Rain, Hail or Shine: Unveiling Mysteries of the Sky

Exploratory Data Analysis

1 Issues to address

The group’s exploratory data analysis seeks to address the following:

• examine possible correlations between mean, minimum and maximum temperatures and rainfall

• data visualisations of temperature by years, months and stations,

• data visualisations of rainfall by years, months and stations.

2 Installing and loading the required libraries

The following code chunk is used to install the necessary R packages:

pacman::p_load(tidyverse, shiny, bslib,lubridate, DT, ggplot2, plotly, ggthemes,
               hrbrthemes, timetk, modeltime, tidymodels,xgboost, recipes, parsnip,
               workflows, patchwork, thematic, showtext, glue, bsicons,tmap, sf,
               terra, gstat, automap, ggstatsplot, ggridges, ggrepel, ggsignif,
               gifski,gganimate, ggiraph, magick, car)

package 'rlang' successfully unpacked and MD5 sums checked
package 'tidyr' successfully unpacked and MD5 sums checked
package 'tidymodels' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\roger\AppData\Local\Temp\RtmpucYiBT\downloaded_packages

3 Importing the Dataset

data <- read_rds("data/weather_data_imputed.rds")

glimpse(data)

Rows: 1,548
Columns: 6
Groups: station [13]
$ station                  <chr> "Admiralty", "Admiralty", "Admiralty", "Admir…
$ tdate                    <date> 2014-01-01, 2014-02-01, 2014-03-01, 2014-04-…
$ mean_monthly_temperature <dbl> 26.22903, 25.79355, 26.76071, 27.35484, 27.81…
$ min_monthly_temperature  <dbl> 21.70000, 22.40000, 21.80000, 23.50000, 22.40…
$ max_monthly_temperature  <dbl> 25.30000, 24.90000, 24.90000, 25.80000, 26.50…
$ monthly_rainfall         <dbl> 98.8000, 15.8000, 120.0000, 261.4000, 301.000…

DT::datatable(data, class = "display compact", style = "bootstrap5")

3.1 Adding year and month columns - for ease of analysis

For ease of analysis for EDA, the DATE in data was further broken down into year and month and added as columns:

data <- data %>%
  mutate(Year = year(tdate), Month = month(tdate))

glimpse(data)

Rows: 1,548
Columns: 8
Groups: station [13]
$ station                  <chr> "Admiralty", "Admiralty", "Admiralty", "Admir…
$ tdate                    <date> 2014-01-01, 2014-02-01, 2014-03-01, 2014-04-…
$ mean_monthly_temperature <dbl> 26.22903, 25.79355, 26.76071, 27.35484, 27.81…
$ min_monthly_temperature  <dbl> 21.70000, 22.40000, 21.80000, 23.50000, 22.40…
$ max_monthly_temperature  <dbl> 25.30000, 24.90000, 24.90000, 25.80000, 26.50…
$ monthly_rainfall         <dbl> 98.8000, 15.8000, 120.0000, 261.4000, 301.000…
$ Year                     <dbl> 2014, 2014, 2014, 2014, 2014, 2014, 2014, 201…
$ Month                    <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 1, 2, 3, 4…

4 Exploratory Data Analysis (EDA)

4.1 Correlation Analysis

In each of the tabsets below, we will examine the correlation between the weather variables (i.e., mean temperature, minimum temperature, maximum temperature and rainfall.

Correlation Matrix

ggcorrmat(
  data,
  cor.vars = c(min_monthly_temperature, mean_monthly_temperature, max_monthly_temperature, monthly_rainfall),
  cor.vars.names = NULL,
  matrix.type = "upper",
  type = "parametric",
  tr = 0.1,
  partial = TRUE,
  digits = 2L,
  sig.level = 0.05,
  conf.level = 0.95,
  bf.prior = 0.707,
  p.adjust.method = "holm",
  pch = "cross",
  ggcorrplot.args = list(method = "square", outline.color = "black", pch.cex = 14),
  package = "RColorBrewer",
  palette = "Dark2",
  colors = c("#E69F00", "white", "#009E73"),
  ggtheme = ggstatsplot::theme_ggstatsplot(),
  ggplot.component = NULL,
  title = "Correlation Matrix" ,
  subtitle = NULL,
  caption = NULL
  )

