Mini Project 1

install.packages(c("jsonlite", "dplyr", "ggplot2", "tidyr", "scales"))
install.packages("readr")

Question 1

data(cars)
median(cars[,1])  # First column is 'speed'

## [1] 15

Question 2

library(jsonlite)

url <- "https://min-api.cryptocompare.com/data/v2/histoday?fsym=BTC&tsym=USD&limit=100"

btc_data <- fromJSON(url)

df <- btc_data$Data$Data

max_close <- max(df$close)
print(max_close)

## [1] 96945.09

College Tuition and Student Debt in the U.S.

Research Questions

1. How does tuition differ by institution type?
2. Which states have the highest student debt?
3. Is there a relationship between tuition and earnings?
4. How do completion rates vary by institution type?
5. Does institution size relate to student debt?

library(readr)

## Warning: package 'readr' was built under R version 4.5.2

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.5.2

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.5.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

df <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-03-10/tuition_cost.csv")

## Rows: 2973 Columns: 10

## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): name, state, state_code, type, degree_length
## dbl (5): room_and_board, in_state_tuition, in_state_total, out_of_state_tuit...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(df)

## # A tibble: 6 × 10
##   name      state state_code type  degree_length room_and_board in_state_tuition
##   <chr>     <chr> <chr>      <chr> <chr>                  <dbl>            <dbl>
## 1 Aaniiih … Mont… MT         Publ… 2 Year                    NA             2380
## 2 Abilene … Texas TX         Priv… 4 Year                 10350            34850
## 3 Abraham … Geor… GA         Publ… 2 Year                  8474             4128
## 4 Academy … Minn… MN         For … 2 Year                    NA            17661
## 5 Academy … Cali… CA         For … 4 Year                 16648            27810
## 6 Adams St… Colo… CO         Publ… 4 Year                  8782             9440
## # ℹ 3 more variables: in_state_total <dbl>, out_of_state_tuition <dbl>,
## #   out_of_state_total <dbl>

summary(df)

##      name              state            state_code            type          
##  Length:2973        Length:2973        Length:2973        Length:2973       
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##                                                                             
##  degree_length      room_and_board  in_state_tuition in_state_total 
##  Length:2973        Min.   :   30   Min.   :  480    Min.   :  962  
##  Class :character   1st Qu.: 7935   1st Qu.: 4890    1st Qu.: 5802  
##  Mode  :character   Median :10000   Median :10099    Median :17669  
##                     Mean   :10095   Mean   :16491    Mean   :22872  
##                     3rd Qu.:12424   3rd Qu.:27124    3rd Qu.:35960  
##                     Max.   :21300   Max.   :59985    Max.   :75003  
##                     NA's   :1094                                    
##  out_of_state_tuition out_of_state_total
##  Min.   :  480        Min.   : 1376     
##  1st Qu.: 9552        1st Qu.:11196     
##  Median :17486        Median :23214     
##  Mean   :20533        Mean   :26913     
##  3rd Qu.:29208        3rd Qu.:39054     
##  Max.   :59985        Max.   :75003     
## 

# Q1: Tuition by institution type
ggplot(df, aes(x=type, y=in_state_tuition, fill=type)) +
  geom_boxplot() + theme_minimal() +
  labs(title="Q1: Tuition by Institution Type", x="", y="Tuition ($)")

# Q2: Top 10 states by tuition
df %>% group_by(state) %>%
  summarise(avg=mean(in_state_tuition, na.rm=TRUE)) %>%
  arrange(desc(avg)) %>% slice_head(n=10) %>%
  ggplot(aes(x=reorder(state,avg), y=avg)) +
  geom_col(fill="steelblue") + coord_flip() + theme_minimal() +
  labs(title="Q2: Top 10 States by Tuition", x="State", y="Avg Tuition ($)")

# Q3: In-state vs out-of-state tuition
ggplot(df, aes(x=in_state_tuition, y=out_of_state_tuition)) +
  geom_point(alpha=0.5) + geom_smooth(method="lm") + theme_minimal() +
  labs(title="Q3: In-State vs Out-of-State Tuition", x="In-State ($)", y="Out-of-State ($)")

## `geom_smooth()` using formula = 'y ~ x'

# Q4: Tuition by degree length
ggplot(df, aes(x=degree_length, y=in_state_tuition, fill=degree_length)) +
  geom_boxplot() + theme_minimal() +
  labs(title="Q4: Tuition by Degree Length", x="", y="Tuition ($)")

# Q5: Total cost in-state vs out-of-state
ggplot(df, aes(x=in_state_total, y=out_of_state_total, color=type)) +
  geom_point(alpha=0.5) + theme_minimal() +
  labs(title="Q5: Total Cost In-State vs Out-of-State", x="In-State Total ($)", y="Out-of-State Total ($)")