def drop_duplicate_column(comparable: Compare):
header_duplicate = [
header[Field.column_name.value] for header in comparable.header
if header[Field.column_type.value] == Field.duplicate.value
]
comparable.data_frame = comparable.data_frame.drop(
columns=header_duplicate)
def drop_not_checked_column(comparable: Compare):
header_not_checked = [
header[Field.column_name.value] for header in comparable.header
if header[Field.column_type.value] == Field.not_checked.value
]
comparable.data_frame = comparable.data_frame.drop(
columns=header_not_checked)
def test_extract_not_checked_column(self):
comparable = Compare()
comparable.header = [
{"column_name": "id", "column_location": 1, "column_type": ""},
{"column_name": "first_name", "column_location": 2, "column_type": ""},
{"column_name": "last_name", "column_location": 3, "column_type": "not_checked"},
{"column_name": "middle_name", "column_location": 3, "column_type": "not_checked"},
{"column_name": "requirement", "column_location": 5, "column_type": "mapped"},
{"column_name": "alternate_name", "column_location": 6, "column_type": ""}]
comparable.index_column_name = [
{"column_name": "id", "column_location": 1}]
data = {
'id': [1, 2, 3],
'first_name': ['f1', 'f2', 'f3'],
'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3'],
'requirement': ['r1', 'r2', 'r3'],
'alternate_name': ['a1', 'a2', 'a3']
}
expected = pd.DataFrame({'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3']})
comparable.data_frame = pd.DataFrame(data)
data_importer.extract_not_checked_column(comparable)
assert expected.equals(comparable.not_checked_column)
def drop_disjunctive_column(comparable: Compare):
header_disjunctive = [
header[Field.column_name.value] for header in comparable.header
if header[Field.column_type.value] == Field.disjunctive.value
]
comparable.data_frame = comparable.data_frame.drop(
columns=header_disjunctive)
def test_stringify_index(self, mock_df, mock_index):
comparable = Compare()
comparable.data_frame = mock_df
comparable.index_column_name = mock_index
index_validator.stringify_index(comparable)
for val in comparable.data_frame['id']:
assert isinstance(val, str)
def test_validate_index_identity(self):
comparable_a = Compare()
comparable_b = Compare()
comparable_a.header = TestIndexValidator.mock_header
comparable_a.index_column_name = TestIndexValidator.mock_index
comparable_b.header = TestIndexValidator.mock_header
comparable_b.index_column_name = TestIndexValidator.mock_index
data = TestIndexValidator.mock_data_a
comparable_a.data_frame = pd.DataFrame(data)
comparable_b.data_frame = pd.DataFrame(data)
assert cell_comparator.validate_index_identity(comparable_a, comparable_b) is None
def test_sort_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['1', '2', 'str', 'abc', 'abc']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.sort_index(comparable)
expected = ['1', '2', 'abc', 'abc', 'str']
assert expected == list(comparable.data_frame['id'])
def test_strip_index(self, mock_df, mock_index):
comparable = Compare()
comparable.data_frame = mock_df
comparable.index_column_name = mock_index
index_validator.strip_index(comparable)
expected = [1, 2, 'str', 'abc', 'abc']
assert expected == list(comparable.data_frame["id"])
def test_check_for_duplicate_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['dup1', '1', '2', 'dup1', '3', '4']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.check_for_duplicate_index(comparable)
actual = list(comparable.duplicate_index['id'].values)
expected = ['dup1', 'dup1']
assert expected == actual
def test_check_for_empty_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['', '', 'str', 'abc', 'abc', '', None, np.nan]}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.check_for_empty_index(comparable)
expected = [0, 1, 5, 6, 7]
actual = comparable.empty_index
assert expected == actual
def test_drop_empty_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['', '', 'str', 'abc', 'abc', '', None]}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
comparable.empty_index = [0, 1, 5, 6]
index_validator.drop_empty_index(comparable)
expected = ['str', 'abc', 'abc']
actual = list(comparable.data_frame["id"])
assert expected == actual
def test_check_for_disjunctive_index(self, mock_index):
comparable_1 = Compare()
comparable_2 = Compare()
comparable_1.index_column_name = mock_index
comparable_2.index_column_name = mock_index
data1 = {
'id': ['a', 'b', '1', '2', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
}
data2 = {
'id': ['a', 'b', '3', '4', 'c'],
"fname": ['p2', 'q2', 'r2', 's2', 'j2']
}
comparable_1.data_frame = pd.DataFrame(data=data1, dtype="object")
comparable_2.data_frame = pd.DataFrame(data=data2, dtype="object")
index_validator.check_for_disjunctive_index(comparable_1, comparable_2)
expected = ['1', '2']
actual = list(comparable_1.disjunctive_index['id'].values)
assert expected == actual
def test_drop_duplicate_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['dup1', 'dup1', 'dup1', 'AAA', 'BBB']}
dup = {'id': ['dup1', 'dup1', 'dup1']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
comparable.duplicate_index = pd.DataFrame(data=dup, dtype="object")
index_validator.drop_duplicate_index(comparable)
expected = ['AAA', 'BBB']
actual = list(comparable.data_frame['id'].values)
assert expected == actual
def test_drop_disjunctive_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
data1 = {
'id': ['1', '2', 'a', 'b', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
}
comparable.data_frame = pd.DataFrame(data=data1, dtype="object")
disjunctive = {'id': ['1', '2']}
comparable.disjunctive_index = pd.DataFrame(data=disjunctive,
dtype="object")
index_validator.drop_disjunctive_index(comparable)
expected = ['a', 'b', 'c']
actual = list(comparable.data_frame['id'].values)
assert expected == actual
def test_strip_index_2(self, mock_index):
comparable = Compare()
data1 = pd.DataFrame({
'id': [
' 1 ', '2 ', ' a \n\n',
'\t\t\t b \n', ' c '
],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
})
expected = pd.DataFrame({
'id': ['1', '2', 'a', 'b', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
})
comparable.index_column_name = mock_index
comparable.data_frame = data1
index_validator.strip_index(comparable)
assert expected.equals(data1)
def test_remove_white_space_char(self):
comparable = Compare()
comparable.header = TestIndexValidator.mock_header
comparable.index_column_name = TestIndexValidator.mock_index
comparable.data_frame = pd.DataFrame(TestIndexValidator.mock_data_white_space_char)
cell_comparator.remove_non_printable_char(comparable)
expected = pd.DataFrame({
'id': [1, 2, 3],
'first_name': ['f1', 'f 2', 'f3'],
'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3'],
'requirement': ['r1', 'r 2', 'r 3'],
'alternate_name': ['a 1', 'a 2', 'a 3']
})
cell_comparator.remove_white_space_char(comparable)
assert expected.equals(comparable.data_frame)
def remove_nan(comparable: Compare):
comparable.data_frame = comparable.data_frame.fillna('')
def drop_empty_index(comparable: Compare):
comparable.data_frame = comparable.data_frame.drop(comparable.empty_index)
def drop_duplicate_index(comparable: Compare):
index_name = idx.get_index_name(comparable)
index_of_dup = comparable.duplicate_index[index_name].index.values
comparable.data_frame = comparable.data_frame.drop(index_of_dup)
def set_data_frame(comparable: Compare):
comparable.data_frame = comparable.original_data_frame.copy(deep=True)
def drop_disjunctive_index(comparable: Compare):
index_name = idx.get_index_name(comparable)
index_of_disjunctive = comparable.disjunctive_index[
index_name].index.values
comparable.data_frame = comparable.data_frame.drop(index_of_disjunctive)