def test_returns_empty_list_for_unique_columns(self):
csv_data = "aaa,bbb\n" "1,1\n" "2,2\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["aaa", "bbb"]
assert check_duplicate_columns(df, "file") == []
def test_returns_empty_list_if_column_end_with_number_but_is_not_duplicate(
self):
csv_data = "taxon taxon,taxon taxon f.1\n" "1,1\n" "2,2\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["taxon taxon", "taxon taxon f.1"]
assert check_duplicate_columns(df, "file") == []
def test_returns_False_if_space_columns_have_similiar_names_but_different_values(
self, ):
csv_data = "a,a \n" "1,3\n" "2,4\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["a", "a "]
expected = [{
"bad_column": "a ",
"filename": "file",
"same_value": False
}]
assert check_duplicate_columns(df, "file") == expected
def test_returns_True_if_space_columns_have_similiar_names_and_same_values(
self):
csv_data = "a,a \n" "1,1\n" "2,2\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["a", "a "]
expected = [{
"bad_column": "a ",
"filename": "file",
"same_value": True
}]
assert check_duplicate_columns(df, "file") == expected
def test_returns_False_if_duplicate_columns_have_different_values(self):
csv_data = "a,a,a\n" "1,3,3\n" "2,4,4\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["a", "a.1", "a.2"]
expected = [
{
"filename": "file",
"bad_column": "a.1",
"same_value": False
},
{
"filename": "file",
"bad_column": "a.2",
"same_value": False
},
]
assert check_duplicate_columns(df, "file") == expected
def test_returns_True_if_duplicate_columns_have_same_value(self):
csv_data = "a,a,a\n" "1,1,1\n" "2,2,2\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["a", "a.1", "a.2"]
expected = [
{
"filename": "file",
"bad_column": "a.1",
"same_value": True
},
{
"filename": "file",
"bad_column": "a.2",
"same_value": True
},
]
assert check_duplicate_columns(df, "file") == expected
def test_returns_empty_list_if_space_columns_have_differnt_names(self):
csv_data = "a,b \n" "1,1\n" "2,2\n"
df = pd.read_csv(StringIO(csv_data))
assert list(df.columns) == ["a", "b "]
assert check_duplicate_columns(df, "file") == []