def test_join_on_fails_with_different_left_index(self):
with pytest.raises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(10, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
merge(df, df2, right_on='b', left_index=True)
def test_join_on_fails_with_different_column_counts(self):
with tm.assertRaises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
merge(df, df2, right_on='a', left_on=['a', 'b'])
def test_join_on_fails_with_different_column_counts(self):
with tm.assertRaises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
merge(df, df2, right_on='a', left_on=['a', 'b'])
def test_join_on_fails_with_different_left_index(self):
with pytest.raises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(10, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
merge(df, df2, right_on='b', left_index=True)
def test_join_on_fails_with_different_column_counts(self):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
msg = r"len\(right_on\) must equal len\(left_on\)"
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='a', left_on=['a', 'b'])
def test_join_on_fails_with_different_column_counts(self):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
msg = r"len\(right_on\) must equal len\(left_on\)"
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='a', left_on=['a', 'b'])
def test_join_on_fails_with_different_left_index(self):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(3, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
msg = (r'len\(right_on\) must equal the number of levels in the index'
' of "left"')
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='b', left_index=True)
def test_join_on_fails_with_different_left_index(self):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(3, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
msg = (r'len\(right_on\) must equal the number of levels in the index'
' of "left"')
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='b', left_index=True)
def test_join_on_fails_with_different_column_counts(self):
df = DataFrame(
{"a": np.random.choice(["m", "f"], size=3), "b": np.random.randn(3)}
)
df2 = DataFrame(
{"a": np.random.choice(["m", "f"], size=10), "b": np.random.randn(10)},
index=tm.makeCustomIndex(10, 2),
)
msg = r"len\(right_on\) must equal len\(left_on\)"
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on="a", left_on=["a", "b"])
def test_join_on_fails_with_different_right_index(self):
df = DataFrame(
{"a": np.random.choice(["m", "f"], size=3), "b": np.random.randn(3)}
)
df2 = DataFrame(
{"a": np.random.choice(["m", "f"], size=10), "b": np.random.randn(10)},
index=tm.makeCustomIndex(10, 2),
)
msg = (
r"len\(left_on\) must equal the number of levels in the index" ' of "right"'
)
with pytest.raises(ValueError, match=msg):
merge(df, df2, left_on="a", right_index=True)
def test_fails_on_no_datetime_index():
index_names = ('Int64Index', 'Index', 'Float64Index', 'MultiIndex')
index_funcs = (tm.makeIntIndex,
tm.makeUnicodeIndex, tm.makeFloatIndex,
lambda m: tm.makeCustomIndex(m, 2))
n = 2
for name, func in zip(index_names, index_funcs):
index = func(n)
df = DataFrame({'a': np.random.randn(n)}, index=index)
msg = ("Only valid with DatetimeIndex, TimedeltaIndex "
"or PeriodIndex, but got an instance of %r" % name)
with pytest.raises(TypeError, match=msg):
df.groupby(TimeGrouper('D'))
def metadata_column_headers(request):
"""Make a list of metadata column headers.
Returns:
list: A metadata column header list whose length is between 0
and `MAX_METADATA_COLS`.
"""
if request.param is 0:
return list()
# pandas bug (?) in makeCustomIndex when nentries = 1
elif request.param is 1:
return ['M_l0_g0']
else:
return list(makeCustomIndex(request.param, 1, prefix='M'))
def test_fails_on_no_datetime_index(self):
index_names = ('Int64Index', 'PeriodIndex', 'Index', 'Float64Index',
'MultiIndex')
index_funcs = (tm.makeIntIndex, tm.makePeriodIndex,
tm.makeUnicodeIndex, tm.makeFloatIndex,
lambda m: tm.makeCustomIndex(m, 2))
n = 2
for name, func in zip(index_names, index_funcs):
index = func(n)
df = DataFrame({'a': np.random.randn(n)}, index=index)
with tm.assertRaisesRegexp(TypeError,
"axis must be a DatetimeIndex, "
"but got an instance of %r" % name):
df.groupby(TimeGrouper('D'))
def test_fails_on_no_datetime_index(self):
index_names = ('Int64Index', 'PeriodIndex', 'Index', 'Float64Index',
'MultiIndex')
index_funcs = (tm.makeIntIndex, tm.makePeriodIndex,
tm.makeUnicodeIndex, tm.makeFloatIndex,
lambda m: tm.makeCustomIndex(m, 2))
n = 2
for name, func in zip(index_names, index_funcs):
index = func(n)
df = DataFrame({'a': np.random.randn(n)}, index=index)
with tm.assertRaisesRegexp(
TypeError, "axis must be a DatetimeIndex, "
"but got an instance of %r" % name):
df.groupby(TimeGrouper('D'))
pd.Series(np.arange(4,9)) # using the numpy function pd.Series(np.linspace(0,9,5)) # allows to specify the number of values to be created btw boundaries pd.Series(np.random.normal(size=5)) np.random.randint(50,101,10) a = np.array([4] * 16) a[1::] = [42] * 15 a[1:8:2] = 16 import pandas.util.testing as tm tm.N, tm.K = 5,3 tm.makeFloatSeries(), tm.makeBoolIndex(), tm.makeCategoricalIndex() tm.makeCustomIndex(nentries=4,nlevels=2), tm.makeFloatIndex(), tm.makeIntIndex() tm.makeMultiIndex(), tm.makeRangeIndex(), tm.makeIntervalIndex() # All possible combinations (Permutations) from itertools import permutations my_list = [1,2,3] perm = list(permutations(my_list)) #(1, 2, 3) #(1, 3, 2) #(2, 1, 3) #(2, 3, 1) #(3, 1, 2) #(3, 2, 1)
# Errors
grouped = df.groupby(grouper, group_keys=False)
def f(df):
return df['close'] / df['open']
