def test_oob_sarimax():
xreg = rs.rand(wineind.shape[0], 2)
fit = ARIMA(order=(1, 1, 1),
seasonal_order=(0, 1, 1, 12),
out_of_sample_size=15).fit(y=wineind, exogenous=xreg)
fit_no_oob = ARIMA(order=(1, 1, 1),
seasonal_order=(0, 1, 1, 12),
out_of_sample_size=0,
suppress_warnings=True).fit(y=wineind[:-15],
exogenous=xreg[:-15, :])
# now assert some of the same things here that we did in the former test
oob = fit.oob()
# compare scores:
scoring = get_callable(fit_no_oob.scoring, VALID_SCORING)
no_oob_preds = fit_no_oob.predict(n_periods=15, exogenous=xreg[-15:, :])
assert np.allclose(oob, scoring(wineind[-15:], no_oob_preds), rtol=1e-2)
# show params are no longer the same
assert not np.allclose(fit.params(), fit_no_oob.params(), rtol=1e-2)
# show we can add the new samples and get the exact same forecasts
xreg_test = rs.rand(5, 2)
fit_no_oob.update(wineind[-15:], xreg[-15:, :])
assert np.allclose(fit.predict(5, xreg_test),
fit_no_oob.predict(5, xreg_test),
rtol=1e-2)
# Show we can get a confidence interval out here
preds, conf = fit.predict(5, xreg_test, return_conf_int=True)
assert all(isinstance(a, np.ndarray) for a in (preds, conf))
class ARIMAModel(BaseModel):
def __init__(self):
"""
Initialize Model
"""
self.seasonal = True
self.metric = 'mse'
self.model = None
self.model_init = False
def _build(self, **config):
"""
build the models and initialize.
:param config: hyperparameters for the model
"""
p = config.get('p', 2)
d = config.get('d', 0)
q = config.get('q', 2)
self.seasonal = config.get('seasonality_mode', True)
P = config.get('P', 1)
D = config.get('D', 0)
Q = config.get('Q', 1)
m = config.get('m', 7)
self.metric = config.get('metric', self.metric)
order = (p, d, q)
if not self.seasonal:
seasonal_order = (0, 0, 0, 0)
else:
seasonal_order = (P, D, Q, m)
self.model = ARIMA(order=order,
seasonal_order=seasonal_order,
suppress_warnings=True)
def fit_eval(self, data, validation_data, **config):
"""
Fit on the training data from scratch.
:param data: A 1-D numpy array as the training data
:param validation_data: A 1-D numpy array as the evaluation data
:return: the evaluation metric value
"""
if not self.model_init:
# Estimating differencing term (d) and seasonal differencing term (D)
kpss_diffs = ndiffs(data, alpha=0.05, test='kpss', max_d=6)
adf_diffs = ndiffs(data, alpha=0.05, test='adf', max_d=6)
d = max(adf_diffs, kpss_diffs)
D = 0 if not self.seasonal else nsdiffs(data, m=7, max_D=12)
config.update(d=d, D=D)
self._build(**config)
self.model_init = True
self.model.fit(data)
val_metric = self.evaluate(x=None,
target=validation_data,
metrics=[self.metric])[0].item()
return {self.metric: val_metric}
def predict(self, x=None, horizon=24, update=False, rolling=False):
"""
Predict horizon time-points ahead the input x in fit_eval
:param x: ARIMA predicts the horizon steps foreward from the training data.
So x should be None as it is not used.
:param horizon: the number of steps forward to predict
:param update: whether to update the original model
:param rolling: whether to use rolling prediction
:return: predicted result of length horizon
"""
if x is not None:
raise ValueError("x should be None")
if update and not rolling:
raise Exception(
"We don't support updating model without rolling prediction currently"
)
if self.model is None:
raise Exception(
"Needs to call fit_eval or restore first before calling predict"
)
if not update and not rolling:
forecasts = self.model.predict(n_periods=horizon)
elif rolling:
if not update:
self.save("tmp.pkl")
forecasts = []
for step in range(horizon):
fc = self.model.predict(n_periods=1).item()
forecasts.append(fc)
# Updates the existing model with a small number of MLE steps for rolling prediction
self.model.update(fc)
if not update:
self.restore("tmp.pkl")
os.remove("tmp.pkl")
return forecasts
def evaluate(self, target, x=None, metrics=['mse'], rolling=False):
"""
Evaluate on the prediction results and y. We predict horizon time-points ahead the input x
in fit_eval before evaluation, where the horizon length equals the second dimension size of
y.
