Assignment9.Rmd

---
title: "Homework 9"
author: "LIU Aoran"
date: "2024-05-21"
output: pdf_document
---

Full name: LIU Aoran

Preferred name: Aaron

ID: 29246040

```{r}
if (!require("dplyr")) install.packages("dplyr")
if (!require("tidyr")) install.packages("tidyr")
if (!require("dbplyr")) install.packages("dbplyr")
if (!require("magrittr")) install.packages("magrittr")
if (!require("ggplot2")) install.packages("ggplot2")

library(usethis)
library(dplyr)
library(tidyr)
library(dbplyr)
library(magrittr)
library(ggplot2)
library(knitr)
library(devtools)
library(tidyverse)
library(pacman)
library(ggthemes)
library(scales)
library(ggrepel)



# install_github("andrew-griffen/gdata")
# install_github("andrew-griffen/griffen")

library(gdata)
library(griffen)
library(hrbrthemes)
library(tidyverse)
library(extrafont)
library(palmerpenguins)
library(hrbrthemes)
library(gt)
library(gtExtras)
library(webshot2)
library(broom)
library(sf)
p_load(gapminder,ggthemes,Hmisc,wesanderson,ggridges)

extrafont::loadfonts(quiet=TRUE, device='pdf')
theme_set(theme_ipsum())
```

# Task 1
```{r}
growth <- function(data) {
  model <- lm(log(gdpPercap) ~ year, data)
  return(tidy(model))
}

gapminder_nested <- gapminder |>
  group_by(country) |>
  nest()

gapminder_coef <- gapminder_nested |>
  mutate(tidy_model = map(data, growth)) |>
  unnest(tidy_model)

gapminder_ycoef <- gapminder_coef |>
  filter(term == "year")

country_continent <- gapminder |>
  select(country, continent) |>
  distinct()

country_info <- gapminder |>
  group_by(country) |>
  filter(year == max(year)) |>
  select(country, continent, pop) |>
  distinct()

gapminder_ycoef <- gapminder_ycoef |>
  left_join(country_info, by = "country")

gapminder_ycoef <- gapminder_ycoef |>
  mutate(conf.low = estimate - 1.96 * std.error,
         conf.high = estimate + 1.96 * std.error)

gapminder_ycoef <- gapminder_ycoef |>
  arrange(continent, country)

gapminder_ycoef <- gapminder_ycoef |>
  select(-data, -term)
```

```{r}

# Create the plot
p <- ggplot(gapminder_ycoef |> filter(continent != "Oceania"), aes(x = reorder(country, estimate), y =estimate, color = country)) +
  geom_point(size = 1) +
  geom_errorbar(aes(ymin = conf.low, ymax = conf.high), width = 0.2) +
  scale_color_manual(values = country_colors) +
  facet_wrap(~ continent, scales = "free") +
  coord_flip() +
  geom_hline(yintercept = 0, linetype = "solid", color = "black") +
  scale_y_continuous(limits = c(-0.05, 0.075)) +
  labs(
    title = "Annual Growth in Per Capita GDP",
    subtitle = "1952 - 2007",
    x = "",
    y = "Growth Rate",
    caption = "Source: Gapminder data, bars represent 95% confidence intervals, zero growth highlighted with black line."
  ) +
  theme(
    legend.position = "none",
    strip.text = element_text(size = 10, face = "bold"),
    axis.text.y = element_text(size = 4, hjust = 1),
    axis.text.x = element_text(size = 6, hjust = 1)
    )
  

ggsave("annualGrowth_plot.png", plot = p, width = 17, height = 14 , units = "cm")

```
```{r, out.width="120%"}
knitr::include_graphics("/Users/okuran/Desktop/R for empirical economics/annualGrowth_plot.png")
```

# Task 2
```{r}
ggplot(data = us_sf) + geom_sf()
```

# Task 3 & 4 (US Electoral College System)

The U.S. Electoral College is a system used to elect the President and Vice President. Each state gets a number of electors equal to its total number of Senators and Representatives. There are 538 electors in total, with 270 needed to win. Most states use a winner-take-all approach, where the candidate with the most votes in a state wins all its electoral votes. 

# Task 5

```{r}
trump_biden <- trump_biden |>
  mutate(prediction = ifelse(trump_polls > biden_polls, "Trump", "Biden"))

print(trump_biden)
```

# Task 6
```{r}
electoral_votes_summary <- trump_biden |>
  group_by(prediction) |>
  summarise(total_electoral_votes = sum(electoral_votes))

print(electoral_votes_summary)

predicted_winner <- electoral_votes_summary |>
  filter(total_electoral_votes == max(total_electoral_votes)) |>
  pull(prediction)
```

If the polls are accurate and do not change before November, the predicted next U.S. President would be: `r predicted_winner`

# Task 7
```{r}
joined_data <- left_join(us_sf, trump_biden, by = "iso3166_2")

print(joined_data)
```

# Task 8
```{r}
ggplot(data = joined_data) +
  geom_sf(aes(fill = prediction))
```

# Task 9
```{r}
party_colors <- c("Trump" = "#CB454A", "Biden" = "#2E74C0")

ggplot(data = joined_data) +
  geom_sf(aes(fill = prediction)) +
  scale_fill_manual(values = party_colors) +
  labs(title = "2024 US Presidential Election Predictions by State",
       fill = "Predicted Winner")
```

# Task 10
```{r}
penguin_summary <- penguins |>
  filter(!is.na(bill_length_mm) & !is.na(bill_depth_mm) & !is.na(flipper_length_mm) & !is.na(body_mass_g) & !is.na(sex)) |>
  group_by(sex, species) |>
  summarise(
    body_mass_g = round(mean(body_mass_g, na.rm = TRUE), 0),
    flipper_length_mm = round(mean(flipper_length_mm, na.rm = TRUE), 0),
    bill_length_mm = round(mean(bill_length_mm, na.rm = TRUE), 2),
    bill_depth_mm = round(mean(bill_depth_mm, na.rm = TRUE), 2)
  )

penguin_gt_table <- penguin_summary |>
  gt() |>
  tab_header(
    title = "Palmer penguin allometry by species and sex"
  ) |>
  cols_label(
    sex = "",
    species = "",
    body_mass_g = "BODY MASS (G)",
    flipper_length_mm = "FLIPPER LENGTH (MM)",
    bill_length_mm = "BILL LENGTH (MM)",
    bill_depth_mm = "BILL DEPTH (MM)"
    ) |>
  tab_footnote(
    footnote = "Note: Data were collected at Palmer Archipelago, Antarctica 2007 - 2009.") |>
  gt_theme_538()
  
gtsave(penguin_gt_table, "penguin_gt_table.png")

```
```{r, echo=FALSE, out.width="100%"}
knitr::include_graphics("penguin_gt_table.png")
```