def test_setitem_new_column(sample_df):
dt = DataTable(sample_df)
new_series = pd.Series([1, 2, 3])
if ks and isinstance(sample_df, ks.DataFrame):
dtype = 'int64'
new_series = ks.Series(new_series)
else:
dtype = 'Int64'
new_col = DataColumn(new_series, use_standard_tags=False)
assert new_col.name is None
dt['test_col2'] = new_col
updated_df = dt.to_dataframe()
assert 'test_col2' in dt.columns
assert dt['test_col2'].logical_type == Integer
assert dt['test_col2'].semantic_tags == set()
assert dt['test_col2'].name == 'test_col2'
assert dt['test_col2']._series.name == 'test_col2'
assert 'test_col2' in updated_df.columns
assert updated_df['test_col2'].dtype == dtype
# Standard tags and no logical type
new_series = pd.Series(['new', 'column', 'inserted'], name='test_col')
if ks and isinstance(sample_df, ks.DataFrame):
dtype = 'object'
new_series = ks.Series(new_series)
else:
dtype = 'category'
new_col = DataColumn(new_series, use_standard_tags=True)
dt['test_col'] = new_col
updated_df = dt.to_dataframe()
assert 'test_col' in dt.columns
assert dt['test_col'].logical_type == Categorical
assert dt['test_col'].semantic_tags == {'category'}
assert dt['test_col'].name == 'test_col'
assert dt['test_col']._series.name == 'test_col'
assert 'test_col' in updated_df.columns
assert updated_df['test_col'].dtype == dtype
# Add with logical type and semantic tag
new_series = pd.Series([1, 2, 3])
if ks and isinstance(sample_df, ks.DataFrame):
new_series = ks.Series(new_series)
new_col = DataColumn(new_series,
logical_type=Double,
use_standard_tags=False,
semantic_tags={'test_tag'})
dt['test_col3'] = new_col
updated_df = dt.to_dataframe()
assert 'test_col3' in dt.columns
assert dt['test_col3'].logical_type == Double
assert dt['test_col3'].semantic_tags == {'test_tag'}
assert dt['test_col3'].name == 'test_col3'
assert dt['test_col3']._series.name == 'test_col3'
assert 'test_col3' in updated_df.columns
assert updated_df['test_col3'].dtype == 'float'
def test_setitem_overwrite_column(sample_df):
dt = DataTable(sample_df,
index='id',
time_index='signup_date',
use_standard_tags=True)
# Change to column no change in types
original_col = dt['age']
new_series = pd.Series([1, 2, 3])
if ks and isinstance(sample_df, ks.DataFrame):
dtype = 'int64'
new_series = ks.Series(new_series)
else:
dtype = 'Int64'
overwrite_col = DataColumn(new_series, use_standard_tags=True)
dt['age'] = overwrite_col
updated_df = dt.to_dataframe()
assert 'age' in dt.columns
assert dt['age'].logical_type == original_col.logical_type
assert dt['age'].semantic_tags == original_col.semantic_tags
assert 'age' in updated_df.columns
assert updated_df['age'].dtype == dtype
assert original_col.to_series() is not dt['age'].to_series()
# Change dtype, logical types, and tags with conflicting use_standard_tags
original_col = dt['full_name']
new_series = pd.Series([True, False, False])
if ks and isinstance(sample_df, ks.DataFrame):
new_series = ks.Series(new_series)
dtype = 'bool'
else:
dtype = 'boolean'
overwrite_col = DataColumn(new_series.astype(dtype),
use_standard_tags=False,
semantic_tags='test_tag')
dt['full_name'] = overwrite_col
updated_df = dt.to_dataframe()
assert 'full_name' in dt.columns
assert dt['full_name'].logical_type == Boolean
assert dt['full_name'].semantic_tags == {'test_tag'}
assert 'full_name' in updated_df.columns
assert updated_df['full_name'].dtype == dtype
assert original_col.to_series() is not dt['full_name'].to_series()
def test_setitem_different_name(sample_df):
dt = DataTable(sample_df)
new_series = pd.Series([1, 2, 3, 4], name='wrong')
if ks and isinstance(sample_df, ks.DataFrame):
new_series = ks.Series(new_series)
warning = 'Name mismatch between wrong and id. DataColumn and underlying series name are now id'
with pytest.warns(ColumnNameMismatchWarning, match=warning):
dt['id'] = DataColumn(new_series,
use_standard_tags=False)
assert dt['id'].name == 'id'
assert dt['id'].to_series().name == 'id'
assert dt.to_dataframe()['id'].name == 'id'
assert 'wrong' not in dt.columns
new_series2 = pd.Series([1, 2, 3, 4], name='wrong2')
if ks and isinstance(sample_df, ks.DataFrame):
new_series2 = ks.Series(new_series2)
warning = 'Name mismatch between wrong2 and new_col. DataColumn and underlying series name are now new_col'
with pytest.warns(ColumnNameMismatchWarning, match=warning):
dt['new_col'] = DataColumn(new_series2,
use_standard_tags=False)
assert dt['new_col'].name == 'new_col'
assert dt['new_col'].to_series().name == 'new_col'
assert dt.to_dataframe()['new_col'].name == 'new_col'
assert 'wrong2' not in dt.columns
warning = 'Name mismatch between wrong and col_with_name. DataColumn and underlying series name are now col_with_name'
with pytest.warns(ColumnNameMismatchWarning, match=warning):
dt['col_with_name'] = DataColumn(new_series,
use_standard_tags=False, name='wrong')
assert dt['col_with_name'].name == 'col_with_name'
assert dt['col_with_name'].to_series().name == 'col_with_name'
assert dt.to_dataframe()['col_with_name'].name == 'col_with_name'
assert 'wrong' not in dt.columns