def test_size(self):
grouped = self.df.groupby(['A', 'B'])
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = self.df.groupby('A')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = self.df.groupby('B')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
df = DataFrame(np.random.choice(20, (1000, 3)), columns=list('abc'))
for sort, key in cart_product((False, True), ('a', 'b', ['a', 'b'])):
left = df.groupby(key, sort=sort).size()
right = df.groupby(key, sort=sort)['c'].apply(lambda a: a.shape[0])
assert_series_equal(left, right, check_names=False)
# GH11699
df = DataFrame([], columns=['A', 'B'])
out = Series([], dtype='int64', index=Index([], name='A'))
assert_series_equal(df.groupby('A').size(), out)
def test_size(df):
grouped = df.groupby(['A', 'B'])
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = df.groupby('A')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = df.groupby('B')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
df = DataFrame(np.random.choice(20, (1000, 3)), columns=list('abc'))
for sort, key in cart_product((False, True), ('a', 'b', ['a', 'b'])):
left = df.groupby(key, sort=sort).size()
right = df.groupby(key, sort=sort)['c'].apply(lambda a: a.shape[0])
tm.assert_series_equal(left, right, check_names=False)
# GH11699
df = DataFrame([], columns=['A', 'B'])
out = Series([], dtype='int64', index=Index([], name='A'))
tm.assert_series_equal(df.groupby('A').size(), out)
def test_xs_level_multiple(self):
text = """ A B C D E
one two three four
a b 10.0032 5 -0.5109 -2.3358 -0.4645 0.05076 0.3640
a q 20 4 0.4473 1.4152 0.2834 1.00661 0.1744
x q 30 3 -0.6662 -0.5243 -0.3580 0.89145 2.5838"""
df = read_csv(StringIO(text), sep=r'\s+', engine='python')
result = df.xs(('a', 4), level=['one', 'four'])
expected = df.xs('a').xs(4, level='four')
tm.assert_frame_equal(result, expected)
# this is a copy in 0.14
result = df.xs(('a', 4), level=['one', 'four'])
# setting this will give a SettingWithCopyError
# as we are trying to write a view
def f(x):
x[:] = 10
pytest.raises(com.SettingWithCopyError, f, result)
# GH2107
dates = lrange(20111201, 20111205)
ids = 'abcde'
idx = MultiIndex.from_tuples([x for x in cart_product(dates, ids)])
idx.names = ['date', 'secid']
df = DataFrame(np.random.randn(len(idx), 3), idx, ['X', 'Y', 'Z'])
rs = df.xs(20111201, level='date')
xp = df.loc[20111201, :]
tm.assert_frame_equal(rs, xp)
def test_series_groupby_nunique(self):
def check_nunique(df, keys, as_index=True):
for sort, dropna in cart_product((False, True), repeat=2):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
assert_series_equal(left, right, check_names=False)
days = date_range('2015-08-23', periods=10)
for n, m in cart_product(10**np.arange(2, 6), (10, 100, 1000)):
frame = DataFrame({
'jim': np.random.choice(list(ascii_lowercase), n),
'joe': np.random.choice(days, n),
'julie': np.random.randint(0, m, n)
})
check_nunique(frame, ['jim'])
check_nunique(frame, ['jim', 'joe'])
frame.loc[1::17, 'jim'] = None
frame.loc[3::37, 'joe'] = None
frame.loc[7::19, 'julie'] = None
frame.loc[8::19, 'julie'] = None
frame.loc[9::19, 'julie'] = None
check_nunique(frame, ['jim'])
check_nunique(frame, ['jim', 'joe'])
check_nunique(frame, ['jim'], as_index=False)
check_nunique(frame, ['jim', 'joe'], as_index=False)
def test_xs_level_multiple(self):
text = """ A B C D E
one two three four
a b 10.0032 5 -0.5109 -2.3358 -0.4645 0.05076 0.3640
a q 20 4 0.4473 1.4152 0.2834 1.00661 0.1744
x q 30 3 -0.6662 -0.5243 -0.3580 0.89145 2.5838"""
df = read_csv(StringIO(text), sep=r'\s+', engine='python')
result = df.xs(('a', 4), level=['one', 'four'])
expected = df.xs('a').xs(4, level='four')
tm.assert_frame_equal(result, expected)
# this is a copy in 0.14
result = df.xs(('a', 4), level=['one', 'four'])
# setting this will give a SettingWithCopyError
# as we are trying to write a view
def f(x):
x[:] = 10
pytest.raises(com.SettingWithCopyError, f, result)
# GH2107
dates = lrange(20111201, 20111205)
ids = 'abcde'
idx = MultiIndex.from_tuples([x for x in cart_product(dates, ids)])
idx.names = ['date', 'secid']
df = DataFrame(np.random.randn(len(idx), 3), idx, ['X', 'Y', 'Z'])
rs = df.xs(20111201, level='date')
xp = df.loc[20111201, :]
tm.assert_frame_equal(rs, xp)
def check_nunique(df, keys, as_index=True):
