def test_pipeline_behavior():
wineind = load_wineind()
train, test = wineind[:125], wineind[125:]
pipeline = Pipeline([
("fourier", FourierFeaturizer(m=12)),
("arima", AutoARIMA(seasonal=False, stepwise=True,
suppress_warnings=True,
maxiter=3, error_action='ignore'))
])
# Quick assertions on indexing
assert len(pipeline) == 2
pipeline.fit(train)
preds = pipeline.predict(5)
assert preds.shape[0] == 5
assert pipeline._final_estimator.model_.fit_with_exog_
# Assert that when the n_periods kwarg is set manually and incorrectly for
# the fourier transformer, we get a ValueError
kwargs = {
"fourier__n_periods": 10
}
with pytest.raises(ValueError) as ve:
pipeline.predict(3, **kwargs)
assert "'n_periods'" in pytest_error_str(ve)
# Assert that we can update the model
pipeline.update(test, maxiter=5)
# And that the fourier transformer was updated properly...
assert pipeline.steps_[0][1].n_ == wineind.shape[0]
def main(datasetid):
if(datasetid == 'shampoo'):
series = read_csv('shampoo-sales.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
else:
series = load_wineind().astype(np.float64)
prot05(series)
hr = load_heartrate(as_series=True)
# > set.seed(123)
# > abc <- rnorm(50, 5, 1)
abc = np.array([
4.439524, 4.769823, 6.558708, 5.070508, 5.129288, 6.715065, 5.460916,
3.734939, 4.313147, 4.554338, 6.224082, 5.359814, 5.400771, 5.110683,
4.444159, 6.786913, 5.497850, 3.033383, 5.701356, 4.527209, 3.932176,
4.782025, 3.973996, 4.271109, 4.374961, 3.313307, 5.837787, 5.153373,
3.861863, 6.253815, 5.426464, 4.704929, 5.895126, 5.878133, 5.821581,
5.688640, 5.553918, 4.938088, 4.694037, 4.619529, 4.305293, 4.792083,
3.734604, 7.168956, 6.207962, 3.876891, 4.597115, 4.533345, 5.779965,
4.916631
])
wineind = load_wineind()
lynx = load_lynx()
# Yes, m is ACTUALLY 12... but that takes a LONG time. If we set it to
# 1, we actually get a much, much faster model fit. We can only use this
# if we're NOT testing the output of the model, but just the functionality!
wineind_m = 1
# A random xreg for the wineind array
wineind_xreg = rs.rand(wineind.shape[0], 2)
def _unlink_if_exists(path):
if os.path.exists(path):
os.unlink(path)
#### from statsmodels.tsa.api import ExponentialSmoothing exp = ExponentialSmoothing(data) exp_model = exp.fit(smoothing_level=0.1) result = exp_model.fittedvalues dir(exp_model) data exp_model.predict(30) result result.plot() #%%%% import pmdarima.datasets as pm wine = pm.load_wineind(True) wine.head() wine.tail() wine.head().append(wine.tail()) wine.shape wine #176 observations wineTrg = wine[0:108] # Up to December '88 #create model for 108 observations wineVal = wine[108:] # From January '89 until end wineTrg wineVal #%%%%% wineTrg.rolling(window=3) wine_ma3c = wineTrg.rolling(window=3, center=True).mean() wine_ma3c
# -*- coding: utf-8 -*-
from pmdarima.preprocessing.exog import base
from pmdarima import datasets
import numpy as np
import pandas as pd
wineind = datasets.load_wineind()
class RandomExogFeaturizer(base.BaseExogFeaturizer):
"""Creates random exog features. This is just used to test base func"""
def _get_prefix(self):
return "RND"
def fit(self, y, X, **_):
return self
def transform(self, y, X=None, n_periods=0, **_):
Xt = np.random.rand(y.shape[0], 4)
Xt = self._safe_hstack(X, Xt)
return y, Xt
def test_default_get_feature_names():
feat = RandomExogFeaturizer()
y_trans, X = feat.fit_transform(wineind)
assert y_trans is wineind
assert X.columns.tolist() == \
['RND_0', 'RND_1', 'RND_2', 'RND_3']
from pmdarima.datasets import load_wineind
import pmdarima as pm
import numpy as np
# this is a dataset from R
wineind = load_wineind().astype(np.float64)
# fit stepwise auto-ARIMA
stepwise_fit = pm.auto_arima(
wineind,
start_p=1,
start_q=1,
max_p=3,
max_q=3,
m=12,
start_P=0,
seasonal=True,
d=1,
D=1,
trace=True,
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
print(stepwise_fit.summary())
print(stepwise_fit.get_params())
from pmdarima import auto_arima
from pmdarima.datasets import load_wineind
from pmdarima import model_selection
ARTIFACT_PATH = "model"
def calculate_cv_metrics(model, endog, metric, cv):
cv_metric = model_selection.cross_val_score(model, endog, cv=cv, scoring=metric, verbose=0)
return cv_metric[~np.isnan(cv_metric)].mean()
with mlflow.start_run():
data = load_wineind()
train, test = model_selection.train_test_split(data, train_size=150)
print("Training AutoARIMA model...")
arima = auto_arima(
train,
error_action="ignore",
trace=False,
suppress_warnings=True,
maxiter=5,
seasonal=True,
m=12,
)
print("Model trained. \nExtracting parameters...")
