def get_data(self, **kwargs):
states = kwargs.get('states')
years = kwargs.get('years')
#json_path = kwargs.get('json_path',None)
#Removing Duplicates
states = list(set(states))
years = list(set(years))
#Checking Errors
self.check_state_years_inputs_errors(states, years)
#Downloading Data
#json_result = self.io_utils.read_json(json_path) if json_path else {'metadata': {'column_descriptions':{}}}
for state in states:
for year in years:
dir_path = os.path.join(self.sinasc_raw_dir, state)
year_str = str(year)
if not os.path.exists(dir_path):
self.io_utils.create_folder_structure(folder=dir_path)
if not os.path.exists(
os.path.join(dir_path, f'{state}_{year_str}.csv.gz')):
df = download(state, year)
self.io_utils.save_df_zipped_csv(
df=df,
dirpath=dir_path,
file_name=f'{state}_{year_str}')
def test_download_new(self):
df = download('SE', 2015)
self.assertIn('IDADEMAE', df.columns)
self.assertGreater(len(df), 0)
def test_download_old(self):
df = download('AL', 1994)
self.assertIn('IDADE_MAE', df.columns)
self.assertGreater(len(df), 0)
def test_download_new(self):
df = download('SE', 2015)
self.assertIn('IDADEMAE', df.columns)
self.assertGreater(len(df), 0)
def test_download_old(self):
df = download('AL', 1994)
self.assertIn('IDADE_MAE', df.columns)
self.assertGreater(len(df), 0)
def test_download_new(self):
df = download("SE", 2015)
self.assertIn("IDADEMAE", df.columns)
self.assertGreater(len(df), 0)
def test_download_old(self):
df = download("AL", 1994)
self.assertIn("IDADE_MAE", df.columns)
self.assertGreater(len(df), 0)