Skip to content

TST: add test for duplicated frame/test_analytics #21898

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jul 16, 2018
Merged

TST: add test for duplicated frame/test_analytics #21898

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
27a2bb7
TST: add test for duplicated frame/test_analytics
h-vetinari Jul 13, 2018
add4ac1
Split off tests for duplicates into separate file
h-vetinari Jul 14, 2018
e8a8d42
Change tests away from classes
h-vetinari Jul 14, 2018
9d428e2
Further cleanup
h-vetinari Jul 14, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
378 changes: 0 additions & 378 deletions pandas/tests/frame/test_analytics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1542,384 +1542,6 @@ def test_isin_empty_datetimelike(self):
result = df1_td.isin(df3)
tm.assert_frame_equal(result, expected)

# ----------------------------------------------------------------------
# Row deduplication

def test_drop_duplicates(self):
df = DataFrame({'AAA': ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'bar', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1, 1, 2, 2, 2, 2, 1, 2],
'D': lrange(8)})

# single column
result = df.drop_duplicates('AAA')
expected = df[:2]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('AAA', keep='last')
expected = df.loc[[6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('AAA', keep=False)
expected = df.loc[[]]
tm.assert_frame_equal(result, expected)
assert len(result) == 0

# multi column
expected = df.loc[[0, 1, 2, 3]]
result = df.drop_duplicates(np.array(['AAA', 'B']))
tm.assert_frame_equal(result, expected)
result = df.drop_duplicates(['AAA', 'B'])
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(('AAA', 'B'), keep='last')
expected = df.loc[[0, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(('AAA', 'B'), keep=False)
expected = df.loc[[0]]
tm.assert_frame_equal(result, expected)

# consider everything
df2 = df.loc[:, ['AAA', 'B', 'C']]

result = df2.drop_duplicates()
# in this case only
expected = df2.drop_duplicates(['AAA', 'B'])
tm.assert_frame_equal(result, expected)

result = df2.drop_duplicates(keep='last')
expected = df2.drop_duplicates(['AAA', 'B'], keep='last')
tm.assert_frame_equal(result, expected)

result = df2.drop_duplicates(keep=False)
expected = df2.drop_duplicates(['AAA', 'B'], keep=False)
tm.assert_frame_equal(result, expected)

# integers
result = df.drop_duplicates('C')
expected = df.iloc[[0, 2]]
tm.assert_frame_equal(result, expected)
result = df.drop_duplicates('C', keep='last')
expected = df.iloc[[-2, -1]]
tm.assert_frame_equal(result, expected)

df['E'] = df['C'].astype('int8')
result = df.drop_duplicates('E')
expected = df.iloc[[0, 2]]
tm.assert_frame_equal(result, expected)
result = df.drop_duplicates('E', keep='last')
expected = df.iloc[[-2, -1]]
tm.assert_frame_equal(result, expected)

# GH 11376
df = pd.DataFrame({'x': [7, 6, 3, 3, 4, 8, 0],
'y': [0, 6, 5, 5, 9, 1, 2]})
expected = df.loc[df.index != 3]
tm.assert_frame_equal(df.drop_duplicates(), expected)

df = pd.DataFrame([[1, 0], [0, 2]])
tm.assert_frame_equal(df.drop_duplicates(), df)

df = pd.DataFrame([[-2, 0], [0, -4]])
tm.assert_frame_equal(df.drop_duplicates(), df)

x = np.iinfo(np.int64).max / 3 * 2
df = pd.DataFrame([[-x, x], [0, x + 4]])
tm.assert_frame_equal(df.drop_duplicates(), df)

df = pd.DataFrame([[-x, x], [x, x + 4]])
tm.assert_frame_equal(df.drop_duplicates(), df)

