 12, 13, 14, 15, 16])])
data = np.arange(6)
mask = np.zeros(1, dtype=np.uint8)
mask[0] = 0b00101101
masked = Series.from_masked_array(data, mask)
assert masked.null_count == 2
df['c'] = masked
# check data
values = list(masked)
validids = [0, 2, 3, 5]
densearray = masked.to_array()
np.testing.assert_equal(data[validids], densearray)
# valid position is corret
for i in validids:
assert data[i] == values[i]
# null position is correct
for i in range(len(values)):
if i not in validids:
assert values[i] is None
got = df.to_string(nrows=None)
print(got)
expect = '''
a b c
0 1 11 0
1 2 12
2 3 13 2
3 4 14 3
4 5 15
5 6 16 5
'''
# values should match despite whitespace difference
assert got.split() == expect.split()
def test_scan_boolean():
s = Series([0, -1, -300, 23, 4, -3, 0, 0, 100])
got = (s > 0).cumsum()
expect = pd.Series([False, False, False, True, True,
True, True, True, True])
assert_eq(expect, got)
got = (s > 0).astype(np.int32).cumsum()
expect = pd.Series([0, 0, 0, 1, 2, 2, 2, 2, 3])
assert_eq(expect, got)
def test_nonmatching_index_setitem(nrows):
np.random.seed(0)
gdf = DataFrame()
gdf['a'] = np.random.randint(2147483647, size=nrows)
gdf['b'] = np.random.randint(2147483647, size=nrows)
gdf = gdf.set_index('b')
test_values = np.random.randint(2147483647, size=nrows)
gdf['c'] = test_values
assert (len(test_values) == len(gdf['c']))
assert (gdf['c'].to_pandas().equals(
Series(test_values).set_index(gdf._index).to_pandas()))
def test_cummin(dtype, nelem):
if dtype == np.int8:
# to keep data in range
data = gen_rand(dtype, nelem, low=-2, high=2)
else:
data = gen_rand(dtype, nelem)
decimal = 4 if dtype == np.float32 else 6
# series
gs = Series(data)
ps = pd.Series(data)
np.testing.assert_array_almost_equal(gs.cummin(), ps.cummin(),
decimal=decimal)
# dataframe series (named series)
gdf = DataFrame()
gdf['a'] = Series(data)
pdf = pd.DataFrame()
pdf['a'] = pd.Series(data)
np.testing.assert_array_almost_equal(gdf.a.cummin(), pdf.a.cummin(),
decimal=decimal)
def test_series_indexing():
a1 = np.arange(20)
series = Series(a1)
# Indexing
sr1 = series[:12]
assert sr1.null_count == 0
np.testing.assert_equal(sr1.to_array(), a1[:12])
sr2 = sr1[3:]
assert sr2.null_count == 0
np.testing.assert_equal(sr2.to_array(), a1[3:12])
# Index with stride
sr3 = sr2[::2]
assert sr3.null_count == 0
np.testing.assert_equal(sr3.to_array(), a1[3:12:2])
def test_cummin_masked():
data = [1, 2, None, 4, 5]
float_types = ['float32', 'float64']
int_types = ['int8', 'int16', 'int32', 'int64']
for type_ in float_types:
gs = Series(data).astype(type_)
ps = pd.Series(data).astype(type_)
assert_eq(gs.cummin(), ps.cummin())
for type_ in int_types:
expected = pd.Series([1, 1, -1, 1, 1]).astype(type_)
gs = Series(data).astype(type_)
assert_eq(gs.cummin(), expected)
def test_series_basic():
# Make series from buffer
a1 = np.arange(10, dtype=np.float64)
series = Series(a1)
assert len(series) == 10
np.testing.assert_equal(series.to_array(), np.hstack([a1]))
# Add new buffer
a2 = np.arange(5)
series = series.append(a2)
assert len(series) == 15
np.testing.assert_equal(series.to_array(), np.hstack([a1, a2]))
# Ensure appending to previous buffer
a3 = np.arange(3)
series = series.append(a3)
assert len(series) == 18
a4 = np.hstack([a1, a2, a3])
np.testing.assert_equal(series.to_array(), a4)
def test_series_indexing(i1, i2, i3):
a1 = np.arange(20)
series = Series(a1)
# Indexing
sr1 = series[i1]
assert sr1.null_count == 0
np.testing.assert_equal(sr1.to_array(), a1[:12])
sr2 = sr1[i2]
assert sr2.null_count == 0
np.testing.assert_equal(sr2.to_array(), a1[3:12])
# Index with stride
sr3 = sr2[i3]
assert sr3.null_count == 0
np.testing.assert_equal(sr3.to_array(), a1[3:12:2])
# Integer indexing
if isinstance(i1, range):
