Skip to content

Fix NewRowSynthesis failing with category data type #937

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

Open
cpruijsen wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix NewRowSynthesis failing with category data type #937

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
7 changes: 4 additions & 3 deletions sdmetrics/single_table/new_row_synthesis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,10 +136,11 @@ def compute_breakdown(
f'{abs(numerical_match_tolerance * row[field])}'
)
elif field in categorical_fields:
if real_data[field].dtype == 'O':
field_filter = f'`{field}` == {repr(row[field])}'
value = row[field]
if isinstance(value, str):
field_filter = f'`{field}` == {repr(value)}'
else:
field_filter = f'`{field}` == {row[field]}'
field_filter = f'`{field}` == {value}'

row_filter.append(field_filter)

Expand Down
66 changes: 66 additions & 0 deletions tests/unit/single_table/test_new_row_synthesis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,72 @@ def test_compute_breakdown_multi_line(self):
# Assert
assert score == 0.5

def test_compute_breakdown_with_category_dtype(self):
"""Test ``compute_breakdown`` when a categorical column uses pandas category dtype.

Expect that string categories are matched instead of raising UndefinedVariableError.
"""
# Setup
real_data = pd.DataFrame({
'gender': pd.Series(['F', 'M', 'F'], dtype='category'),
})
synthetic_data = pd.DataFrame({
'gender': ['F', 'X'],
})
metadata = {
'tables': {
'table': {
'columns': {
'gender': {'sdtype': 'categorical'},
},
}
}
}
metric = NewRowSynthesis()

# Run
result = metric.compute_breakdown(real_data, synthetic_data, metadata)

# Assert
assert result == {
'score': 0.5,
'num_new_rows': 1,
'num_matched_rows': 1,
}

def test_compute_breakdown_with_string_dtype(self):
"""Test ``compute_breakdown`` when a categorical column uses pandas string dtype.

Expect that string values are matched instead of raising UndefinedVariableError.
"""
# Setup
real_data = pd.DataFrame({
'gender': pd.Series(['F', 'M', 'F'], dtype='string'),
})
synthetic_data = pd.DataFrame({
'gender': ['F', 'X'],
})
metadata = {
'tables': {
'table': {
'columns': {
'gender': {'sdtype': 'categorical'},
},
}
}
}
metric = NewRowSynthesis()

# Run
result = metric.compute_breakdown(real_data, synthetic_data, metadata)

# Assert
assert result == {
'score': 0.5,
'num_new_rows': 1,
'num_matched_rows': 1,
}

def test_compute_with_sample_size(self):
"""Test the ``compute`` method with a sample size.

Expand Down