analysis answer

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()

Load the data…

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())
)

Create the month levels

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

Tidy the data…

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))

Calculate the mean monthly temperatures in the 17th Century

c17th <- historical_temperature %>%
     filter(year<1700 & year>=1600) %>%
     group_by(month) %>%
     summarise("temperature"=mean(temperature, na.rm=TRUE), .groups="drop")

(the .groups="drop" removes a warning message in newer versions of R. It is experimental, e.g. see this stackoverflow post)

Calculate the mean monthly temperatures in the 21st Century

c21st <- historical_temperature %>%
     filter(year>=2000) %>%
     group_by(month) %>%
     summarise("temperature"=mean(temperature, na.rm=TRUE), .groups="drop")

Now add the difference to the c21st table and print it out

c21st["change"] <- c21st["temperature"] - c17th["temperature"]
c21st

From this we can see that most of the warming is focused on the winter months.

We will now repeat this for the maximum and minimum temperatures…

c17th_max <- historical_temperature %>%
     filter(year<1700 & year>=1600) %>%
     group_by(month) %>%
     summarise("temperature"=max(temperature, na.rm=TRUE), .groups="drop")
c21st_max <- historical_temperature %>%
     filter(year>=2000) %>%
     group_by(month) %>%
     summarise("temperature"=max(temperature, na.rm=TRUE), .groups="drop")
c21st_max["change"] <- c21st_max["temperature"] - c17th_max["temperature"]
c21st_max

c17th_min <- historical_temperature %>%
     filter(year<1700 & year>=1600) %>%
     group_by(month) %>%
     summarise("temperature"=min(temperature, na.rm=TRUE), .groups="drop")
c21st_min <- historical_temperature %>%
     filter(year>=2000) %>%
     group_by(month) %>%
     summarise("temperature"=min(temperature, na.rm=TRUE), .groups="drop")
c21st_min["change"] <- c21st_min["temperature"] - c17th_min["temperature"]
c21st_min

Finally, we can get the average increase in monthly temperatures by calculating the mean of the change column in c21st

mean(c21st[["change"]])

## [1] 1.643698