Mean Vs Min Temp

ggscatterstats(
      data = data,
      x = mean_monthly_temperature,
      y = min_monthly_temperature,
      xlab = "Mean Temperature",
      ylab = "Minimum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

Mean Vs Max Temp

ggscatterstats(
      data = data,
      x = mean_monthly_temperature,
      y = max_monthly_temperature,
      xlab = "Mean Temperature",
      ylab = "Maximum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

Max Vs Min Temp

ggscatterstats(
      data = data,
      x = max_monthly_temperature,
      y = min_monthly_temperature,
      xlab = "Maximum Temperature",
      ylab = "Minimum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

Mean Temp Vs Rainfall

ggscatterstats(
      data = data,
      x = mean_monthly_temperature,
      y = monthly_rainfall,
      xlab = "Maximum Temperature",
      ylab = "Minimum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

Min Temp Vs Rainfall

ggscatterstats(
      data = data,
      x = min_monthly_temperature,
      y = monthly_rainfall,
      xlab = "Maximum Temperature",
      ylab = "Minimum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

Max Temp Vs Rainfall

ggscatterstats(
      data = data,
      x = max_monthly_temperature,
      y = monthly_rainfall,
      xlab = "Maximum Temperature",
      ylab = "Minimum Temperature",
      title = "Correlation Scatter Plot",
      marginal = FALSE
    )

4.2 Exploring relationships for temperature/ rainfall between stations

Mean Temp by Station

We will first arrange the stations in ascending order of mean temperature, for ease of comparison. Thereafter we will use ggbetweenstats to plot a violin plot to examine the relationship between mean temperature and station.

data$station <- reorder(data$station, data$mean_monthly_temperature)
          
ggbetweenstats(
  data = data,
  x = station, 
  y = mean_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Mean Monthly Temperature",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE) +
  labs(title = 'Violin Plot of Mean Monthly Temperature by Stations',
       y = "Temperature") +
  theme(axis.text.x = element_text(angle = 60,
                                   size = 8))

Visualisation using a ridgeline plot.

ggplot(data,
       aes(x = mean_monthly_temperature, 
       y = station, 
       fill = stat(x))) +
       geom_density_ridges_gradient(scale =2,
                                    rel_min_height = 0.01,
                                    gradient_lwd = 1.) +
  scale_y_discrete(name= NULL) +
  scale_fill_viridis_c(name = "°C", option = "C") +
  labs(title = 'Ridgeline Plot of Mean Monthly Temperature by Stations',
       x = "Temperature (°C)",
       y = "Station") +
  theme_ridges(font_size = 10, grid = TRUE) +
  theme(plot.title = element_text(size = 14),
        plot.subtitle = element_text(size = 10),
        axis.title.x = element_text(size = 8),
        axis.title.y = element_text(size = 8, angle = 360))

Min Temp by Station

We will first arrange the stations in ascending order of minimum temperature, for ease of comparison. Thereafter we will use ggbetweenstats to plot a violin plot to examine the relationship between minimum temperature and station.

data$station <- reorder(data$station, data$min_monthly_temperature)
          
ggbetweenstats(
  data = data,
  x = station, 
  y = min_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Minimum Monthly Temperature",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE) +
  labs(title = 'Violin Plot of Minimum Monthly Temperature by Stations',
       y = "Temperature") +
  theme(axis.text.x = element_text(angle = 60,
                                   size = 8))

Visualisation using a rideline plot.

ggplot(data,
       aes(x = min_monthly_temperature, 
       y = station, 
       fill = stat(x))) +
       geom_density_ridges_gradient(scale =2,
                                    rel_min_height = 0.01,
                                    gradient_lwd = 1.) +
  scale_y_discrete(name= NULL) +
  scale_fill_viridis_c(name = "°C", option = "C") +
  labs(title = 'Ridgeline Plot of Minimum Monthly Temperature by Stations',
       x = "Temperature (°C)",
       y = "Station") +
  theme_ridges(font_size = 10, grid = TRUE) +
  theme(plot.title = element_text(size = 14),
        plot.subtitle = element_text(size = 10),
        axis.title.x = element_text(size = 8),
        axis.title.y = element_text(size = 8, angle = 360))

Max Temp by Station

We will first arrange the stations in ascending order of maximum temperature, for ease of comparison. Thereafter we will use ggbetweenstats to plot a violin plot to examine the relationship between maximum temperature and station.

