def test_filter_maintains_ordering(self):
# Simple case: index is sequential. #4621
df = DataFrame({
'pid': [1, 1, 1, 2, 2, 3, 3, 3],
'tag': [23, 45, 62, 24, 45, 34, 25, 62]
})
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
# Now index is sequentially decreasing.
df.index = np.arange(len(df) - 1, -1, -1)
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
# Index is shuffled.
SHUFFLED = [4, 6, 7, 2, 1, 0, 5, 3]
df.index = df.index[SHUFFLED]
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
def test_groupby_multi_categorical_as_index(self):
# GH13204
df = DataFrame({"cat": Categorical([1, 2, 2], [1, 2, 3]), "A": [10, 11, 11], "B": [101, 102, 103]})
result = df.groupby(["cat", "A"], as_index=False).sum()
expected = DataFrame(
{
"cat": Categorical([1, 1, 2, 2, 3, 3]),
"A": [10, 11, 10, 11, 10, 11],
"B": [101.0, nan, nan, 205.0, nan, nan],
},
columns=["cat", "A", "B"],
)
tm.assert_frame_equal(result, expected)
# function grouper
f = lambda r: df.loc[r, "A"]
result = df.groupby(["cat", f], as_index=False).sum()
expected = DataFrame(
{
"cat": Categorical([1, 1, 2, 2, 3, 3]),
"A": [10.0, nan, nan, 22.0, nan, nan],
"B": [101.0, nan, nan, 205.0, nan, nan],
},
columns=["cat", "A", "B"],
)
tm.assert_frame_equal(result, expected)
# another not in-axis grouper (conflicting names in index)
s = Series(["a", "b", "b"], name="cat")
result = df.groupby(["cat", s], as_index=False).sum()
expected = DataFrame(
{
"cat": Categorical([1, 1, 2, 2, 3, 3]),
"A": [10.0, nan, nan, 22.0, nan, nan],
"B": [101.0, nan, nan, 205.0, nan, nan],
},
columns=["cat", "A", "B"],
)
tm.assert_frame_equal(result, expected)
# is original index dropped?
expected = DataFrame(
{
"cat": Categorical([1, 1, 2, 2, 3, 3]),
"A": [10, 11, 10, 11, 10, 11],
"B": [101.0, nan, nan, 205.0, nan, nan],
},
columns=["cat", "A", "B"],
)
for name in [None, "X", "B", "cat"]:
df.index = Index(list("abc"), name=name)
result = df.groupby(["cat", "A"], as_index=False).sum()
tm.assert_frame_equal(result, expected, check_index_type=True)
def test_filter_maintains_ordering(self):
# Simple case: index is sequential. #4621
df = DataFrame({'pid': [1, 1, 1, 2, 2, 3, 3, 3],
'tag': [23, 45, 62, 24, 45, 34, 25, 62]})
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
# Now index is sequentially decreasing.
df.index = np.arange(len(df) - 1, -1, -1)
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
# Index is shuffled.
SHUFFLED = [4, 6, 7, 2, 1, 0, 5, 3]
df.index = df.index[SHUFFLED]
s = df['pid']
grouped = df.groupby('tag')
actual = grouped.filter(lambda x: len(x) > 1)
expected = df.iloc[[1, 2, 4, 7]]
assert_frame_equal(actual, expected)
grouped = s.groupby(df['tag'])
actual = grouped.filter(lambda x: len(x) > 1)
expected = s.iloc[[1, 2, 4, 7]]
assert_series_equal(actual, expected)
def test_groupby_multi_categorical_as_index(self):
# GH13204
df = DataFrame({'cat': Categorical([1, 2, 2], [1, 2, 3]),
'A': [10, 11, 11],
'B': [101, 102, 103]})
result = df.groupby(['cat', 'A'], as_index=False).sum()
expected = DataFrame({'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10, 11, 10, 11, 10, 11],
'B': [101.0, nan, nan, 205.0, nan, nan]},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# function grouper
f = lambda r: df.loc[r, 'A']
result = df.groupby(['cat', f], as_index=False).sum()
expected = DataFrame({'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10.0, nan, nan, 22.0, nan, nan],
'B': [101.0, nan, nan, 205.0, nan, nan]},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# another not in-axis grouper (conflicting names in index)
s = Series(['a', 'b', 'b'], name='cat')
result = df.groupby(['cat', s], as_index=False).sum()
expected = DataFrame({'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10.0, nan, nan, 22.0, nan, nan],
'B': [101.0, nan, nan, 205.0, nan, nan]},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# is original index dropped?
expected = DataFrame({'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10, 11, 10, 11, 10, 11],
'B': [101.0, nan, nan, 205.0, nan, nan]},
columns=['cat', 'A', 'B'])
group_columns = ['cat', 'A']
for name in [None, 'X', 'B', 'cat']:
df.index = Index(list("abc"), name=name)
if name in group_columns and name in df.index.names:
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
result = df.groupby(group_columns, as_index=False).sum()
else:
result = df.groupby(group_columns, as_index=False).sum()
tm.assert_frame_equal(result, expected, check_index_type=True)
def test_groupby_multi_categorical_as_index(self):
# GH13204
df = DataFrame({
'cat': Categorical([1, 2, 2], [1, 2, 3]),
'A': [10, 11, 11],
'B': [101, 102, 103]
})
result = df.groupby(['cat', 'A'], as_index=False).sum()
expected = DataFrame(
{
'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10, 11, 10, 11, 10, 11],
'B': [101.0, nan, nan, 205.0, nan, nan]
},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# function grouper
f = lambda r: df.loc[r, 'A']
result = df.groupby(['cat', f], as_index=False).sum()
expected = DataFrame(
{
'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10.0, nan, nan, 22.0, nan, nan],
'B': [101.0, nan, nan, 205.0, nan, nan]
},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# another not in-axis grouper (conflicting names in index)
s = Series(['a', 'b', 'b'], name='cat')
result = df.groupby(['cat', s], as_index=False).sum()
expected = DataFrame(
{
'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10.0, nan, nan, 22.0, nan, nan],
'B': [101.0, nan, nan, 205.0, nan, nan]
},
columns=['cat', 'A', 'B'])
tm.assert_frame_equal(result, expected)
# is original index dropped?
expected = DataFrame(
{
'cat': Categorical([1, 1, 2, 2, 3, 3]),
'A': [10, 11, 10, 11, 10, 11],
'B': [101.0, nan, nan, 205.0, nan, nan]
},
columns=['cat', 'A', 'B'])
group_columns = ['cat', 'A']
for name in [None, 'X', 'B', 'cat']:
df.index = Index(list("abc"), name=name)
if name in group_columns and name in df.index.names:
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
result = df.groupby(group_columns, as_index=False).sum()
else:
result = df.groupby(group_columns, as_index=False).sum()
tm.assert_frame_equal(result, expected, check_index_type=True)
