Skip to content
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

Fix update and add tests for update and join. #848

Merged
merged 1 commit into from
Oct 1, 2019
Merged

Fix update and add tests for update and join. #848

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 7 additions & 5 deletions databricks/koalas/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5379,7 +5379,8 @@ def merge(self, right: 'DataFrame', how: str = 'inner',
column_index=column_index)
return DataFrame(internal)

def join(self, right: 'DataFrame', on: Optional[Union[str, List[str]]] = None,
def join(self, right: 'DataFrame',
on: Optional[Union[str, List[str], Tuple[str, ...], List[Tuple[str, ...]]]] = None,
how: str = 'left', lsuffix: str = '', rsuffix: str = '') -> 'DataFrame':
"""
Join columns of another DataFrame.
Expand Down Expand Up @@ -5633,13 +5634,14 @@ def update(self, other: 'DataFrame', join: str = 'left', overwrite: bool = True)
if isinstance(other, ks.Series):
other = DataFrame(other)

update_columns = list(set(self._internal.data_columns)
.intersection(set(other._internal.data_columns)))
update_columns = list(set(self._internal.column_index)
.intersection(set(other._internal.column_index)))
update_sdf = self.join(other[update_columns], rsuffix='_new')._sdf

for column_name in update_columns:
for column_index in update_columns:
column_name = self._internal.column_name_for(column_index)
old_col = scol_for(update_sdf, column_name)
new_col = scol_for(update_sdf, column_name + '_new')
new_col = scol_for(update_sdf, other._internal.column_name_for(column_index) + '_new')
if overwrite:
update_sdf = update_sdf.withColumn(column_name, F.when(new_col.isNull(), old_col)
.otherwise(new_col))
Expand Down
61 changes: 60 additions & 1 deletion databricks/koalas/tests/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1143,6 +1143,33 @@ def test_join(self):
join_kdf.sort_values(by=list(join_kdf.columns), inplace=True)
self.assert_eq(join_pdf.reset_index(drop=True), join_kdf.reset_index(drop=True))

# multi-index columns
columns1 = pd.MultiIndex.from_tuples([('x', 'key'), ('Y', 'A')])
columns2 = pd.MultiIndex.from_tuples([('x', 'key'), ('Y', 'B')])
pdf1.columns = columns1
pdf2.columns = columns2
kdf1.columns = columns1
kdf2.columns = columns2

join_pdf = pdf1.join(pdf2, lsuffix='_left', rsuffix='_right')
join_pdf.sort_values(by=list(join_pdf.columns), inplace=True)

join_kdf = kdf1.join(kdf2, lsuffix='_left', rsuffix='_right')
join_kdf.sort_values(by=list(join_kdf.columns), inplace=True)

self.assert_eq(join_pdf, join_kdf)

# check `on` parameter
join_pdf = pdf1.join(pdf2.set_index(('x', 'key')), on=[('x', 'key')],
lsuffix='_left', rsuffix='_right')
join_pdf.sort_values(by=list(join_pdf.columns), inplace=True)

join_kdf = kdf1.join(kdf2.set_index(('x', 'key')), on=[('x', 'key')],
lsuffix='_left', rsuffix='_right')
join_kdf.sort_values(by=list(join_kdf.columns), inplace=True)

self.assert_eq(join_pdf.reset_index(drop=True), join_kdf.reset_index(drop=True))

def test_replace(self):
pdf = pd.DataFrame({"name": ['Ironman', 'Captain America', 'Thor', 'Hulk'],
"weapon": ['Mark-45', 'Shield', 'Mjolnir', 'Smash']})
Expand Down Expand Up @@ -1195,7 +1222,7 @@ def test_replace(self):

def test_update(self):
# check base function
def get_data():
def get_data(left_columns=None, right_columns=None):
left_pdf = pd.DataFrame({'A': ['1', '2', '3', '4'],
'B': ['100', '200', np.nan, np.nan]},
columns=['A', 'B'])
Expand All @@ -1206,6 +1233,12 @@ def get_data():
columns=['A', 'B'])
right_kdf = ks.DataFrame({'B': ['x', None, 'y', None],
'C': ['100', '200', '300', '400']}, columns=['B', 'C'])
if left_columns is not None:
left_pdf.columns = left_columns
left_kdf.columns = left_columns
if right_columns is not None:
right_pdf.columns = right_columns
right_kdf.columns = right_columns
return left_kdf, left_pdf, right_kdf, right_pdf

left_kdf, left_pdf, right_kdf, right_pdf = get_data()
Expand All @@ -1221,6 +1254,32 @@ def get_data():
with self.assertRaises(NotImplementedError):
left_kdf.update(right_kdf, join='right')

# multi-index columns
left_columns = pd.MultiIndex.from_tuples([('X', 'A'), ('X', 'B')])
right_columns = pd.MultiIndex.from_tuples([('X', 'B'), ('Y', 'C')])

left_kdf, left_pdf, right_kdf, right_pdf = get_data(left_columns=left_columns,
right_columns=right_columns)
left_pdf.update(right_pdf)
left_kdf.update(right_kdf)
self.assert_eq(left_pdf.sort_values(by=[('X', 'A'), ('X', 'B')]),
left_kdf.sort_values(by=[('X', 'A'), ('X', 'B')]))

left_kdf, left_pdf, right_kdf, right_pdf = get_data(left_columns=left_columns,
right_columns=right_columns)
left_pdf.update(right_pdf, overwrite=False)
left_kdf.update(right_kdf, overwrite=False)
self.assert_eq(left_pdf.sort_values(by=[('X', 'A'), ('X', 'B')]),
left_kdf.sort_values(by=[('X', 'A'), ('X', 'B')]))

right_columns = pd.MultiIndex.from_tuples([('Y', 'B'), ('Y', 'C')])
left_kdf, left_pdf, right_kdf, right_pdf = get_data(left_columns=left_columns,
right_columns=right_columns)
left_pdf.update(right_pdf)
left_kdf.update(right_kdf)
self.assert_eq(left_pdf.sort_values(by=[('X', 'A'), ('X', 'B')]),
left_kdf.sort_values(by=[('X', 'A'), ('X', 'B')]))

def test_pivot_table_dtypes(self):
pdf = pd.DataFrame({'a': [4, 2, 3, 4, 8, 6],
'b': [1, 2, 2, 4, 2, 4],
Expand Down