def test_data_clean(self):
'''external_id record "2XyZyJ" should be "2XyVyJ"
'''
for df in self.dfs:
self.assertTrue(any(df.external_id == '2XyZyJ'))
df_clean = data_clean(df)
self.assertFalse(any(df_clean.external_id == '2XyZyJ'))
self.assertTrue(any(df_clean.external_id == '2XyVyJ'))
def test_redcap_merge_duplicates(self):
clean_dfs = []
for df in self.dfs:
df = remove_dupes(df)
df = data_clean(df)
clean_dfs.append(df)
final_data = merge_data(clean_dfs, self.names, 'internal_id')
full_ids = len(final_data['internal_id'])
unique_ids = len(final_data['internal_id'].unique())
self.assertTrue(full_ids, unique_ids)
def test_inquisit_merge_shape(self):
clean_dfs = []
for df in self.dfs:
df = remove_dupes(df)
df = data_clean(df)
clean_dfs.append(df)
final_data = merge_data(clean_dfs, self.names, 'internal_id')
rows = final_data.shape[0]
cols = final_data.shape[1]
cols_total = sum([x.shape[1] for x in self.dfs]) - len(self.dfs) + 1
self.assertTrue(rows > 0)
self.assertEqual(cols_total, cols)
def test_block2_duplicates(self):
df = remove_dupes(self.block2)
df = data_clean(df)
full_ids = len(df['internal_id'])
unique_ids = len(df['internal_id'].unique())
self.assertTrue(full_ids, unique_ids)