Ruru H Project 3 Code

---
title: "Project 3"
author: "Ruru Group E"
date: "2024-08-03"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(readxl)
library(dplyr)
library(ggplot2)
```


```{r}
vehicles <- read.csv("VehicleYear-2024.csv")

auckland_vehicles <- vehicles %>%
  filter(TLA == "AUCKLAND")

auckland_vehicles <- auckland_vehicles %>%
  mutate(Fuel_Type = case_when(
    grepl("PETROL HYBRID|PLUGIN PETROL HYBRID", MOTIVE_POWER, ignore.case = TRUE) ~ "Petrol_Hybrid",
    grepl("PETROL", MOTIVE_POWER, ignore.case = TRUE) ~ "Petrol",
    grepl("DIESEL", MOTIVE_POWER, ignore.case = TRUE) ~ "Diesel",
    TRUE ~ "Other"
  ))


auckland_vehicles <- auckland_vehicles %>%
  mutate(CO2_Emissions_g_per_km = case_when(
    Fuel_Type == "Petrol" ~ (8.5 * 2.3 * 1000) / 100,        # Convert to g/km
    Fuel_Type == "Diesel" ~ (6.5 * 2.7 * 1000) / 100,        # Convert to g/km
    Fuel_Type == "Petrol_Hybrid" ~ (4.0 * 2.3 * 1000) / 100, # Convert to g/km
    TRUE ~ NA_real_
  ))


auckland_vehicles <- auckland_vehicles %>%
  mutate(CO2_Emissions_g_per_passenger_km = CO2_Emissions_g_per_km / 1.5)

average_auckland_co2_emissions <- auckland_vehicles %>%
  filter(Fuel_Type %in% c("Petrol", "Diesel", "Petrol_Hybrid")) %>%
  group_by(Fuel_Type) %>%
  summarise(Average_CO2_Emissions_g_per_passenger_km = mean(CO2_Emissions_g_per_passenger_km, na.rm = TRUE)) %>%
  mutate(Model = paste("Car (", Fuel_Type, ")", sep = "")) %>%
  select(Model, Average_CO2_Emissions_g_per_passenger_km)

Make <- c("BMW", "CHEVROLET", "CHEVROLET", "NISSAN", "MITSUBISHI", "SKODA", "SKODA", "TOYOTA", "TOYOTA", "FORD", "HONDA")
Model <- c("316I", "OPTRA", "NULL", "SUNNY", "LANCER", "OCTAVIA", "OCTAVIA", "COROLLA", "COROLLA", "RANGER", "CR-V")
Condition <- c("Used", "Used", "Used", "Not Specified", "Used", "Used", "Used", "New", "New", "New", "NULL")
Body_Type <- c("S.WAGON", "SALOON", "S.WAGON", "SALOON", "SALOON", "SALOON", "SALOON", "S.WAGON", "SALOON", "VAN", "S.WAGON")
Engine_CC <- c(1596, 1799, 1799, 1970, 1600, 1800, 1800, 1970, 2000, 2500, 1970)
Fuel_Type <- c("Petrol", "Petrol", "Petrol", "Diesel", "Diesel", "Diesel", "Diesel", "Diesel", "Petrol", "Petrol", "Diesel")
Model_Year <- c(1989, 2005, 2005, 1998, 1998, 2004, 2005, 1998, 2005, 2005, 1998)
Registration_Date <- c(2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005)
L_per_100km <- c(7.5, 6.2, 6.2, 6.6, 6.9, 7.0, 7.0, 7.0, 8.0, 7.0, 9.3)
CO2 <- c(176, 145, 145, 177, 185, 188, 188, 188, 188, 170, 217)

bus_data <- data.frame(Make, Model, Condition, Body_Type, Engine_CC, Fuel_Type, Model_Year, Registration_Date, L_per_100km, CO2)

filtered_buses <- bus_data %>%
  filter(Fuel_Type %in% c("Petrol", "Diesel"))

filtered_buses <- filtered_buses %>%
  mutate(CO2_Emissions_g_per_passenger_km = CO2 / 30)

average_bus_co2_emissions <- filtered_buses %>%
  group_by(Fuel_Type) %>%
  summarise(Average_CO2_Emissions_g_per_passenger_km = mean(CO2_Emissions_g_per_passenger_km, na.rm = TRUE)) %>%
  mutate(Model = paste("Bus (", Fuel_Type, ")", sep = "")) %>%
  select(Model, Average_CO2_Emissions_g_per_passenger_km)


scooter_data <- data.frame(
  Model = c("Gen 2.5", "Gen 3.0"),
  Battery_Capacity_Ah = c(9.6, 15.9),
  Range_km = c(22, 40),
  Voltage_V = 36,
  CO2_Emissions_per_kWh = 500 # g/kWh
)


