def test_nsdiffs_corner_cases():
# max_D must be a positive int
with pytest.raises(ValueError):
nsdiffs(austres, m=2, max_D=0)
# assert 0 for constant
assert nsdiffs([1, 1, 1, 1], m=2) == 0
# show fails for m <= 1
for m in (0, 1):
with pytest.raises(ValueError):
nsdiffs(austres, m=m)
def test_nsdiffs_corner_cases():
# max_D must be a positive int
assert_raises(ValueError, nsdiffs, austres, m=2, max_D=0)
# assert 0 for constant
assert nsdiffs([1, 1, 1, 1], m=2) == 0
# show fails for m <= 1
assert_raises(ValueError, nsdiffs, austres, m=1)
assert_raises(ValueError, nsdiffs, austres, m=0)
def autoarima(self, data, pre_len=7):
D_f = nsdiffs(data, m=3, max_D=5, test='ch')
d_f = ndiffs(data, alpha=0.05, test='kpss', max_d=5)
if len(data) <= 30:
seasonal = False
else:
seasonal = True
try:
stepwise_fit = auto_arima(
data,
start_p=0,
start_q=0,
max_p=3,
max_q=3,
m=12,
start_P=0,
seasonal=seasonal,
d=d_f,
D=D_f,
trace=False,
error_action=
'ignore', # don't want to know if an order does not work
suppress_warnings=True, # don't want convergence warnings
stepwise=True) # set to stepwise
except:
stepwise_fit = auto_arima(
data,
start_p=0,
start_q=0,
max_p=3,
max_q=0,
m=12,
start_P=0,
seasonal=False,
d=0,
D=0,
trace=False,
error_action=
'ignore', # don't want to know if an order does not work
suppress_warnings=True, # don't want convergence warnings
stepwise=True) # set to stepwise
output = stepwise_fit.predict(n_periods=pre_len).tolist()
self._get_model({
'model_name': 'autoarima',
'model': stepwise_fit,
'pred': output,
'org_data': data,
'pre_len': pre_len
})
return output
def test_nsdiffs_on_wine():
assert nsdiffs(wineind, m=52) == 2
#exit()
print('==-Order of (d,D) ===')
r = []
terr = [v for v in h_snl['STND_TRRTRY_NM'].unique()]
for ter in terr:
terrData = h_snl[h_snl.STND_TRRTRY_NM == ter]
optionList = list(set(terrData.KEY))
for i in optionList:
print('In progress' + '\n' + ter + '-----' + str(i))
r1 = pd.DataFrame()
histData = h_snl[(h_snl.STND_TRRTRY_NM == ter) & (h_snl.KEY == i)]
if len(histData) >= 52:
sales = histData['RTL_QTY']
try:
d = int(ndiffs(sales, test='adf'))
D = int(nsdiffs(sales, m=52, max_D=5))
r.append(ter + "_" + str(i) + "_" + str(d) + "_" + str(D))
print('== Difference algo works ==')
except:
d = 1
D = 0
r.append(ter + "_" + str(i) + "_" + str(d) + "_" + str(D))
print('== Difference algo fails ==')
else:
histData['d'] = 1
histData['D'] = 0
r.append(ter + "_" + str(i) + "_" + str(d) + "_" + str(D))
print('== Less history ==')
orderdf = pd.DataFrame()