for i in i1: # Python int-s
assert series[i] == a1[i]
if isinstance(i1, np.ndarray) and i1.dtype in index_dtypes:
for i in i1: # numpy integers
assert series[i] == a1[i]
def test_series_init_none():
# test for creating empty series
# 1: without initializing
sr1 = Series()
got = sr1.to_string()
print(got)
expect = '<empty Series of dtype=float64>'
# values should match despite whitespace difference
assert got.split() == expect.split()
# 2: Using `None` as a initializer
sr2 = Series(None)
got = sr2.to_string()
print(got)
expect = '<empty Series of dtype=float64>'
# values should match despite whitespace difference
assert got.split() == expect.split()
def test_dataframe_boolean_mask_Series(gdf):
mask = Series([True, False, True, False])
mask2 = Series([True, True, True, True])
mask3 = Series([True, True, True, True, True, True, True, True])
mask4 = Series([True]) # More likely to trigger an undefined memory read
mask5 = Series([False])
mask6 = Series([False, False, False, False])
gdf_masked = gdf[mask]
gdf_masked2 = gdf[mask2]
gdf_masked3 = gdf[mask3]
gdf_masked4 = gdf[mask4]
gdf_masked5 = gdf[mask5]
gdf_masked6 = gdf[mask6]
assert gdf_masked.shape[0] == 2
assert gdf_masked2.shape[0] == 4
assert gdf_masked3.shape[0] == 8
assert gdf_masked4.shape[0] == 1
assert gdf_masked5.shape[0] == 0
assert gdf_masked6.shape[0] == 0
def test_series_shape_empty():
ps = pd.Series()
cs = Series([])
assert ps.shape == cs.shape
def test_series_shape():
ps = pd.Series([1, 2, 3, 4])
cs = Series([1, 2, 3, 4])
assert ps.shape == cs.shape
def test_series_append():
a1 = np.arange(10, dtype=np.float64)
series = Series(a1)
# Add new buffer
a2 = np.arange(5)
series = series.append(a2)
assert len(series) == 15
np.testing.assert_equal(series.to_array(), np.hstack([a1, a2]))
# Ensure appending to previous buffer
a3 = np.arange(3)
series = series.append(a3)
assert len(series) == 18
a4 = np.hstack([a1, a2, a3])
np.testing.assert_equal(series.to_array(), a4)
# Appending different dtype
a5 = np.array([1, 2, 3], dtype=np.int32)
a6 = np.array([4.5, 5.5, 6.5], dtype=np.float64)
series = Series(a5).append(a6)
np.testing.assert_equal(series.to_array(), np.hstack([a5, a6]))
series = Series(a6).append(a5)
np.testing.assert_equal(series.to_array(), np.hstack([a6, a5]))
def test_series_basic():
# Make series from buffer
a1 = np.arange(10, dtype=np.float64)
series = Series(a1)
assert len(series) == 10
np.testing.assert_equal(series.to_array(), np.hstack([a1]))
np.testing.assert_equal(series.to_array(), np.hstack([a6, a5]))
index_dtypes = [np.int64, np.int32, np.int16, np.int8,
np.uint64, np.uint32, np.uint16, np.uint8]
@pytest.mark.parametrize(
'i1, i2, i3',
([(slice(None, 12), slice(3, None), slice(None, None, 2)),
(range(12), range(3, 12), range(0, 9, 2)),
(np.arange(12), np.arange(3, 12), np.arange(0, 9, 2)),
(list(range(12)), list(range(3, 12)), list(range(0, 9, 2))),
(pd.Series(range(12)), pd.Series(range(3, 12)),
pd.Series(range(0, 9, 2))),
(Series(range(12)), Series(range(3, 12)), Series(range(0, 9, 2))),
([i in range(12) for i in range(20)],
[i in range(3, 12) for i in range(12)],
[i in range(0, 9, 2) for i in range(9)]),
(np.array([i in range(12) for i in range(20)], dtype=bool),
np.array([i in range(3, 12) for i in range(12)], dtype=bool),
np.array([i in range(0, 9, 2) for i in range(9)], dtype=bool))]
+ [(np.arange(12, dtype=t), np.arange(3, 12, dtype=t),
np.arange(0, 9, 2, dtype=t)) for t in index_dtypes]),
ids=(['slice', 'range', 'numpy.array', 'list', 'pandas.Series',
'Series', 'list[bool]', 'numpy.array[bool]']
+ ['numpy.array[%s]' % t.__name__ for t in index_dtypes]))
def test_series_indexing(i1, i2, i3):
a1 = np.arange(20)
series = Series(a1)
# Indexing