Lab4_EY.qmd

---
title: "Lab 4"
author: "Erin Yu"
format: pdf
editor: visual
---

# Lab 4

#Read in the Data

```{r}
if (!file.exists("met_all.gz")) {
  download.file(
    url = "https://raw.githubusercontent.com/USCbiostats/data-science-data/master/02_met/met_all.gz",
    destfile = "met_all.gz",
    method   = "libcurl",
    timeout  = 60
  )
}
met <- data.table::fread("met_all.gz")
```

#Prepare the Data

```{r}
#Remove temperatures less than -17C
met <- met[temp >= -17] [elev == 9999.0, elev := NA]

#Generate a date variable
met[, date := as.Date(paste(year, month, day, sep = "-"))]

met <- met[data.table::week(date) == 1]

#Compute means by station
met_avg <- met[, .(
  mean_temp = mean(temp, na.rm = TRUE),
  mean_rh = mean(rh, na.rm = TRUE),
  mean_wind_sp = mean(wind.sp, na.rm = TRUE),
  mean_vis_dist = mean(vis.dist, na.rm = TRUE),
  mean_dew_point = mean(dew.point, na.rm = TRUE),
  lat = mean(lat, na.rm = TRUE),
  lon = mean(lon, na.rm = TRUE),
  elev = mean(elev, na.rm = TRUE)
), by = USAFID]

#Create Region Variables
met_avg[, region := ifelse(lon < -98 & lat > 39.71, 'NW',
                    ifelse(lon < -98 & lat <= 39.71, 'SW',
                    ifelse(lon >= -98 & lat > 39.71, 'NE', 
                            'SE')))]

#Create Categorical variables
met_avg[, elev_cat := ifelse(elev > 252, "high", "low")]

```

#Use geom_violin

```{r}
install.packages("ggplot2")
library(ggplot2)

met_avg[!is.na(region) & !is.na(mean_wind_sp) & !is.na(mean_dew_point)] |> 
  ggplot(aes(x = region, y = mean_wind_sp, fill = region))+
  geom_violin() +
  facet_wrap(~ region, nrow = 1) +
  labs(title = "Violin Plot of Wind Speed by Region") +
  labs(x = "Region", y = "Wind Speed")

```

It was difficult for me to interpret this data because the graph would not generate.

#Use geom_jitter with stat_smooth

```{r}
install.packages("ggplot2")
library(ggplot2)

ggplot(met_avg, aes(x = mean_dew_point, y = mean_wind_sp, color = region)) +
  geom_jitter() +
  stat_smooth(method = "lm", se = FALSE) +
  labs(title = "Association Between Dew Point and Wind Speed by Region") +
  theme_minimal()
```

It was difficult for me to interpret this data because the graph was blank

#Bar plot of weather stations

```{r}
library(ggplot2)
ggplot(met_avg, aes(x = elev_cat, fill = region)) +
  geom_bar(position = "dodge") +
  scale_fill_brewer(palette = "Set3") +
  labs(title = "Weather Stations by Elevation Category", x = "Elevation Category", y = "Count") +
  theme_minimal()
```

It was difficult for me to interpret this data because the graph was blank

#Statistical Summary

```{r}
ggplot(met_avg, aes(x = region, y = mean_dew_point, fill = region)) +
  stat_summary(fun.data = "mean_sdl", geom = "bar", color = "black") +
  stat_summary(fun.data = "mean_sdl", geom = "errorbar", width = 0.2) +
  labs(title = "Mean Dew Point by Region with Error Bars") +
  theme_minimal()

ggplot(met_avg, aes(x = region, y = mean_wind_sp, fill = region)) +
  stat_summary(fun.data = "mean_sdl", geom = "bar", color = "black") +
  stat_summary(fun.data = "mean_sdl", geom = "errorbar", width = 0.2) +
  labs(title = "Mean Wind Speed by Region with Error Bars") +
  theme_minimal()
```

It was difficult for me to interpret this data because the graph was blank

#Map showing spatial trend

```{r}
pal <- colorNumeric(palette = "Blues", domain = met_avg$mean_rh)

leaflet(met_avg) %>%
  addTiles() %>%
  addCircles(lng = ~lon, lat = ~lat, color = ~pal(mean_rh), radius = 50000) %>%
  addLegend("bottomright", pal = pal, values = ~mean_rh, title = "Relative Humidity") %>%
  addMarkers(lng = ~lon[rank(-mean_rh) <= 10], lat = ~lat[rank(-mean_rh) <= 10], 
             popup = ~paste("RH: ", round(mean_rh, 2)))
```

#Use ggplot extension

```{r}
install.packages("gganimate")
library(gganimate)

p <- ggplot(met_avg, aes(x = lon, y = lat, color = mean_wind_sp, size = mean_rh)) +
  geom_point() +
  scale_color_viridis_c() +
  theme_minimal() +
  labs(title = 'Wind Speed and Humidity: {frame_time}', x = 'Longitude', y = 'Latitude') +
  transition_time(year)

animate(p)
```

It was difficult for me to interpret this data because the graph was blank