def run_cleaning_per_file_name(file_name):
print(file_name)
logger = logging.getLogger("svm_writer")
sr_list, file_name = ExcelLoader.load_excel(file_name)
dh = DataHolder(file_name.split(".")[0])
for sr in sr_list:
dh.add_sheet(sr.sheet_name,
pd.DataFrame(columns=sr.headers, data=sr.row_vals),
pd.DataFrame(columns=sr.headers, data=sr.xls_types),
orig_sheet_name=sr.sheet_name)
dh, meta_dh = HeaderFinder.find_headers(dh)
# save original state
dh.create_memento()
# Find and remove deviating rows
dh = DevRowFinder.delete_deviating_rows(dh)
# Identify and add date col
DateColIdentifier.identify_and_gen_date_cols(dh, svm_logger=logger)
class DataHolderTest(TestCase):
def setUp(self):
self.names = ["first", "second"]
self.dh = DataHolder("test")
d1 = pd.DataFrame(data={'col1': ["1", "2"], 'col2': ["3", "4"]})
d2 = pd.DataFrame(data={'col1': [1, 2], 'col2': [3, 4]})
self.dh.add_sheet(self.names[0], d1, d2, orig_sheet_name="1")
d1 = pd.DataFrame(data={'col1': ["1", "2"], 'col2': ["1", "1"]})
d2 = pd.DataFrame(data={'col1': [1, 2], 'col2': [1, 1]})
self.dh.add_sheet(self.names[0], d1, d2, orig_sheet_name="2")
d1 = pd.DataFrame(data={'col1': ["1", "2"], 'col2': ["15", "16"]})
d2 = pd.DataFrame(data={'col1': [1, 2], 'col2': [15, 16]})
self.dh.add_sheet(self.names[1], d1, d2, orig_sheet_name="2")
def test_set_card_ids(self):
trngs = []
trngs.append({"group_id": "one"})
trngs.append({"group_id": "two"})
RowParser.set_card_ids(trngs, self.dh)
# print(self.dh)
true_ids = [0, 1, 1]
for ds, ind in zip(self.dh.data_struct_list, true_ids):
self.assertEqual(ds.card_id, ind)
def test_updating(self):
for dh_ind, df_data, df_profiles in self.dh.enumerate():
if dh_ind == 0:
df_data.loc[0, "col2"] = "5"
df_profiles.loc[0, "col2"] = 5
if dh_ind == 1:
df_data.loc[0, "col1"] = "5"
df_profiles.loc[0, "col1"] = 5
if dh_ind == 2:
df_data.loc[1, "col1"] = "19"
df_profiles.loc[1, "col1"] = 19
self.dh.update_with_ind(dh_ind, df_data, df_profiles)
assert_frame_equal(self.dh.data_dict[self.names[0]][0].df_data, self.dh.data_struct_list[0].df_data)
assert_frame_equal(self.dh.data_dict[self.names[0]][1].df_data, self.dh.data_struct_list[1].df_data)
assert_frame_equal(self.dh.data_dict[self.names[1]][0].df_data, self.dh.data_struct_list[2].df_data)
assert_frame_equal(self.dh.data_dict[self.names[0]][0].df_profiles, self.dh.data_struct_list[0].df_profiles)
assert_frame_equal(self.dh.data_dict[self.names[0]][1].df_profiles, self.dh.data_struct_list[1].df_profiles)
assert_frame_equal(self.dh.data_dict[self.names[1]][0].df_profiles, self.dh.data_struct_list[2].df_profiles)
for key in self.dh.data_dict:
for d_struct in self.dh.data_dict[key]:
self.assertEqual(key, d_struct.name)
for ds in self.dh.data_struct_list:
self.assertEqual(ds, self.dh.id_dict[ds.id])
def test_mementos(self):
self.dh.create_memento()
for dh_ind, df_data, df_profiles in self.dh.enumerate():
if dh_ind == 0:
df_data.loc[0, "col2"] = "5"
df_profiles.loc[0, "col2"] = 5
if dh_ind == 1:
df_data.loc[0, "col1"] = "5"
df_profiles.loc[0, "col1"] = 5
if dh_ind == 2:
df_data.loc[1, "col1"] = "19"
df_profiles.loc[1, "col1"] = 19
self.dh.update_with_ind(dh_ind, df_data, df_profiles)
self.dh.create_memento()
diff_dict_list = SheetStateComparer.compare_states(self.dh.mementos[0], self.dh.mementos[1])
#for diff_dict in diff_dict_list:
#pass#diff_
for i in range(2):
for j in range(2):
el = diff_dict_list[0]["diff_array"][i][j]
if i == 0 and j == 1:
self.assertEqual(el.change, "Corrected")
else:
self.assertEqual(el.change, "No change")
def test_serialization(self):
self.dh.data_struct_list[0].roles.append("Claims Paid")
self.dh.data_struct_list[0].df_data.sort_values("col1", ascending=False, inplace=True)
serialized = self.dh.encode()
data_framed = DataHolder.decode(serialized)
assert_frame_equal(self.dh.data_struct_list[0].df_data, data_framed.data_struct_list[0].df_data)
assert_frame_equal(self.dh.data_struct_list[1].df_data, data_framed.data_struct_list[1].df_data)
assert_frame_equal(self.dh.data_struct_list[2].df_data, data_framed.data_struct_list[2].df_data)
assert_frame_equal(self.dh.data_struct_list[0].df_profiles, data_framed.data_struct_list[0].df_profiles)
assert_frame_equal(self.dh.data_struct_list[1].df_profiles, data_framed.data_struct_list[1].df_profiles)
assert_frame_equal(self.dh.data_struct_list[2].df_profiles, data_framed.data_struct_list[2].df_profiles)
self.assertEqual(data_framed.data_struct_list[0].roles[0], "Claims Paid")
# Test conservation of ids
for ind in range(len(self.dh.data_struct_list)):
self.assertEqual(data_framed.data_struct_list[ind].id, self.dh.data_struct_list[ind].id)