def test_issue502(summarizer, typeset):
series = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11],
dtype=pd.Int64Dtype())
result = describe_1d(series, summarizer, typeset)
assert result["min"] == 1
assert result["max"] == 11
def test_describe_unique(data, is_unique, p_distinct, p_unique):
"""Test the unique feature of 1D data"""
desc_1d = describe_1d(data)
if is_unique is not None:
assert desc_1d["p_unique"] == p_unique, "Describe 1D p_unique incorrect"
assert desc_1d["p_distinct"] == p_distinct, "Describe 1D p_distinct incorrect"
assert desc_1d["is_unique"] == is_unique, "Describe 1D should return unique"
def test_describe_unique(data, expected, summarizer, typeset):
"""Test the unique feature of 1D data"""
config["vars"]["num"]["low_categorical_threshold"] = 0
desc_1d = describe_1d(data, summarizer, typeset)
if expected["is_unique"] is not None:
assert (desc_1d["p_unique"] == expected["p_unique"]
), "Describe 1D p_unique incorrect"
assert (desc_1d["p_distinct"] == expected["p_distinct"]
), "Describe 1D p_distinct incorrect"
assert (desc_1d["is_unique"] == expected["is_unique"]
), "Describe 1D should return unique"
def multiprocess_1d(args: tuple) -> Tuple[str, dict]:
"""Wrapper to process series in parallel.
Args:
column: The name of the column.
series: The series values.
Returns:
A tuple with column and the series description.
"""
column, series = args
return column, describe_1d(config, series, summarizer, typeset)
def mock_multiprocess_1d(args, summarizer, typeset) -> Tuple[str, dict]:
"""Wrapper to process series in parallel.
copy of multiprocess_1d function in get_series_descriptions, summary.py
Args:
column: The name of the column.
series: The series values.
Returns:
A tuple with column and the series description.
"""
column, series = args
return column, describe_1d(series, summarizer, typeset)
def test_issue502():
series = pd.Series([1, 2, 3, 4, 5], dtype=pd.Int64Dtype())
result = describe_1d(series)
assert result["min"] == 1
assert result["max"] == 5