How to use pmdarima - 10 common examples

<br>
"""
print(__doc__)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
import numpy as np

# #############################################################################
# Load the data and split it into separate pieces
data = pm.datasets.load_lynx()
train, test = model_selection.train_test_split(data, train_size=90)

# Fit a simple auto_arima model
modl = pm.auto_arima(train, start_p=1, start_q=1, start_P=1, start_Q=1,
                     max_p=5, max_q=5, max_P=5, max_Q=5, seasonal=True,
                     stepwise=True, suppress_warnings=True, D=10, max_D=10,
                     error_action='ignore')

# Create predictions for the future, evaluate on test
preds, conf_int = modl.predict(n_periods=test.shape[0], return_conf_int=True)

# Print the error:
print("Test RMSE: %.3f" % np.sqrt(mean_squared_error(test, preds)))

# #############################################################################
# Plot the points and the forecasts

<br>
"""
print(__doc__)

# Author: Taylor Smith 

import numpy as np
import pmdarima as pm
from pmdarima import pipeline, preprocessing as ppc, arima
from matplotlib import pyplot as plt

print("pmdarima version: %s" % pm.__version__)

# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = data[:150], data[150:]

# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
    ("fourier", ppc.FourierFeaturizer(m=12, k=4)),
    ("arima", arima.AutoARIMA(stepwise=True, trace=1, error_action="ignore",
                              seasonal=False,  # because we use Fourier
                              transparams=False,
                              suppress_warnings=True))
])

pipe.fit(train)
print("Model fit:")
print(pipe)

.. raw:: html

   <br>
"""
print(__doc__)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
import numpy as np
from matplotlib import pyplot as plt

# #############################################################################
# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = model_selection.train_test_split(data, train_size=150)

# Fit a simple auto_arima model
arima = pm.auto_arima(train, error_action='ignore', trace=True,
                      suppress_warnings=True, maxiter=10,
                      seasonal=True, m=12)

# #############################################################################
# Plot actual test vs. forecasts:
x = np.arange(test.shape[0])
plt.scatter(x, test, marker='x')
plt.plot(x, arima.predict(n_periods=test.shape[0]))
plt.title('Actual test samples vs. forecasts')
plt.show()

.. raw:: html

   <br>
"""
print(__doc__)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
import matplotlib.pyplot as plt
import numpy as np

# #############################################################################
# Load the data and split it into separate pieces
data = pm.datasets.load_lynx()
train, test = model_selection.train_test_split(data, train_size=100)

# #############################################################################
# Fit with some validation (cv) samples
arima = pm.auto_arima(train, start_p=1, start_q=1, d=0, max_p=5, max_q=5,
                      out_of_sample_size=10, suppress_warnings=True,
                      stepwise=True, error_action='ignore')

# Now plot the results and the forecast for the test set
preds, conf_int = arima.predict(n_periods=test.shape[0],
                                return_conf_int=True)

fig, axes = plt.subplots(2, 1, figsize=(12, 8))
x_axis = np.arange(train.shape[0] + preds.shape[0])
axes[0].plot(x_axis[:train.shape[0]], train, alpha=0.75)
axes[0].scatter(x_axis[train.shape[0]:], preds, alpha=0.4, marker='o')

.. raw:: html

   <br>
"""
print(__doc__)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
import joblib  # for persistence
import os

# #############################################################################
# Load the data and split it into separate pieces
y = pm.datasets.load_wineind()
train, test = model_selection.train_test_split(y, train_size=125)

# Fit an ARIMA
arima = pm.ARIMA(order=(1, 1, 2), seasonal_order=(0, 1, 1, 12))
arima.fit(y)

# #############################################################################
# Persist a model and create predictions after re-loading it
pickle_tgt = "arima.pkl"
try:
    # Pickle it
    joblib.dump(arima, pickle_tgt, compress=3)

    # Load the model up, create predictions
    arima_loaded = joblib.load(pickle_tgt)
    preds = arima_loaded.predict(n_periods=test.shape[0])

print(__doc__)

# Author: Taylor Smith 

import numpy as np
import pmdarima as pm
from pmdarima import pipeline
from pmdarima import model_selection
from pmdarima import preprocessing as ppc
from pmdarima import arima
from matplotlib import pyplot as plt

print("pmdarima version: %s" % pm.__version__)

# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = model_selection.train_test_split(data, train_size=150)

# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
    ("fourier", ppc.FourierFeaturizer(m=12, k=4)),
    ("arima", arima.AutoARIMA(stepwise=True, trace=1, error_action="ignore",
                              seasonal=False,  # because we use Fourier
                              suppress_warnings=True))
])

pipe.fit(train)
print("Model fit:")
print(pipe)

.. raw:: html

   <br>
"""
print(__doc__)

# Author: Taylor Smith 

import numpy as np
import pmdarima as pm
from pmdarima import model_selection

print("pmdarima version: %s" % pm.__version__)

# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = model_selection.train_test_split(data, train_size=165)

# Even though we have a dedicated train/test split, we can (and should) still
# use cross-validation on our training set to get a good estimate of the model
# performance. We can choose which model is better based on how it performs
# over various folds.
model1 = pm.ARIMA(order=(2, 1, 1), seasonal_order=(0, 0, 0, 1))
model2 = pm.ARIMA(order=(1, 1, 2), seasonal_order=(0, 1, 1, 12))
cv = model_selection.SlidingWindowForecastCV(window_size=100, step=24, h=1)

model1_cv_scores = model_selection.cross_val_score(
    model1, train, scoring='smape', cv=cv, verbose=2)

model2_cv_scores = model_selection.cross_val_score(
    model2, train, scoring='smape', cv=cv, verbose=2)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
import numpy as np

# #############################################################################
# Load the data and split it into separate pieces
data = pm.datasets.load_lynx()
train, test = model_selection.train_test_split(data, train_size=90)

# Fit a simple auto_arima model
modl = pm.auto_arima(train, start_p=1, start_q=1, start_P=1, start_Q=1,
                     max_p=5, max_q=5, max_P=5, max_Q=5, seasonal=True,
                     stepwise=True, suppress_warnings=True, D=10, max_D=10,
                     error_action='ignore')

# Create predictions for the future, evaluate on test
preds, conf_int = modl.predict(n_periods=test.shape[0], return_conf_int=True)

# Print the error:
print("Test RMSE: %.3f" % np.sqrt(mean_squared_error(test, preds)))

# #############################################################################
# Plot the points and the forecasts
x_axis = np.arange(train.shape[0] + preds.shape[0])
x_years = x_axis + 1821  # Year starts at 1821

plt.plot(x_years[x_axis[:train.shape[0]]], train, alpha=0.75)

print(__doc__)

# Author: Taylor Smith 

import pmdarima as pm
from pmdarima import model_selection
import numpy as np
from matplotlib import pyplot as plt

# #############################################################################
# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = model_selection.train_test_split(data, train_size=150)

# Fit a simple auto_arima model
arima = pm.auto_arima(train, error_action='ignore', trace=True,
                      suppress_warnings=True, maxiter=10,
                      seasonal=True, m=12)

# #############################################################################
# Plot actual test vs. forecasts:
x = np.arange(test.shape[0])
plt.scatter(x, test, marker='x')
plt.plot(x, arima.predict(n_periods=test.shape[0]))
plt.title('Actual test samples vs. forecasts')
plt.show()

if (len(lista_datos) > 100):
        lista_datos_orig=lista_datos
        lista_datos=lista_datos[len(lista_datos)-100:]
    else:
        lista_datos_orig=lista_datos

    if orig_size < 100:
        start_point =0
    else:
        start_point= int(orig_size) - 100
    lista_puntos = np.arange(start_point, orig_size,1)

    df, df_train, df_test = create_train_test(lista_puntos, lista_datos)

    engine_output={}
    stepwise_model =  pm.auto_arima(df_train['valores'], start_p=1, start_q=1, max_p=3, max_q=3, m=12,
                              start_P=0, seasonal=True, d=1, D=1, trace=False, approx=False,
                              error_action='ignore',  # don't want to know if an order does not work
                              suppress_warnings=True,  # don't want convergence warnings
                              c=False,
                              disp=-1,
                              stepwise=True)  # set to stepwise

    print ("Fitted first model")
    stepwise_model.fit(df_train['valores'])

    fit_forecast_pred = stepwise_model.predict_in_sample(df_train['valores'])
    fit_forecast = pd.DataFrame(fit_forecast_pred,index = df_train.index,columns=['Prediction'])

    future_forecast_pred = stepwise_model.predict(n_periods=len(df_test['valores']))
    future_forecast = pd.DataFrame(future_forecast_pred,index = df_test.index,columns=['Prediction'])
    print(df_test.index)