def setUp(self) -> None:
self.__log = logging.getLogger('IncidentsDataframeAggregator')
s_config = '{"data_structure":{"columns":[], ' \
'"convert_to_number": [],' \
'"incident_outcome_columns":["COL01","COL02","COL03"],' \
'"other_injured_columns": ["OINJ01", "OINJ02"],' \
'"other_deadh_columns": ["ODEA01"]' \
'}}'
config = json.loads(s_config)
support_dataframes = SupportDecodeDataframes()
support_dataframes.load_dataframes()
self.incidenti = Incidenti(
file_incidenti=os.path.join("/fake_dir/", "fake_file_name.csv"),
anagrafica_comuni=AnagraficaComuni("/fake_dir/fake_filename.csv"),
support_dataframes=support_dataframes,
data_file_configurations=config["data_structure"])
test_df = {
"Comune": [
"Milano", "Como", "Como", "Cernusco Sul Naviglio", "Roncolate",
"Vimodrone", "Almenno"
],
"Provincia": ["MI", "CO", "CO", "MI", "BG", "MI", "AL"],
"comune": ["1001", "1000", "1000", "1002", "1003", "1004", "1005"],
"veicolo__a___sesso_conducente": [1, 1, 2, 0, 1, 1, 0],
}
self.incidenti.df_incidenti = pd.DataFrame.from_records(test_df)
self.aggregator = IncidentsDataframeAggregator(self.incidenti)
def setUp(self) -> None:
self.__log = logging.getLogger('IncidentsDataframeAggregator')
s_config = '{"data_structure":{"columns":[], ' \
'"convert_to_number": [],' \
'"incident_outcome_columns":["COL01","COL02","COL03"],' \
'"other_injured_columns": ["OINJ01", "OINJ02"],' \
'"other_deadh_columns": ["ODEA01"]' \
'}}'
config = json.loads(s_config)
support_dataframes = SupportDecodeDataframes()
support_dataframes.load_dataframes()
self.incidenti = Incidenti(file_incidenti = os.path.join("/fake_dir/", "fake_file_name.csv"),
anagrafica_comuni = AnagraficaComuni("/fake_dir/fake_filename.csv"),
support_dataframes = support_dataframes,
data_file_configurations=config["data_structure"])
test_df = {
"Comune": ["Milano", "Como", "Como", "Cernusco Sul Naviglio","Roncolate", "Vimodrone"],
"comune": ["1001", "1000", "1000", "1002", "1003", "1004"],
"Provincia": ["MI", "CO", "CO", "MI", "BG", "MI"],
"COL01": [ 0, 1, 1, 1, 1, 4], # Incolume: 4, Morto: 1
"COL02": [ 4, 3, 1, 2, 2, 1], # Incolume: 2, Morto: 2, Ferito: 2
"COL03": [ 1, 1, 2, 2, 4, 1], # Incolume: 3, Morto: 1, Ferito: 2
"ODEA01": [ 0, 0, 2, 1, 0, 1], # 4
"OINJ01": [ 3, 0, 0, 0, 5, 0], # 8
"OINJ02": [ 6, 0, 1, 1, 0, 1], # 9
"natura_incidente":[11, 1, 1, 2, 2, 1]
}
self.incidenti.df_incidenti = pd.DataFrame.from_records(test_df)
self.aggregator = IncidentsDataframeAggregator(self.incidenti)
def setUp(self) -> None:
self.__log = logging.getLogger('IncidentsDataframeAggregator')
s_config = '{"data_structure":{"columns":[], ' \
'"convert_to_number": [],' \
'"incident_outcome_columns":["COL01","COL02","COL03"],' \
'"other_injured_columns": ["OINJ01", "OINJ02"],' \
'"other_deadh_columns": ["ODEA01"]' \
'}}'
config = json.loads(s_config)
support_dataframes = SupportDecodeDataframes()
support_dataframes.load_dataframes()
self.incidenti = Incidenti(
file_incidenti=os.path.join("/fake_dir/", "fake_file_name.csv"),
anagrafica_comuni=AnagraficaComuni("/fake_dir/fake_filename.csv"),
support_dataframes=support_dataframes,
data_file_configurations=config["data_structure"])
test_df = {
"Comune": [
"Milano", "Como", "Como", "Cernusco Sul Naviglio", "Roncolate",
"Vimodrone", "Peschiera Borromeo"
],
"comune": ["1001", "1000", "1000", "1002", "1003", "1004", "1005"],
"Provincia": ["MI", "CO", "CO", "MI", "BG", "MI", "MI"],
"veicolo__a___esito_conducente": [1, 1, 3, 0, 1, 0, 0],
"veicolo__a___passeggeri_an35": [1, 2, 1, 0, 1, 0, 0],
"veicolo__a___esito_passegg38": [2, 1, 0, 0, 3, 0, 0],
"veicolo__a___esito_passegg41": [2, 1, 2, 0, 4, 0, 0],
"veicolo__a___esito_passegg44": [3, 3, 4, 0, 0, 0, 0]
}
self.incidenti.df_incidenti = pd.DataFrame.from_records(test_df)
self.aggregator = IncidentsDataframeAggregator(self.incidenti)
self.outcome_labels = [
"Incolume", "Ferito", "Morto nelle 24 ore",
