R Notebook

First load the tidyverse, then read in all of the data and tidy it up…

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✔ ggplot2 3.3.3     ✔ purrr   0.3.4
## ✔ tibble  3.1.1     ✔ dplyr   1.0.5
## ✔ tidyr   1.1.3     ✔ stringr 1.4.0
## ✔ readr   1.4.0     ✔ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

temperature <- read_table(
    "https://chryswoods.com/data_analysis_r/cetml1659on.txt",
    skip=6,
    na=c("-99.99", "-99.9"),
    col_types=cols("DATE"=col_integer())
)

month_levels <- c("JAN", "FEB", "MAR", "APR", "MAY", "JUN",
                  "JUL", "AUG", "SEP", "OCT", "NOV", "DEC")

historical_temperature <- temperature %>%
    select(-YEAR) %>%
    pivot_longer(c("JAN", "FEB", "MAR", "APR", "MAY", "JUN",
                   "JUL", "AUG", "SEP", "OCT", "NOV", "DEC"),
                 names_to="month",
                 values_to="temperature") %>%
    rename(year=DATE) %>%
    mutate(month=factor(month, month_levels))

Next, add in the “decade” and “century” variables (columns) as we will be using them later…

historical_temperature["decade"] <- (historical_temperature["year"] %/% 10) * 10
historical_temperature["century"] <- (historical_temperature["year"] %/% 100) * 100
historical_temperature

Graph that shows the average maximum temperature per month…

ggplot(historical_temperature %>%
         group_by(month) %>%
         summarise(max_temp=max(temperature, na.rm=TRUE), .groups="drop"),
       aes(x=month, y=max_temp, group="month")) + 
  geom_line()

Change in average temperature in December per decade.

ggplot( historical_temperature %>%
          filter(month=="DEC") %>%
          group_by(decade) %>%
          summarise(average=mean(temperature, na.rm=TRUE), .groups="drop"),
        aes(x=decade, y=average)
      ) + 
  geom_point() +
  geom_smooth()

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

## Warning: Removed 1 rows containing non-finite values (stat_smooth).

## Warning: Removed 1 rows containing missing values (geom_point).

Change in average temperature per century, plus a smooth trend line

ggplot( historical_temperature %>%
          group_by(century) %>%
          summarise(average=mean(temperature, na.rm=TRUE), .groups="drop"),
        aes(x=century, y=average)) + 
  geom_point() + 
  geom_smooth(span=2.0)

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