for sort, dropna in cart_product((False, True), repeat=2):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
assert_series_equal(left, right, check_names=False)
def check_nunique(df, keys, as_index=True):
for sort, dropna in cart_product((False, True), repeat=2):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
assert_series_equal(left, right, check_names=False)
def test_xs_integer_key():
# see gh-2107
dates = lrange(20111201, 20111205)
ids = 'abcde'
index = MultiIndex.from_tuples([x for x in cart_product(dates, ids)],
names=['date', 'secid'])
df = DataFrame(np.random.randn(len(index), 3), index, ['X', 'Y', 'Z'])
result = df.xs(20111201, level='date')
expected = df.loc[20111201, :]
tm.assert_frame_equal(result, expected)
def test_ngroup_cumcount_pair(self):
# brute force comparison for all small series
for p in cart_product(range(3), repeat=4):
df = DataFrame({'a': p})
g = df.groupby(['a'])
order = sorted(set(p))
ngroupd = [order.index(val) for val in p]
cumcounted = [p[:i].count(val) for i, val in enumerate(p)]
assert_series_equal(g.ngroup(), Series(ngroupd))
assert_series_equal(g.cumcount(), Series(cumcounted))
def test_xs_integer_key():
# see gh-2107
dates = lrange(20111201, 20111205)
ids = 'abcde'
index = MultiIndex.from_tuples(
[x for x in cart_product(dates, ids)],
names=['date', 'secid'])
df = DataFrame(
np.random.randn(len(index), 3), index, ['X', 'Y', 'Z'])
result = df.xs(20111201, level='date')
expected = df.loc[20111201, :]
tm.assert_frame_equal(result, expected)
def test_series_groupby_nunique(self):
def check_nunique(df, keys, as_index=True):
for sort, dropna in cart_product((False, True), repeat=2):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
assert_series_equal(left, right, check_names=False)
days = date_range('2015-08-23', periods=10)
for n, m in cart_product(10 ** np.arange(2, 6), (10, 100, 1000)):
frame = DataFrame({
'jim': np.random.choice(
list(ascii_lowercase), n),
'joe': np.random.choice(days, n),
'julie': np.random.randint(0, m, n)
})
check_nunique(frame, ['jim'])
check_nunique(frame, ['jim', 'joe'])
frame.loc[1::17, 'jim'] = None
frame.loc[3::37, 'joe'] = None
frame.loc[7::19, 'julie'] = None
frame.loc[8::19, 'julie'] = None
frame.loc[9::19, 'julie'] = None
check_nunique(frame, ['jim'])
check_nunique(frame, ['jim', 'joe'])
check_nunique(frame, ['jim'], as_index=False)
check_nunique(frame, ['jim', 'joe'], as_index=False)
df[df.PRICE == 24990].VOLUME.describe().values.tolist(),
df[df.PRICE == 25499].VOLUME.describe().values.tolist()
]
expected = pd.DataFrame(
data,
index=pd.Index([24990, 25499], name='PRICE'),
columns=['count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max'])
tm.assert_frame_equal(result, expected)
# nunique
# --------------------------------
@pytest.mark.parametrize("n, m",
cart_product(10**np.arange(2, 6), (10, 100, 1000)))
@pytest.mark.parametrize("sort, dropna", cart_product((False, True), repeat=2))
def test_series_groupby_nunique(n, m, sort, dropna):
def check_nunique(df, keys, as_index=True):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
tm.assert_series_equal(left, right, check_names=False)
days = date_range('2015-08-23', periods=10)
df = pd.DataFrame({'PRICE': prices,
'VOLUME': volumes})
result = df.groupby('PRICE').VOLUME.describe()
data = [df[df.PRICE == 24990].VOLUME.describe().values.tolist(),
df[df.PRICE == 25499].VOLUME.describe().values.tolist()]
expected = pd.DataFrame(data,
index=pd.Index([24990, 25499], name='PRICE'),
columns=['count', 'mean', 'std', 'min',
'25%', '50%', '75%', 'max'])
tm.assert_frame_equal(result, expected)
# nunique
# --------------------------------
@pytest.mark.parametrize("n, m", cart_product(10 ** np.arange(2, 6),
(10, 100, 1000)))
@pytest.mark.parametrize("sort, dropna", cart_product((False, True), repeat=2))
def test_series_groupby_nunique(n, m, sort, dropna):
def check_nunique(df, keys, as_index=True):
gr = df.groupby(keys, as_index=as_index, sort=sort)
left = gr['julie'].nunique(dropna=dropna)
gr = df.groupby(keys, as_index=as_index, sort=sort)
right = gr['julie'].apply(Series.nunique, dropna=dropna)
if not as_index:
right = right.reset_index(drop=True)
tm.assert_series_equal(left, right, check_names=False)
days = date_range('2015-08-23', periods=10)