data$station <- reorder(data$station, data$max_monthly_temperature)
          
ggbetweenstats(
  data = data,
  x = station, 
  y = max_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Maximum Monthly Temperature",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE) +
  labs(title = 'Violin Plot of Maximum Monthly Temperature by Stations',
       y = "Temperature") +
  theme(axis.text.x = element_text(angle = 60,
                                   size = 8))

Visualising using a ridgeline plot.

ggplot(data,
       aes(x = max_monthly_temperature, 
       y = station, 
       fill = stat(x))) +
       geom_density_ridges_gradient(scale =2,
                                    rel_min_height = 0.01,
                                    gradient_lwd = 1.) +
  scale_y_discrete(name= NULL) +
  scale_fill_viridis_c(name = "°C", option = "C") +
  labs(title = 'Ridgeline Plot of Maximum Monthly Temperature by Stations',
       x = "Temperature (°C)",
       y = "Station") +
  theme_ridges(font_size = 10, grid = TRUE) +
  theme(plot.title = element_text(size = 14),
        plot.subtitle = element_text(size = 10),
        axis.title.x = element_text(size = 8),
        axis.title.y = element_text(size = 8, angle = 360))

Rainfall by Station

We will first arrange the stations in ascending order of monthly rainfall, for ease of comparison. Thereafter we will use ggbetweenstats to plot a violin plot to examine the relationship between monthly rainfall and station.

data$station <- reorder(data$station, data$monthly_rainfall)
          
ggbetweenstats(
  data = data,
  x = station, 
  y = monthly_rainfall,
  type = "p",
  mean.ci = TRUE, 
  title = "Monthly Rainfall",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE) +
  labs(title = 'Violin Plot of Monthly Rainfall by Stations',
       y = "Temperature") +
  theme(axis.text.x = element_text(angle = 60,
                                   size = 8))

Visualising using a ridgeline plot.

ggplot(data,
       aes(x = monthly_rainfall, 
       y = station, 
       fill = stat(x))) +
       geom_density_ridges_gradient(scale =2,
                                    rel_min_height = 0.01,
                                    gradient_lwd = 1.) +
  scale_y_discrete(name= NULL) +
  scale_fill_viridis_c(name = "°C", option = "C") +
  labs(title = 'Ridgeline Plot of Monthly Rainfall by Stations',
       x = "Temperature (°C)",
       y = "Station") +
  theme_ridges(font_size = 10, grid = TRUE) +
  theme(plot.title = element_text(size = 14),
        plot.subtitle = element_text(size = 10),
        axis.title.x = element_text(size = 8),
        axis.title.y = element_text(size = 8, angle = 360))

4.3 Exploring relationships for temperature/ rainfall across years

Mean Temp by Year

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between mean temperature across the years.

ggbetweenstats(
  data = data,
  x = Year, 
  y = mean_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Mean Temperature by year from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data <- data %>%
  group_by(Year) %>%
  summarise(avgvalue = mean(mean_monthly_temperature))

p6<- ggplot() +
  geom_line(data = data,
            aes(x = as.factor(Month),
                y = mean_monthly_temperature,
                label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Year,scales = "free_x")+
  labs(title = "Mean Temperature by year from 2014 to 2023",
       colour = "Month") +
  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p6 <- ggplotly(p6, tooltip = "all")

p6

Min Temp by Year

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between minimum temperature across the years.

ggbetweenstats(
  data = data,
  x = Year, 
  y = min_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Min Temperature by year from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data <- data %>%
  group_by(Year) %>%
  summarise(avgvalue = mean(min_monthly_temperature))

p7<- ggplot() +
  geom_line(data = data,
            aes(x = as.factor(Month),
                y = min_monthly_temperature,
                label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Year,scales = "free_x")+
  labs(title = "Min Temperature by year from 2014 to 2023",
       colour = "Month") +

  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p7 <- ggplotly(p7, tooltip = "all")

p7

Max Temp by Year

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between maximum temperature across the years.

ggbetweenstats(
  data = data,
  x = Year, 
  y = max_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Max Temperature by year from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data <- data %>%
  group_by(Year) %>%
  summarise(avgvalue = mean(max_monthly_temperature))

p8<- ggplot() +
  geom_line(data = data,
            aes(x = as.factor(Month),
                y = max_monthly_temperature,
                label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Year,scales = "free_x")+
  labs(title = "Max Temperature by year from 2014 to 2023",
       colour = "Month") +

