def test_reset_semantic_tags_with_time_index(sample_df):
semantic_tags = {
'signup_date': 'tag1',
}
dt = DataTable(sample_df,
time_index='signup_date',
semantic_tags=semantic_tags,
use_standard_tags=False)
assert dt['signup_date'].semantic_tags == {'time_index', 'tag1'}
dt = dt.reset_semantic_tags('signup_date', retain_index_tags=True)
assert dt['signup_date'].semantic_tags == {'time_index'}
dt = dt.reset_semantic_tags('signup_date')
assert dt['signup_date'].semantic_tags == set()
def test_reset_semantic_tags_with_index(sample_df):
semantic_tags = {
'id': 'tag1',
}
dt = DataTable(sample_df,
index='id',
semantic_tags=semantic_tags,
use_standard_tags=False)
assert dt['id'].semantic_tags == {'index', 'tag1'}
dt = dt.reset_semantic_tags('id', retain_index_tags=True)
assert dt['id'].semantic_tags == {'index'}
dt = dt.reset_semantic_tags('id')
assert dt['id'].semantic_tags == set()
def test_reset_selected_column_semantic_tags(sample_df):
semantic_tags = {'full_name': 'tag1', 'age': 'age'}
input_types = ['age', ['age'], {'age'}]
for input_type in input_types:
dt = DataTable(sample_df,
semantic_tags=semantic_tags,
use_standard_tags=True)
dt = dt.reset_semantic_tags(input_type)
assert dt.columns['full_name'].semantic_tags == {'tag1'}
assert dt.columns['age'].semantic_tags == {'numeric'}
def test_reset_all_semantic_tags(sample_df):
semantic_tags = {'full_name': 'tag1', 'age': 'age'}
dt = DataTable(sample_df,
semantic_tags=semantic_tags,
use_standard_tags=True)
new_dt = dt.reset_semantic_tags()
# Verify original tags were not changed
assert dt.columns['full_name'].semantic_tags == {'tag1'}
assert dt.columns['age'].semantic_tags == {'numeric', 'age'}
assert new_dt is not dt
assert new_dt.columns['full_name'].semantic_tags == set()
assert new_dt.columns['age'].semantic_tags == {'numeric'}
def test_underlying_index_on_update(sample_df):
if dd and isinstance(sample_df, dd.DataFrame):
pytest.xfail(
'Setting underlying index is not supported with Dask input')
if ks and isinstance(sample_df, ks.DataFrame):
pytest.xfail(
'Setting underlying index is not supported with Koalas input')
dt = DataTable(sample_df.copy(), index='id')
dt.update_dataframe(sample_df.tail(2))
assert (dt._dataframe.index == [2, 3]).all()
assert dt._dataframe.index.name is None
assert type(dt._dataframe.index) == pd.Int64Index
assert type(dt.to_dataframe().index) == pd.Int64Index
actual = dt.iloc[[0, 1]]
assert type(actual._dataframe.index) == pd.Index
assert type(actual.to_dataframe().index) == pd.Index
actual = dt.select(dt.index)
assert type(actual._dataframe.index) == pd.Int64Index
assert type(actual.to_dataframe().index) == pd.Int64Index
actual = dt[['age']]
assert type(actual._dataframe.index) == pd.Int64Index
assert type(actual.to_dataframe().index) == pd.Int64Index
actual = dt.drop(dt.index)
assert type(actual._dataframe.index) == pd.RangeIndex
assert type(actual.to_dataframe().index) == pd.RangeIndex
actual = dt.reset_semantic_tags(retain_index_tags=False)
assert type(actual._dataframe.index) == pd.RangeIndex
assert type(actual.to_dataframe().index) == pd.RangeIndex
actual = dt.set_types(retain_index_tags=False,
semantic_tags={'id': 'numeric'})
assert type(actual._dataframe.index) == pd.RangeIndex
assert type(actual.to_dataframe().index) == pd.RangeIndex
dt.pop(dt.index)
assert type(dt._dataframe.index) == pd.RangeIndex
assert type(dt.to_dataframe().index) == pd.RangeIndex
def test_reset_semantic_tags_invalid_column(sample_df):
dt = DataTable(sample_df)
error_msg = "Input contains columns that are not present in dataframe: 'invalid_column'"
with pytest.raises(LookupError, match=error_msg):
dt.reset_semantic_tags('invalid_column')
