tomonori-masui

import statsmodels.api as sm

data = sm.datasets.sunspots.load_pandas()
ts_sun = data.data.set_index('YEAR').SUNACTIVITY
ts_sun.plot(figsize=(12, 5))
plt.show()

tomonori-masui

ts_sun_diff = (ts_sun - ts_sun.shift(1)).dropna()
tsplot(ts_sun_diff)

tomonori-masui

import pandas as pd
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")

# adapted from https://www.kaggle.com/kashnitsky/topic-9-part-1-time-series-analysis-in-python?scriptVersionId=50985180&cellId=80
def tsplot(y, lags=None, figsize=(12, 7)):
    """
        Plot time series, its ACF and PACF, calculate Dickey–Fuller test
        

tomonori-masui

test_len = int(len(ts_sun) * 0.2)
sun_train, sun_test = ts_sun.iloc[:-test_len], ts_sun.iloc[-test_len:]

tomonori-masui

from sktime.forecasting.arima import AutoARIMA

forecaster = AutoARIMA(start_p=8, max_p=9, suppress_warnings=True)
sun_train.index = sun_train.index.astype(int)
forecaster.fit(sun_train)
forecaster.summary()

tomonori-masui

from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_absolute_percentage_error


def plot_forecast(series_train, series_test, forecast, forecast_int=None):

    mae = mean_absolute_error(series_test, forecast)
    mape = mean_absolute_percentage_error(series_test, forecast)

    plt.figure(figsize=(12, 6))

tomonori-masui

fh = np.arange(test_len) + 1
forecast, forecast_int = forecaster.predict(fh=fh, return_pred_int=True, alpha=0.05)
sun_arima_mae, sun_arima_mape = plot_forecast(sun_train, sun_test, forecast, forecast_int)

tomonori-masui

from sktime.forecasting.compose import make_reduction, TransformedTargetForecaster
from sktime.forecasting.model_selection import ExpandingWindowSplitter, ForecastingGridSearchCV
from sktime.performance_metrics.forecasting import MeanAbsolutePercentageError
import lightgbm as lgb

def create_forecaster():

    # creating forecaster with LightGBM
    regressor = lgb.LGBMRegressor()
    forecaster = make_reduction(regressor, window_length=5, strategy="recursive")

tomonori-masui

ts_nl = sm.datasets.get_rdataset("Nile").data
ts_nl = ts_nl.set_index('time').value

tsplot(ts_nl)

tomonori-masui

ts_nl_diff = (ts_nl - ts_nl.shift(1)).dropna()
tsplot(ts_nl_diff)