This module and lecture were focused on visualizing data through time series; the changes and continuities of statistical behaviors within data sets can be shown over any metric of time (seconds, days, years, etc.) Macroscopic perspectives typically use years to understand financial periods, celestial-bodies (i.e. rotations and revolutions), or historical trends to name a few examples. I decided t use the pre-loaded dataset within R "EuStockMarkets", which describes the stock market data concerning four countries within the EU: Germany DAX (Ibis), Switzerland (SM)I, France (CAC), and UK (FTSE) through the years 1991-1998. First, I loaded the data and my packages; in particular, I loaded ggplot to visualize the data, and later incorporated the tidyverse package to manage and manipulate the data.
I changed the data set into a data frame to prepare it for visualization and make it easier to use. Using tidyverse, I told R to use the price and index attributes; using the mutate function allowed me to compose the annual cycles (repetitions) of each country: Before the mutation, years were represented in decimals and broke down years into an unusable collection of quantities (i.e. 1991.xxx). Next, I used plot.ly to visualize the time series.
The plot is designed to compare years(x) and price(y), with colors being differentiated by the country the stats belong to. The resulting plot is as such:
This visualization presents a trend that depicts a growing rate of stock market prices over time during the period of interest. There are clear moments of oscillation, however the bigger picture presents a clear trend towards higher prices no matter which country is being depicted.
No comments:
Post a Comment