R Notebook

# 1. load packages
library(tidyverse)
library(scales)

# 2. load data
file_path <- "sgu-solar-installations-2011-to-present-and-totals.csv"
df <- read_csv(file_path)

# 3. Data process
yearly_data <- df %>%
  select(matches("Installation Quantity")) %>%
  select(-`Total Installation Quantity`, -`Historic Total Installation Quantity (2001 - 2010)`) %>%
  summarise(across(everything(), sum, na.rm = TRUE)) %>%
  pivot_longer(cols = everything(), names_to = "Period", values_to = "Monthly_Count") %>%
  mutate(Year = as.numeric(str_extract(Period, "\\d{4}"))) %>%
  group_by(Year) %>%
  summarise(Yearly_New_Installations = sum(Monthly_Count)) %>%
  arrange(Year) %>%
  ungroup()

# 4. Total new installations per year
ggplot(yearly_data, aes(x = factor(Year), y = Yearly_New_Installations)) +
  geom_col(fill = "#0072B2") + 
  geom_text(aes(label = comma(Yearly_New_Installations)), 
            vjust = -0.5, 
            size = 3) +
  labs(
    title = "Annual Rooftop Solar Installations in Australia",
    subtitle = "Total new installations per year",
    x = "Year",
    y = "Annual Installations"
  ) +
  scale_y_continuous(labels = comma) + 
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1) 
  )

# 5. Number of new installations per year
ggplot(yearly_data, aes(x = Year, y = Yearly_New_Installations)) +
  geom_line(color = "#0072B2", linewidth = 1.2) + 
  geom_point(color = "#0072B2", size = 3) +   
  geom_text(aes(label = comma(Yearly_New_Installations)), 
            vjust = -1, size = 3.5) +
  labs(
    title = "Annual Rooftop Solar Installations in Australia (Trend)",
    subtitle = "Number of new installations per year",
    x = "Year",
    y = "Annual Installations"
  ) +
  scale_x_continuous(breaks = seq(min(yearly_data$Year), max(yearly_data$Year), by = 1)) +
  scale_y_continuous(labels = comma, expand = expansion(mult = c(0.1, 0.15))) + 
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    panel.grid.minor.x = element_blank() 
  )

# Growth of total installed units over time (2010 - Present)
historic_total <- df %>%
  pull(`Historic Total Installation Quantity (2001 - 2010)`) %>%
  sum(na.rm = TRUE)

yearly_cumulative_data <- df %>%
  select(matches("Installation Quantity")) %>%
  select(-`Total Installation Quantity`, -`Historic Total Installation Quantity (2001 - 2010)`) %>%
  summarise(across(everything(), sum, na.rm = TRUE)) %>%
  pivot_longer(cols = everything(), names_to = "Period", values_to = "Monthly_Count") %>%
  mutate(Year = as.numeric(str_extract(Period, "\\d{4}"))) %>%
  group_by(Year) %>%
  summarise(Yearly_New = sum(Monthly_Count)) %>%
  arrange(Year) %>%
  ungroup() %>%
  mutate(Total_Cumulative = historic_total + cumsum(Yearly_New))

start_point <- tibble(
  Year = 2010,
  Yearly_New = 0,
  Total_Cumulative = historic_total
)

final_plot_data <- bind_rows(start_point, yearly_cumulative_data)

ggplot(final_plot_data, aes(x = Year, y = Total_Cumulative)) +
  geom_line(color = "#D55E00", linewidth = 1.2) + 
  geom_point(color = "#D55E00", size = 3) +
  geom_text(aes(label = comma(Total_Cumulative)), 
            vjust = -1, size = 3, check_overlap = TRUE) +
  labs(
    title = "Total Cumulative Rooftop Solar Installations in Australia",
    subtitle = "Growth of total installed units over time (2010 - Present)",
    x = "Year",
    y = "Total Cumulative Installations (Units)"
  ) +
  scale_x_continuous(breaks = seq(2010, max(final_plot_data$Year), by = 1)) +
  scale_y_continuous(labels = comma, expand = expansion(mult = c(0.05, 0.15))) +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1), 
    panel.grid.minor.x = element_blank() 
  )