:param target: target for evaluation.
:param x: ARIMA predicts the horizon steps foreward from the training data.
So x should be None as it is not used.
:param metrics: a list of metrics in string format
:param rolling: whether to use rolling prediction
:return: a list of metric evaluation results
"""
if x is not None:
raise ValueError("We don't support input x currently")
if target is None:
raise ValueError("Input invalid target of None")
if self.model is None:
raise Exception(
"Needs to call fit_eval or restore first before calling evaluate"
)
forecasts = self.predict(horizon=len(target), rolling=rolling)
return [Evaluator.evaluate(m, target, forecasts) for m in metrics]
def save(self, checkpoint_file):
if self.model is None:
raise Exception(
"Needs to call fit_eval or restore first before calling save")
with open(checkpoint_file, 'wb') as fout:
pickle.dump(self.model, fout)
def restore(self, checkpoint_file):
with open(checkpoint_file, 'rb') as fin:
self.model = pickle.load(fin)
self.model_init = True
def test_oob_for_issue_28():
# Continuation of above: can we do one with an exogenous array, too?
xreg = rs.rand(hr.shape[0], 4)
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=10).fit(y=hr, exogenous=xreg)
oob = arima.oob()
assert not np.isnan(oob)
# Assert that the endog shapes match. First is equal to the original,
# and the second is the differenced array
assert np.allclose(arima.arima_res_.data.endog, hr, rtol=1e-2)
assert arima.arima_res_.model.endog.shape[0] == hr.shape[0]
# Now assert the same for exog
assert np.allclose(arima.arima_res_.data.exog, xreg, rtol=1e-2)
assert arima.arima_res_.model.exog.shape[0] == xreg.shape[0]
# Compare the OOB score to an equivalent fit on data - 10 obs, but
# without any OOB scoring, and we'll show that the OOB scoring in the
# first IS in fact only applied to the first (train - n_out_of_bag)
# samples
arima_no_oob = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=0).fit(y=hr[:-10],
exogenous=xreg[:-10, :])
scoring = val.get_scoring_metric(arima_no_oob.scoring)
preds = arima_no_oob.predict(n_periods=10, exogenous=xreg[-10:, :])
assert np.allclose(oob, scoring(hr[-10:], preds), rtol=1e-2)
# Show that the model parameters are not the same because the model was
# updated.
xreg_test = rs.rand(5, 4)
assert not np.allclose(arima.params(), arima_no_oob.params(), rtol=1e-2)
# Now assert on the forecast differences.
with_oob_forecasts = arima.predict(n_periods=5, exogenous=xreg_test)
no_oob_forecasts = arima_no_oob.predict(n_periods=5, exogenous=xreg_test)
with pytest.raises(AssertionError):
assert_array_almost_equal(with_oob_forecasts, no_oob_forecasts)
# But after we update the no_oob model with the latest data, we should
# be producing the same exact forecasts
# First, show we'll fail if we try to add observations with no exogenous
with pytest.raises(ValueError):
arima_no_oob.update(hr[-10:], None)
# Also show we'll fail if we try to add mis-matched shapes of data
with pytest.raises(ValueError):
arima_no_oob.update(hr[-10:], xreg_test)
# Show we fail if we try to add observations with a different dim exog
with pytest.raises(ValueError):
arima_no_oob.update(hr[-10:], xreg_test[:, :2])
# Actually add them now, and compare the forecasts (should be the same)
arima_no_oob.update(hr[-10:], xreg[-10:, :])
assert np.allclose(with_oob_forecasts,
arima_no_oob.predict(n_periods=5, exogenous=xreg_test),
rtol=1e-2)
def model_plot(days):
days = int(days)
pd.plotting.register_matplotlib_converters()
df = pd.read_csv('data/new_york.csv')
df['Date'] = pd.to_datetime(df['Date'])
#converting data to daily usage.