# it works!
result = grouped.apply(f)
tm.assert_index_equal(result.index, df.index)
@pytest.mark.parametrize('name, func',
[('Int64Index', tm.makeIntIndex),
('Index', tm.makeUnicodeIndex),
('Float64Index', tm.makeFloatIndex),
('MultiIndex', lambda m: tm.makeCustomIndex(m, 2))])
def test_fails_on_no_datetime_index(name, func):
n = 2
index = func(n)
df = DataFrame({'a': np.random.randn(n)}, index=index)
msg = ("Only valid with DatetimeIndex, TimedeltaIndex "
"or PeriodIndex, but got an instance of '{}'".format(name))
with pytest.raises(TypeError, match=msg):
df.groupby(TimeGrouper('D'))
def test_aaa_group_order():
# GH 12840
# check TimeGrouper perform stable sorts
n = 20
def test_raise_on_panel4d_with_multiindex(self, parser, engine):
tm.skip_if_no_ne()
p4d = tm.makePanel4D(7)
p4d.items = tm.makeCustomIndex(len(p4d.items), nlevels=2)
with pytest.raises(NotImplementedError):
pd.eval('p4d + 1', parser=parser, engine=engine)
class TestResolvePath(object):
archive = '.\\'
headers = makeCustomIndex(7, 1, prefix='C')
multi_schema = SortedDict({'0': headers[1], '1': headers[3]})
multi_schema2 = SortedDict({
'0': headers[0],
'1': headers[2],
'2': headers[3]
})
multi_schema3 = SortedDict({'0': headers[1], '1': headers[6]})
single_schema = SortedDict({
'0': headers[0],
})
single_schema2 = SortedDict({'0': headers[4]})
@staticmethod
def data_gen_invalid(row: int, col: int):
valmap_invalid = [
['val', 'val', 'xxx', 'val'],
['val', nan, 'val', 'val'],
['val', nan, 'val', nan],
[nan, nan, 'val', 'xxx'], # noqa: E201
['xxx', nan, 'val', nan]
]
if row < len(valmap_invalid):
if col < len(valmap_invalid[row]):
return valmap_invalid[row][col]
return make_dataframe_value(row, col)
@staticmethod
def data_gen(row: int, col: int):
valmap = [
['val', 'val', 'val', 'val'],
['val', nan, 'val', 'val'],
['val', nan, 'val', nan],
[nan, nan, 'val', nan], # noqa: E201
[nan, nan, 'val', nan] # noqa: E201
]
if row < len(valmap):
if col < len(valmap[row]):
return valmap[row][col]
return make_dataframe_value(row, col)
@staticmethod
def data_gen_normalizable(row: int, col: int):
valmap = [
['Value 1.', 'Value 1.', 'Value 1.', 'Value 1.'],
['Value 1.', nan, 'Value 1.', 'Value 1.'],
['Value 1.', nan, 'Value 1.', nan],
[nan, nan, 'Value 1.', nan], # noqa: E201
[nan, nan, 'Value 1.', nan] # noqa: E201
]
if row < len(valmap):
if col < len(valmap[row]):
return valmap[row][col]
return make_dataframe_value(row, col)
@pytest.mark.parametrize('schema, expected', [
(single_schema, join(archive, 'val')),
(multi_schema, join(archive, 'val', 'val')),
(multi_schema2, join(archive, 'val', 'val', 'val')),
])
def test_resolve_path(self, schema, expected):
data = make_dataframe(5, 4, data_gen_f=TestResolvePath.data_gen)
actual = resolve_path(self.archive, schema, data)
assert actual == expected
@pytest.mark.parametrize(
'schema, expected',
[(single_schema, join(archive, 'value_1')),
(multi_schema, join(archive, 'value_1', 'value_1')),
(multi_schema2, join(archive, 'value_1', 'value_1', 'value_1'))])
def test_resolve_path_normalized(self, schema, expected):
data = make_dataframe(5,
