Plotting Seasonality and Correlation

Matt Dancho

timetk: A toolkit for time series analysis in R

This tutorial focuses on 3 new functions for visualizing time series diagnostics:

library(tidyverse)
library(timetk)

# Setup for the plotly charts (# FALSE returns ggplots)
interactive <- FALSE

Correlation Plots

Grouped ACF Diagnostics

m4_hourly %>%
    group_by(id) %>%
    plot_acf_diagnostics(
        date, value,               # ACF & PACF
        .lags = "7 days",          # 7-Days of hourly lags
        .interactive = interactive
    )

Grouped CCF Plots

walmart_sales_weekly %>%
    select(id, Date, Weekly_Sales, Temperature, Fuel_Price) %>%
    group_by(id) %>%
    plot_acf_diagnostics(
        Date, Weekly_Sales,        # ACF & PACF
        .ccf_vars    = c(Temperature, Fuel_Price),   # CCFs
        .lags        = "3 months",    # 3 months of weekly lags
        .interactive = interactive
    )

Seasonality

Seasonal Visualizations

taylor_30_min %>%
    plot_seasonal_diagnostics(date, value, .interactive = interactive)

Grouped Seasonal Visualizations

m4_hourly %>%
    group_by(id) %>%
    plot_seasonal_diagnostics(date, value, .interactive = interactive)

STL Diagnostics

m4_hourly %>%
    group_by(id) %>%
    plot_stl_diagnostics(
        date, value,
        .frequency = "auto", .trend = "auto",
        .feature_set = c("observed", "season", "trend", "remainder"),
        .interactive = interactive)

Learning More

If you are interested in learning from my advanced Time Series Analysis & Forecasting Course, then join my waitlist. The course is coming soon.

You will learn:

Signup for the Time Series Course waitlist