This repository is for storing lab tasks for time series analysis, an undergraduate class.
posting url : https://ohjinjin.github.io/dataanalysis/time-series-1/
a practice for converting the frequency(from monthly to quarterly or yearly) using 'beersales' data of TSA package and 'wineind' data of forecast package.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Lab1_convert_the_frequency.ipynb
Additional self-practice in this regard : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/selftest1_convert_the_frequency.ipynb
a practice for applying Simple exponential smoothing using 'forecast' package.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/simple_exponential_smoothing_exmaple.ipynb
a practice for finding optimal alpha value in Simple Exponential Smoothing.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/find_optimal_alpha_in_ses.ipynb
a practice for applying Simple exponential smoothing using 'fpp2' package.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/simple_exponential_smoothing_exmaple2.ipynb
a practice for applying Holt's linear trend method using 'fpp2' package.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Holt's_linear_trend_method.ipynb
practices for applying Holt's Winters' seasonal method using own data and 'austourists' data of 'fpp2' package.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Holt-Winters'%20seasonal%20method.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Holt-Winters'%20seasonal%20method2.ipynb
practices for applying ETS using 'austourists' data of 'fpp2' package.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/ETS_example.ipynb
for comparing ETS(MAM) and Holt's Winters' multiplicative method..
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/ETS_vs_HW_example.ipynb
a practice for simulating ETS and SES method.
link : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/ses_vs_ets.ipynb
practices for comparing ETS and All of exponential methods.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/comparing_all_of_exponential_smoothing_method_wih_ets_1.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/comparing_all_of_exponential_smoothing_method_wih_ets_2.ipynb
link3 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/compare_ses_vs_ets_via_same_parameter.ipynb
practices for decomposing data variance components_Among them, the_trend-cycle_component.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/decomposition_ex1_MovingAverage_for_the_trend-cycle_component1.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/decomposition_ex1_MovingAverage_for_the_trend-cycle_component2.ipynb
link3 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/ma_for_decomposition.ipynb
a practice for decomposing via classical decomposition.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/classical_decomposition.ipynb
practices for fitting data on Average method, Naive method, Seasonal naive method and Drift method.(well-known as benchmark)
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/benchmark_1.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/benchmark_2.ipynb
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/midterm_1.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/midterm_2.ipynb
link3 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/midterm_3.ipynb
practices for fitting ARIMA.
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Random_Walk_Process.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/White_noise.ipynb
link3 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Random_Walk_drift_term.ipynb
link4 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/Random_Walk_to_Stationarity_Series.ipynb
link5 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/stationary_series_diff,log.ipynb
link6 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_checkresiduals_of_randomwalks.ipynb
link7 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_ACF_PACF.ipynb
link8: https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_kpss.ipynb
link9 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_ljungbox.ipynb
link10 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_ar.ipynb
link11 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/AR_box_jenkins_with_benchmark.ipynb
link12 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/MA_simulation.ipynb
link13 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/MA_box_jenkins_with_benchmark.ipynb
link14 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_arma.ipynb
link15 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_arima.ipynb
link16 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_seasonalARIMA.ipynb
link17 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_seasonalARIMA_2.ipynb
link18 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/arima_with_boxjenkins.ipynb
link19 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/lab_forecast_combination.ipynb
link20 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/evaluate_via_cross_validation.ipynb
link1 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/final_1.ipynb
link2 : https://github.com/ohjinjin/TimeSeries_Lab/blob/master/final_2.ipynb