4,
data_gen_f=TestResolvePath.data_gen_normalizable)
actual = resolve_path(self.archive, schema, data)
assert actual == expected
@pytest.mark.parametrize('schema', [
single_schema2,
multi_schema3,
])
def test_resolve_path_indexerror(self, schema):
data = make_dataframe(5, 4, data_gen_f=TestResolvePath.data_gen)
with pytest.raises(IndexError):
resolve_path(self.archive, schema, data)
@pytest.mark.parametrize('schema', [
single_schema,
multi_schema,
multi_schema2,
])
def test_resolve_path_valueerror(self, schema):
data = make_dataframe(5,
4,
data_gen_f=TestResolvePath.data_gen_invalid)
with pytest.raises(ValueError):
resolve_path(self.archive, schema, data)
def check_raise_on_panel_with_multiindex(self, parser, engine):
tm.skip_if_no_ne()
p = tm.makePanel(7)
p.items = tm.makeCustomIndex(len(p.items), nlevels=2)
with tm.assertRaises(NotImplementedError):
pd.eval('p + 1', parser=parser, engine=engine)
def test_raise_on_panel_with_multiindex(self, parser, engine):
p = tm.makePanel(7)
p.items = tm.makeCustomIndex(len(p.items), nlevels=2)
with pytest.raises(NotImplementedError):
pd.eval('p + 1', parser=parser, engine=engine)
def test_raise_on_panel_with_multiindex(self, parser, engine):
p = tm.makePanel(7)
p.items = tm.makeCustomIndex(len(p.items), nlevels=2)
with pytest.raises(NotImplementedError):
pd.eval('p + 1', parser=parser, engine=engine)
def f(df):
return df["close"] / df["open"]
# it works!
result = grouped.apply(f)
tm.assert_index_equal(result.index, df.index)
@pytest.mark.parametrize(
"name, func",
[
("Int64Index", tm.makeIntIndex),
("Index", tm.makeUnicodeIndex),
("Float64Index", tm.makeFloatIndex),
("MultiIndex", lambda m: tm.makeCustomIndex(m, 2)),
],
)
def test_fails_on_no_datetime_index(name, func):
n = 2
index = func(n)
df = DataFrame({"a": np.random.randn(n)}, index=index)
msg = ("Only valid with DatetimeIndex, TimedeltaIndex "
f"or PeriodIndex, but got an instance of '{name}'")
with pytest.raises(TypeError, match=msg):
df.groupby(Grouper(freq="D"))
def test_aaa_group_order():
# GH 12840
# Errors
grouped = df.groupby(grouper, group_keys=False)
def f(df):
return df['close'] / df['open']
# it works!
result = grouped.apply(f)
tm.assert_index_equal(result.index, df.index)
@pytest.mark.parametrize('name, func', [
('Int64Index', tm.makeIntIndex),
('Index', tm.makeUnicodeIndex),
('Float64Index', tm.makeFloatIndex),
('MultiIndex', lambda m: tm.makeCustomIndex(m, 2))
])
def test_fails_on_no_datetime_index(name, func):
n = 2
index = func(n)
df = DataFrame({'a': np.random.randn(n)}, index=index)
msg = ("Only valid with DatetimeIndex, TimedeltaIndex "
"or PeriodIndex, but got an instance of '{}'".format(name))
with pytest.raises(TypeError, match=msg):
df.groupby(TimeGrouper('D'))
def test_aaa_group_order():
# GH 12840
# check TimeGrouper perform stable sorts
def check_raise_on_panel4d_with_multiindex(self, parser, engine):
tm.skip_if_no_ne()
p4d = tm.makePanel4D(7)
p4d.items = tm.makeCustomIndex(len(p4d.items), nlevels=2)
with tm.assertRaises(NotImplementedError):
pd.eval('p4d + 1', parser=parser, engine=engine)