"Morto entro il trentesimo giorno", "Non dato"
]
def setUp(self) -> None:
self.__log = logging.getLogger('IncidentsDataframeAggregator')
s_config = '{"data_structure":{"columns":[], "convert_to_number": [],"incident_outcome_columns":["COL01","COL02","COL03"]}}'
config = json.loads(s_config)
support_dataframes = SupportDecodeDataframes()
support_dataframes.load_dataframes()
incidenti = Incidenti(file_incidenti = os.path.join("/fake_dir/", "fake_file_name.csv"),
anagrafica_comuni = AnagraficaComuni("/fake_dir/fake_filename.csv"),
support_dataframes = support_dataframes,
data_file_configurations=config["data_structure"])
test_df = {
"Comune": ["Milano", "Como", "Como", "Cernusco Sul Naviglio","Roncolate"],
"comune": ["1001", "1000", "1000", "1002", "1003"],
"Provincia": ["MI", "CO", "CO", "MI", "BG"],
"COL01": [ 0, 1, 1, 1, 1],
"COL02": [ 4, 3, 1, 2, 2],
"COL03": [ 1, 1, 2, 2, 4]
}
incidenti.df_incidenti = pd.DataFrame.from_records(test_df)
self.aggregator = IncidentsDataframeAggregator(incidenti)
def main(args):
log = logging.getLogger('RunIncidenti')
log.info("************> INIZIO <************")
rv = False
try:
if os.path.isfile(args.config_file) == False:
log.error("Invalid config file parameter: {fi}".format(
fi=args.config_file))
return rv
with open(args.config_file) as fconfig:
config = json.load(fconfig)
base_dir = config['data_files']['data_path']
incidenti_fn = config['data_files']['file_incidenti']
com_anagr_fn = config['data_files']['anagrafica_comuni']
anagrafica_comuni = AnagraficaComuni(
file_comuni_anagrafica=os.path.join(base_dir, com_anagr_fn))
support_dataframes = SupportDecodeDataframes()
incidenti = Incidenti(
file_incidenti=os.path.join(base_dir, incidenti_fn),
anagrafica_comuni=anagrafica_comuni,
support_dataframes=support_dataframes,
data_file_configurations=config["data_structure"])
rv = incidenti.load_data_files()
aggregator = IncidentsDataframeAggregator(incidenti)
if rv == False:
log.error("Fallita lettura dei datafile.")
else:
if args.operation == "article":
rv = article_artifacts_maker(aggregator, incidenti, config)
elif args.operation == "debug":
aggregator.get_incidents_outcome_by_typology('nation_wide')
aggregator.calculate_total_incident_outcome()
chart_male_female(aggregator, config)
chart_incident_typology(aggregator, config)
chart_hourly_incidents(aggregator, config)
passengers_outcome("province", "Milano", aggregator,
incidenti, config)
except Exception as ex:
log.error("The job returned an error - {ex}".format(ex=str(ex)))
if rv == False:
log.error("Operation failed - calculated data is not valid.")
log.info("************> FINE <************")
return rv
from src.ClassIncidenti import Incidenti
from src.ClassAnagraficaComuni import AnagraficaComuni
from src.ClassSupportDecodeDataframes import SupportDecodeDataframes
from src.ClassIncidentsDataframeAggregator import IncidentsDataframeAggregator
config = None
with open(config_file) as fconfig:
config = json.load(fconfig)
init_logger('/tmp', log_level=logging.FATAL, std_out_log_level=logging.FATAL)
base_dir = config['data_files']['data_path']
print(base_dir)
incidenti_fn = config['data_files']['file_incidenti']
incidenti_cols = config['data_structure']['columns']
cols_to_be_converted = config["data_structure"]["convert_to_number"]
anagrafica_comuni = AnagraficaComuni(
file_comuni_anagrafica=os.path.join(data_dir, istat_comuni_file))
support_dataframes = SupportDecodeDataframes()
incidenti = Incidenti(file_incidenti=os.path.join(data_dir, incidenti_fn),
anagrafica_comuni=anagrafica_comuni,
support_dataframes=support_dataframes,
data_file_configurations=config["data_structure"])
incidenti.load_data_files()
aggregator = IncidentsDataframeAggregator(incidenti)
("Vers. Incidenti:", Incidenti.get_version(), "Vers. Aggregator:",
IncidentsDataframeAggregator.get_version(), "Numerosita' df:",
incidenti.df_incidenti.shape[0])