# GH 11864
df = pd.DataFrame([i] * 9 for i in range(16))
df = df.append([[1] + [0] * 8], ignore_index=True)

for keep in ['first', 'last', False]:
assert df.duplicated(keep=keep).sum() == 0

@pytest.mark.parametrize('subset', ['a', ['a'], ['a', 'B']])
def test_duplicated_with_misspelled_column_name(self, subset):
# GH 19730
df = pd.DataFrame({'A': [0, 0, 1],
'B': [0, 0, 1],
'C': [0, 0, 1]})

with pytest.raises(KeyError):
df.duplicated(subset)

with pytest.raises(KeyError):
df.drop_duplicates(subset)

@pytest.mark.slow
def test_duplicated_do_not_fail_on_wide_dataframes(self):
# gh-21524
# Given the wide dataframe with a lot of columns
# with different (important!) values
data = {'col_{0:02d}'.format(i): np.random.randint(0, 1000, 30000)
for i in range(100)}
df = pd.DataFrame(data).T
result = df.duplicated()

# Then duplicates produce the bool pd.Series as a result
# and don't fail during calculation.
# Actual values doesn't matter here, though usually
# it's all False in this case
assert isinstance(result, pd.Series)
assert result.dtype == np.bool

def test_drop_duplicates_with_duplicate_column_names(self):
# GH17836
df = DataFrame([
[1, 2, 5],
[3, 4, 6],
[3, 4, 7]
], columns=['a', 'a', 'b'])

result0 = df.drop_duplicates()
tm.assert_frame_equal(result0, df)

result1 = df.drop_duplicates('a')
expected1 = df[:2]
tm.assert_frame_equal(result1, expected1)

def test_drop_duplicates_for_take_all(self):
df = DataFrame({'AAA': ['foo', 'bar', 'baz', 'bar',
'foo', 'bar', 'qux', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1, 1, 2, 2, 2, 2, 1, 2],
'D': lrange(8)})

# single column
result = df.drop_duplicates('AAA')
expected = df.iloc[[0, 1, 2, 6]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('AAA', keep='last')
expected = df.iloc[[2, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('AAA', keep=False)
expected = df.iloc[[2, 6]]
tm.assert_frame_equal(result, expected)

# multiple columns
result = df.drop_duplicates(['AAA', 'B'])
expected = df.iloc[[0, 1, 2, 3, 4, 6]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['AAA', 'B'], keep='last')
expected = df.iloc[[0, 1, 2, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['AAA', 'B'], keep=False)
expected = df.iloc[[0, 1, 2, 6]]
tm.assert_frame_equal(result, expected)

def test_drop_duplicates_tuple(self):
df = DataFrame({('AA', 'AB'): ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'bar', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1, 1, 2, 2, 2, 2, 1, 2],
'D': lrange(8)})

# single column
result = df.drop_duplicates(('AA', 'AB'))
expected = df[:2]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(('AA', 'AB'), keep='last')
expected = df.loc[[6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(('AA', 'AB'), keep=False)
expected = df.loc[[]] # empty df
assert len(result) == 0
tm.assert_frame_equal(result, expected)

# multi column
expected = df.loc[[0, 1, 2, 3]]
result = df.drop_duplicates((('AA', 'AB'), 'B'))
tm.assert_frame_equal(result, expected)

def test_drop_duplicates_NA(self):
# none
df = DataFrame({'A': [None, None, 'foo', 'bar',
'foo', 'bar', 'bar', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1.0, np.nan, np.nan, np.nan, 1., 1., 1, 1.],
'D': lrange(8)})

# single column
result = df.drop_duplicates('A')
expected = df.loc[[0, 2, 3]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('A', keep='last')
expected = df.loc[[1, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('A', keep=False)
expected = df.loc[[]] # empty df
tm.assert_frame_equal(result, expected)
assert len(result) == 0

# multi column
result = df.drop_duplicates(['A', 'B'])
expected = df.loc[[0, 2, 3, 6]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['A', 'B'], keep='last')
expected = df.loc[[1, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['A', 'B'], keep=False)
expected = df.loc[[6]]
tm.assert_frame_equal(result, expected)

