def test_search_missing_values(self, caplog):
name = os.path.join(here, dir_data, "sample-missing-values.tsv")
ds = wrapper.Dataset(name, "real location", error=0.01)
ds.read_datafile()
ds.search_missing_values()
assert "Missing values found in column: colI" in caplog.text
assert "Missing values found in column: colJ" in caplog.text
def test_clean_column_names(self, caplog):
name = os.path.join(here, dir_data, "sample-column-names.tsv")
ds = wrapper.Dataset(name, "real location", error=0.01)
ds.read_datafile()
ds.clean_column_names()
assert "Column 'gene(name)' renamed to 'gene_name_'" in caplog.text
assert "Column 'coléèà' renamed to 'col_'" in caplog.text
assert "Column 'col[]()/' renamed to 'col_'" in caplog.text
def test_check_data_type_discrete_OK(self, caplog):
name = os.path.join(here, dir_data, "sample-discrete.tsv")
ds = wrapper.Dataset(name, "discrete")
ds.read_datafile()
ds.check_data_type()
assert "10 rows and 3 columns" in caplog.text
assert "Column 'colD': 2 different values" in caplog.text
assert "Column 'colE': 3 different values" in caplog.text
def test_check_data_type_real_location_not_OK(self, caplog):
name = os.path.join(here, dir_data, "sample-discrete.tsv")
ds = wrapper.Dataset(name, "real location", error=0.01)
ds.read_datafile()
assert "10 rows and 3 columns" in caplog.text
with pytest.raises(wrapper.CastFloat64Error,
match="could not convert string to float"):
ds.check_data_type()
def test_check_data_type_real_location_OK(self, caplog):
name = os.path.join(here, dir_data, "sample-real-location.tsv")
ds = wrapper.Dataset(name, "real location", error=0.01)
ds.read_datafile()
ds.check_data_type()
assert "10 rows and 4 columns" in caplog.text
assert "Column 'colA'" in caplog.text
assert "Column 'colB'" in caplog.text
assert "Column 'colC'" in caplog.text
def test_init(self):
ds = wrapper.Dataset("", "merged")
assert ds.input_file == ""
assert ds.data_type == "merged"
assert ds.error == None
assert ds.df == None
assert ds.column_meta == {}
assert ds.separator_char == "\t"
assert ds.missing_char == ""
def test_read_datafile(self, caplog):
name = os.path.join(here, dir_data, "sample-real-location.tsv")
ds = wrapper.Dataset(name, "real location", error=0.01)
ds.read_datafile()
assert "10 rows and 4 columns" in caplog.text
def test_check_duplicate_col_names(self):
ds = wrapper.Dataset("", "merged")
ds.input_file = os.path.join(here, dir_data, "input-dup-col.tsv")
with pytest.raises(wrapper.DuplicateColumnNameError,
match="Found duplicate column names"):
ds.check_duplicate_col_names()