def test_find_by(data, columns, expected_messages, expected_err_items_count):
df = pd.DataFrame(data)
assert duplicates.find_by(df, columns) == create_result(
"Duplicates",
expected_messages,
items_count=len(df),
err_items_count=expected_err_items_count,
)
def run_general_rules(self):
self.save_result(garbage_symbols(self.source_items.df))
df = self.source_items.df
self.save_result(
coverage_rules.check_fields_coverage(
df.drop(columns=df.columns[df.columns.str.startswith("_")])))
self.save_result(category_rules.get_categories(df))
if getattr(self, "uniques", None):
self.save_result(
duplicate_rules.find_by(self.source_items.df, self.uniques))
def test_find_by(data, columns, expected_messages):
df = pd.DataFrame(data)
assert_results_equal(
duplicates.find_by(df, columns),
create_result("Duplicates", expected_messages, items_count=len(df)),
)