# nan
df = DataFrame({'A': ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'bar', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1.0, np.nan, np.nan, np.nan, 1., 1., 1, 1.],
'D': lrange(8)})

# single column
result = df.drop_duplicates('C')
expected = df[:2]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('C', keep='last')
expected = df.loc[[3, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('C', keep=False)
expected = df.loc[[]] # empty df
tm.assert_frame_equal(result, expected)
assert len(result) == 0

# multi column
result = df.drop_duplicates(['C', 'B'])
expected = df.loc[[0, 1, 2, 4]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['C', 'B'], keep='last')
expected = df.loc[[1, 3, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates(['C', 'B'], keep=False)
expected = df.loc[[1]]
tm.assert_frame_equal(result, expected)

def test_drop_duplicates_NA_for_take_all(self):
# none
df = DataFrame({'A': [None, None, 'foo', 'bar',
'foo', 'baz', 'bar', 'qux'],
'C': [1.0, np.nan, np.nan, np.nan, 1., 2., 3, 1.]})

# single column
result = df.drop_duplicates('A')
expected = df.iloc[[0, 2, 3, 5, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('A', keep='last')
expected = df.iloc[[1, 4, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('A', keep=False)
expected = df.iloc[[5, 7]]
tm.assert_frame_equal(result, expected)

# nan

# single column
result = df.drop_duplicates('C')
expected = df.iloc[[0, 1, 5, 6]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('C', keep='last')
expected = df.iloc[[3, 5, 6, 7]]
tm.assert_frame_equal(result, expected)

result = df.drop_duplicates('C', keep=False)
expected = df.iloc[[5, 6]]
tm.assert_frame_equal(result, expected)

def test_drop_duplicates_inplace(self):
orig = DataFrame({'A': ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'bar', 'foo'],
'B': ['one', 'one', 'two', 'two',
'two', 'two', 'one', 'two'],
'C': [1, 1, 2, 2, 2, 2, 1, 2],
'D': lrange(8)})

# single column
df = orig.copy()
df.drop_duplicates('A', inplace=True)
expected = orig[:2]
result = df
tm.assert_frame_equal(result, expected)

df = orig.copy()
df.drop_duplicates('A', keep='last', inplace=True)
expected = orig.loc[[6, 7]]
result = df
tm.assert_frame_equal(result, expected)

df = orig.copy()
df.drop_duplicates('A', keep=False, inplace=True)
expected = orig.loc[[]]
result = df
tm.assert_frame_equal(result, expected)
assert len(df) == 0

# multi column
df = orig.copy()
df.drop_duplicates(['A', 'B'], inplace=True)
expected = orig.loc[[0, 1, 2, 3]]
result = df
tm.assert_frame_equal(result, expected)

df = orig.copy()
df.drop_duplicates(['A', 'B'], keep='last', inplace=True)
expected = orig.loc[[0, 5, 6, 7]]
result = df
tm.assert_frame_equal(result, expected)

df = orig.copy()
df.drop_duplicates(['A', 'B'], keep=False, inplace=True)
expected = orig.loc[[0]]
result = df
tm.assert_frame_equal(result, expected)

# consider everything
orig2 = orig.loc[:, ['A', 'B', 'C']].copy()

df2 = orig2.copy()
df2.drop_duplicates(inplace=True)
# in this case only
expected = orig2.drop_duplicates(['A', 'B'])
result = df2
tm.assert_frame_equal(result, expected)

df2 = orig2.copy()
df2.drop_duplicates(keep='last', inplace=True)
expected = orig2.drop_duplicates(['A', 'B'], keep='last')
result = df2
tm.assert_frame_equal(result, expected)

df2 = orig2.copy()
df2.drop_duplicates(keep=False, inplace=True)
expected = orig2.drop_duplicates(['A', 'B'], keep=False)
result = df2
tm.assert_frame_equal(result, expected)

# Rounding
def test_round(self):
# GH 2665
Expand Down
Loading