This homework used STL decomposition to extract the trend, seasonal, and residual components of the time series. The data was tidied with `mutate()` and visualized using `filter()`. The trend model was estimated using `TSLM()` and forecasts were generated with the `forecast()` function, which were then visualized with `autoplot()`. Basic forecasting models such as **MEAN(), NAIVE(),** and **RW()** were applied and visualized. Missing dates were handled by updating the time series index with `update_tsibble()`. Fitted values and residuals were calculated using `augment()` and visualized with `ggplot()` and ACF plots. Additionally, a **log() transformation** was applied, and seasonally adjusted series were generated for improved forecasting accuracy.

This homework used the **tidyverse** and **ggplot2** packages to tidy and manipulate data. The data was cleaned and transformed for analysis by converting it into tibble and tsibble formats. Time series data was extracted and visualized, with **seasonal data** being specifically plotted using `gg_season()` and `gg_subseries()`. The **autocorrelation function (ACF)** was also applied for deeper analysis. Daily data was updated into the **tsibble()** format to ensure correct indexing and consistency. The combined data was visualized using various plotting functions from **ggplot2**, enabling a comprehensive exploration of trends, seasonality, and autocorrelation in the time series.