Assignment 4

Setup

library(tidyverse)

## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr

## Conflicts with tidy packages ----------------------------------------------

## filter(): dplyr, stats
## lag():    dplyr, stats

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

library(ggridges)
library(ggjoy)

## The ggjoy package has been deprecated. Please switch over to the
## ggridges package, which provides the same functionality. Porting
## guidelines can be found here:
## https://github.com/clauswilke/ggjoy/blob/master/README.md

load("D:/Downloads/olywthr.rdata")

Background

In this assignment you will explore a few different ways to explore the variation in weather over a year. We will use the olywthr dataset.

Problem 1

Use all of the historical data to compute the probability of rain for each day of the year. Do a simple scatterplot graph to portray the results as a forecast for calendar 2018. You should filter out all of the leapdays in history since there is no February 29 in 2018.

olywthr %>%
  filter(!(mo == 2 & dy == 29)) %>%
  group_by(mo, dy) %>%
  summarise(prain =  mean(PRCP > 0, na.rm = TRUE)) %>%
  ungroup() -> cal18
cal18$day <- seq.int(nrow(cal18))

rainy18 <-ggplot(cal18, aes(day, prain)) +
  geom_point()

rainy18

Problem 2

Add a loess smoother to the scatterplot. Select a good value of the span argument.

 rainy18 +
  geom_smooth(span = 0.2) #higher span argument restricts flexibility of loess curve

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

#span = 0.2 seems like a good value for this graphic

Problem 3

Create density plots for the value of prain and use facetting to show each month separately.

cal18 %>% ggplot(aes(prain)) +
  geom_histogram() +
  facet_wrap(~mo)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Problem 4

Read the material at https://github.com/clauswilke/ggridges and then create a joyplot or (ridgeline plot) as an alternative to the facet by month.

ggplot(cal18, aes(x = mo, y = prain, height = prain)) +
  geom_ridgeline()

ggplot(cal18, aes(x = mo, y = prain, height = prain, group = mo)) +
  geom_joy(stat = "identity", scale = 3)