  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p8 <- ggplotly(p8, tooltip = "all")

p8

Rainfall by Year

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between monthly rainfall across the years.

ggbetweenstats(
  data = data,
  x = Year, 
  y = monthly_rainfall,
  type = "p",
  mean.ci = TRUE, 
  title = "Rainfall by year from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

p9 <- ggplot(data,
             aes(y=monthly_rainfall,
                 x = as.factor(Month),
                 fill = as.factor(Year),
                 label = station)) +
  geom_bar(stat = "identity")+
  facet_wrap(~Year, scales = "free_x") +
  labs(title="Monthly rainfall each year from 2014 to 2023",
       y = "Rainfall volume (mm)",
       x = "Month") +
  theme_minimal()+
  theme(panel.spacing.y = unit(10, "lines"))+
  scale_fill_discrete(name = "Year")

p9 <- ggplotly(p9, tooltip = "all")

p9

4.4 Exploring relationships for temperature/ rainfall across months

Mean Temp by Month

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between mean temperature across the different months in a year.

ggbetweenstats(
  data = data,
  x = Month, 
  y = mean_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Mean Temperature by month from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data <- data %>%
  group_by(Month) %>%
  summarise(avgvalue = mean(mean_monthly_temperature))

p1<- ggplot() +
  geom_line(data = data,
            aes(x = Year,
                y = mean_monthly_temperature,
                group = Month,
                colour = as.factor(Month),
                 label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Month,scales = "free_x")+
  labs(title = "Mean Temperature by month from 2014 to 2023",
       colour = "Month") +

  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p1 <- ggplotly(p1, tooltip = "all")

p1

Min Temp by Month

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between minimum temperature across the different months in a year.

ggbetweenstats(
  data = data,
  x = Month, 
  y = min_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Min Temperature by month from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data2 <- data %>%
  group_by(Month) %>%
  summarise(avgvalue = mean(min_monthly_temperature))

p2<- ggplot() +
  geom_line(data = data,
            aes(x = Year,
                y = min_monthly_temperature,
                group = Month,
                colour = as.factor(Month),
                 label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data2,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Month,scales = "free_x")+
  labs(title = "Min Temperature by month from 2014 to 2023",
       colour = "Month") +

  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p2 <- ggplotly(p2, tooltip = "all")

p2

Max Temp by Month

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between maximum temperature across the different months in a year.

ggbetweenstats(
  data = data,
  x = Month, 
  y = max_monthly_temperature,
  type = "p",
  mean.ci = TRUE, 
  title = "Max Temperature by month from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive line graph.

hline.data3 <- data %>%
  group_by(Month) %>%
  summarise(avgvalue = mean(max_monthly_temperature))

p3<- ggplot() +
  geom_line(data = data,
            aes(x = Year,
                y = max_monthly_temperature,
                group = Month,
                colour = as.factor(Month),
                 label = station))+
  geom_hline(aes(yintercept=avgvalue),
       data=hline.data3,
       linetype=6,
       colour="red",
       size=0.5)+
  facet_wrap(~Month,scales = "free_x")+
  labs(title = "Max Temperature by month from 2014 to 2023",
       colour = "Month") +

  xlab("Year")+
  ylab("Degrees (°C)")+
  theme_tufte(base_family = "Helvetica")+ 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p3 <- ggplotly(p3, tooltip = "all")

p3

Rainfall by Month

Using the code chunk below, we will use ggbetweenstats to find out if there is any significant differences between monthly rainfall across the different months in a year.

ggbetweenstats(
  data = data,
  x = Month, 
  y = monthly_rainfall,
  type = "p",
  mean.ci = TRUE, 
  title = "Monthly rainfall each year from 2014 to 2023",
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE)

Visualising using an interactive bar chart.

p5 <- ggplot(data,
             aes(y=monthly_rainfall,
                 x = as.factor(Year),
                 fill = as.factor(Year),
                 label = station)) +
  geom_bar(stat = "identity")+
  facet_wrap(~Month, scales = "free_x") +
  labs(title="Monthly rainfall each year from 2014 to 2023",
       y = "Rainfall volume (mm)",
       x = "Month") +
  theme_minimal()+
  theme(panel.spacing.y = unit(10, "lines"))+
  scale_fill_discrete(name = "Year")  + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 1),
        legend.position = "none")

p5 <- ggplotly(p5, tooltip = "all")

p5