df.index = df.Date
df = df.drop('Date', axis=1)
# resample the dataframe every 1 day (D) and sum ovr each day
df = df.resample('D').sum()
df = df.tz_localize(None)
nyc_weather = pd.read_csv('data/weather/weatherNY.csv')
nyc_weather['DATE'] = pd.to_datetime(nyc_weather['DATE'])
nyc_weather = nyc_weather.set_index('DATE')
nyc_weather.drop(['NAME','STATION'],axis=1,inplace=True)
nyc_weather = nyc_weather['2015-07-01':'2020-08-10']
df = df[:'2020-08-10']
#trying 1 day increments with EXOG. MAYBE BEST CANDIDATE? with fourier terms june to june as 638 and august to august 516
day = days
real_values = []
predictions = []
df1 = df["2016":"2019"]
nyc_weather = nyc_weather["2016":"2019"]
y = df1.Consumption
exog = pd.DataFrame({'date': y.index})
exog = exog.set_index(pd.PeriodIndex(exog['date'], freq='D'))
exog['is_weekend'] = np.where(exog.index.dayofweek < 5,0,1)
#add weather data
exog['TMIN'] = nyc_weather['TMIN'].values
exog['sin1'] = np.sin(2 * np.pi * exog.index.dayofyear / 638)
exog['cos1'] = np.cos(2 * np.pi * exog.index.dayofyear / 638)
exog['sin2'] = np.sin(4 * np.pi * exog.index.dayofyear /638)
exog['cos2'] = np.cos(4 * np.pi * exog.index.dayofyear /638)
exog['sin3'] = np.sin(2 * np.pi * exog.index.dayofyear / 516)
exog['cos3'] = np.cos(2 * np.pi * exog.index.dayofyear / 516)
exog['sin4'] = np.sin(4 * np.pi * exog.index.dayofyear /516)
exog['cos4'] = np.cos(4 * np.pi * exog.index.dayofyear /516)
exog = exog.drop(columns=['date'])
num_to_update = 0
y_to_train = y.iloc[:(len(y)-100)]
exog_to_train = exog.iloc[:(len(y)-100)]
dates = []
steps = []
for i in range(5):
#first iteration train the model
if i == 0:
arima_exog_model = ARIMA(order=(3, 0, 1), seasonal_order=(2, 0, 0, 7),exogenous=exog_to_train, error_action='ignore',
initialization='approximate_diffuse', suppress_warnings=True).fit(y=y_to_train)
preds = arima_exog_model.predict_in_sample(exog_to_train)
#first prediction
y_to_test = y.iloc[(len(y)-100):(len(y)-100+day)]
y_exog_to_test = exog.iloc[(len(y)-100):(len(y)-100+day)]
y_arima_exog_forecast = arima_exog_model.predict(n_periods=day, exogenous=y_exog_to_test)
real_values.append(y_to_test.values)
predictions.append(y_arima_exog_forecast.tolist())
dates.append(y_to_test.index)
steps.append(y_to_test.index[-1])
#y_arima_exog_forecast = arima_exog_model.predict(n_periods=2, exogenous=exog_to_test)
else:
y_to_update = y.iloc[(len(y)-100+num_to_update):(len(y)-100+num_to_update)+day]
exog_to_update = exog.iloc[(len(y)-100+num_to_update):(len(y)-100+num_to_update)+day]
#to test
to_test = y.iloc[(len(y)-100+num_to_update)+day:(len(y)-100+num_to_update)+(day*2)]
exog_to_test = exog.iloc[(len(y)-100+num_to_update)+day:(len(y)-100+num_to_update)+(day*2)]
#update the model
arima_exog_model.update(y_to_update,exogenous=exog_to_update)
y_arima_exog_forecast = arima_exog_model.predict(n_periods=day, exogenous=exog_to_test)
dates.append(to_test.index)
steps.append(to_test.index[-1])
predictions.append(y_arima_exog_forecast.tolist())
real_values.append(to_test.values)
num_to_update += day
predict = [item for sublist in predictions for item in sublist]
true = [item for sublist in real_values for item in sublist]
dates = [item for sublist in dates for item in sublist]
#for viz purposes
y_to_train2 = y_to_train[-200:]
preds = preds[-200:]
y_to_train2 = y_to_train2.to_frame()
fig = go.Figure()
# Create and style traces
fig.add_trace(go.Scatter(x=y_to_train2.index, y=y_to_train2.Consumption, name='True values',
line=dict(color='firebrick', width=4,dash='dot')))
fig.add_trace(go.Scatter(x=y_to_train2.index, y=preds[-200:], name='In-sample Prediction',
line=dict(color='royalblue', width=4)))
fig.add_trace(go.Scatter(x=dates, y=predict, name='Prediction',
line=dict(color='green', width=4)))
fig.add_trace(go.Scatter(x=dates, y=true, name='True',
line=dict(color='firebrick', width=4,dash='dot')))
fig.update_layout(title='Electricity Consumption in New York',
xaxis_title='Date',
yaxis_title='Consumption',
xaxis_showgrid=True,
yaxis_showgrid=True,
#autosize=False,
#width=500,
#height=500,
paper_bgcolor=app_colors['background'],
plot_bgcolor=app_colors['background'])
return fig