---
title: "Week 14 Web Scraping"
author: "Katie Fitzgerald"
date: "`r Sys.Date()`"
format: 
  html:
    self-contained: true
    toc: true
    toc_float: true
    number_section: false
    highlight: "tango"
    theme: "cosmo"
editor: visual
editor_options: 
  chunk_output_type: console
---

```{r, message=FALSE}
library(tidyverse)
library(scales)
library(geomtextpath)
```

```{r}
statepop <- read_rds("data/statepop_2020.RDS")
states <- map_data("state")

statepop |> 
  mutate(state = str_to_lower(state)) |> 
  right_join(states, by = c("state" = "region")) |> 
  mutate(pop2020_mil = pop2020/1000000) |> 
  ggplot(aes(x = long, y = lat, group = group,
             fill = pop2020_mil)) +
  geom_polygon() +
  labs(fill = "Population \nin millions") +
  theme_void() +
  coord_fixed(1.3)
```

# PSSA

```{r}
pssa <- read_rds("data/pssa_2025.RDS")
ggplot(pssa, aes(x = grade, 
                 y = percent_proficient_and_above,
                 color = subject)) +
  geom_line() +
  theme(legend.position = "bottom")
```

# Olympics

```{r}
olympics <- read_rds("data/olympics.RDS") |> 
  mutate(time = parse_number(time),
         date = ymd(date))

ggplot(olympics, aes(x = date, y = time, color = sex)) +
  geom_line() +
  geom_labelpath(aes(label = sex)) +
  scale_x_date(breaks = seq(as.Date("1890-01-01"), 
                            as.Date("2020-01-01"),
                            by = "10 years"),
               date_labels = "%Y") +
  theme_minimal() +
  theme(legend.position = "none") +
  labs(title = "Olympic Records (100m Dash)",
       y = "Time (in seconds)",
       x = "Year") 

#alternative
olympics <- olympics |> 
  mutate(year = year(date)) 
olympics |> 
  ggplot(aes(x = year, y = time, color = sex)) +
  geom_line() +
  geom_labelpath(aes(label = sex)) +
  scale_x_continuous(breaks = seq(1890, 2020, by = 10)) +
  theme_minimal() +
  theme(legend.position = "none") +
  labs(title = "Olympic Records (100m Dash)",
       y = "Time (in seconds)",
       x = "Year") 
```