def rank_cities(state):
mult = build_multicity_dataset(state)
cols = list(filter(re.compile('casos_\d+').search, mult.columns))
mult = mult[cols]
print(mult.head())
codes = pd.read_excel('../../data/codigos_{}.xlsx'.format(state),
names=['city', 'code'],
header=None).set_index('code').T
ints = pd.DataFrame()
for col in mult.columns:
# ints.loc[codes[int(re.sub('casos_', '', col))]] = [np.trapz(mult[col])]
ints[col] = [np.trapz(mult[col])]
return ints
def build_model(data, lag_order, window_type):
data.index = pd.DatetimeIndex(data.index)
model = DynamicVAR(data, lag_order=lag_order, window=12, window_type=window_type)
return model
if __name__ == "__main__":
prediction_window = 6 # weeks
# scenario = 'local'
scenario = 'global'
if scenario == 'local':
data = get_alerta_table(3303500) # Nova Iguaçu: 3303500
data = data[['casos', 'p_inc100k','nivel']]
else:
data = build_multicity_dataset('RJ')
data = data[[col for col in data.columns if col.startswith('casos') and not col.startswith('casos_est')][:3]]
data = data.diff()
print(data.info())
#TODO: Apply Seasonal differencing to series
# data.casos.plot(title="Series")
model = build_model(data, 12, 'expanding')
# fit = model.(maxlags=11, ic='aic') # 4 lags
# print(model.coefs.minor_xs('casos_3303500').info())
forecast = model.forecast(prediction_window)
print(forecast)
model.plot_forecast(prediction_window)
plt.savefig('DVAR_forecast_{}_weeks.png'.format(prediction_window))
def test_multi_city_dataset(self):
df = build_multicity_dataset('RJ')
self.assertGreater(len(df.columns), 500)