scooter_data <- scooter_data %>%
  mutate(Battery_Capacity_kWh = (Battery_Capacity_Ah * Voltage_V) / 1000)

scooter_data <- scooter_data %>%
  mutate(Consumption_per_km_kWh = Battery_Capacity_kWh / Range_km)


scooter_data <- scooter_data %>%
  mutate(CO2_Emissions_per_km_g = Consumption_per_km_kWh * CO2_Emissions_per_kWh)


average_scooter_emissions <- scooter_data %>%
  summarise(Average_CO2_Emissions_g_per_km = mean(CO2_Emissions_per_km_g))


electric_scooter_data <- data.frame(
  Model = "Electric Scooters",
  Average_CO2_Emissions_g_per_passenger_km = average_scooter_emissions$Average_CO2_Emissions_g_per_km
)


other_modes_data <- data.frame(
  Model = c("Walking", "Biking"),
  Average_CO2_Emissions_g_per_passenger_km = c(0, 0)
)


final_data <- bind_rows(
  average_auckland_co2_emissions,
  average_bus_co2_emissions,
  electric_scooter_data,
  other_modes_data
)

print(final_data)

```



```{r}
data <- data.frame(
  Mode_of_Transport = c('Car (Diesel)', 'Car (Petrol)', 'Car (Petrol_Hybrid)', 'Bus (Diesel)', 'Bus (Petrol)', 'Electric Scooters', 'Walking', 'Biking'),
  Average_CO2_Emissions = c(117.0, 130.333333, 61.333333, 6.35, 5.493333, 7.504773, 0.0, 0.0)
)

plot <- ggplot(data, aes(x = Average_CO2_Emissions, y = reorder(Mode_of_Transport, Average_CO2_Emissions), fill = Average_CO2_Emissions)) +
  geom_bar(stat = "identity", color = "black") +  # Add black border to bars
  scale_fill_gradient(low = "green", high = "red", name = "CO2 Emissions (g/km)") +
  labs(title = "Average CO2 Emissions by Mode of Transport (per passenger)",
       x = "Average CO2 Emissions (g/km per passenger)",
       y = "Mode of Transport") +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5),
    panel.border = element_rect(color = "black", fill = NA, size = 1)  # Add black border around the plot
  )

ggsave("CO2_Emissions_by_Transport_with_Border.png", plot = plot, width = 10, height = 6)


```



## Calories Burnt

```{r}
met_values <- c(
  "Bus" = 1.0,
  "Walking" = 4.0,
  "Car" = 1.0,
  "Electric_Scooter" = 1.0
)

distances <- c(
  "Bus" = 3.5,
  "Walking" = 3.3,
  "Car" = 3.2,
  "Electric_Scooter" = 3.9
)

speeds <- c(
  "Bus" = 20,
  "Walking" = 5,
  "Car" = 60,
  "Electric_Scooter" = 15
)

weight <- 70


durations <- distances / speeds

calories_burned <- met_values * weight * durations

calories_data <- data.frame(
  Mode_of_Transport = names(calories_burned),
  Distance_km = distances,
  Duration_hours = durations,
  MET_value = met_values,
  Calories_Burned = calories_burned
)

print(calories_data)

```

```{r}
library(ggplot2)

calories_data <- data.frame(
  Mode_of_Transport = c("Bus", "Walking", "Car", "Electric_Scooter"),
  Distance_km = c(3.5, 3.3, 3.2, 3.9),
  Duration_hours = c(0.175, 0.66, 0.05333333, 0.26),
  MET_value = c(1, 4, 1, 1),
  Calories_Burned = c(12.25, 184.8, 3.733333, 18.2)
)


p <- ggplot(calories_data, aes(x = reorder(Mode_of_Transport, -Calories_Burned), y = Calories_Burned, fill = Calories_Burned)) +
  geom_bar(stat = "identity", color = "black", width = 0.7) +
  coord_flip() +
  geom_text(aes(label = round(Calories_Burned, 1)), hjust = -0.1, color = "black", size = 4.5, fontface = "bold") +
  labs(title = "Calories Burned by Mode of Transport",
       x = "Mode of Transport",
       y = "Calories Burned") +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, size = 22, face = "bold"),
    axis.title.x = element_text(size = 18, face = "bold"),
    axis.title.y = element_text(size = 18, face = "bold"),
    axis.text.x = element_text(size = 16),
    axis.text.y = element_text(size = 16),
    panel.grid.major = element_line(color = "gray", size = 0.5),
    panel.grid.minor = element_blank(),
    panel.border = element_rect(color = "black", fill = NA, size = 1)
  ) +
  scale_fill_gradient(low = "green", high = "red", name = "Calories Burned")

ggsave("Calories_Burned_by_Transport.png", plot = p, width = 12, height = 8, dpi = 300)

```