# List any packages you need to use here
packages <- c("ggplot2", "readr", "tidyverse", "dplyr", "ggpubr")

#Check to see if any of your listed packages need installed
check_install_packages <- function(pkg){
  if (!require(pkg, character.only = TRUE)) {
    install.packages(pkg, dependencies = TRUE)
    library(pkg, character.only = TRUE)
  }
}

# Download the packages and read in the libraries if necessary
sapply(packages, check_install_packages)
## $ggplot2
## NULL
## 
## $readr
## NULL
## 
## $tidyverse
## NULL
## 
## $dplyr
## NULL
## 
## $ggpubr
## NULL
data("USArrests")
head(USArrests, n = 50)
##                Murder Assault UrbanPop Rape
## Alabama          13.2     236       58 21.2
## Alaska           10.0     263       48 44.5
## Arizona           8.1     294       80 31.0
## Arkansas          8.8     190       50 19.5
## California        9.0     276       91 40.6
## Colorado          7.9     204       78 38.7
## Connecticut       3.3     110       77 11.1
## Delaware          5.9     238       72 15.8
## Florida          15.4     335       80 31.9
## Georgia          17.4     211       60 25.8
## Hawaii            5.3      46       83 20.2
## Idaho             2.6     120       54 14.2
## Illinois         10.4     249       83 24.0
## Indiana           7.2     113       65 21.0
## Iowa              2.2      56       57 11.3
## Kansas            6.0     115       66 18.0
## Kentucky          9.7     109       52 16.3
## Louisiana        15.4     249       66 22.2
## Maine             2.1      83       51  7.8
## Maryland         11.3     300       67 27.8
## Massachusetts     4.4     149       85 16.3
## Michigan         12.1     255       74 35.1
## Minnesota         2.7      72       66 14.9
## Mississippi      16.1     259       44 17.1
## Missouri          9.0     178       70 28.2
## Montana           6.0     109       53 16.4
## Nebraska          4.3     102       62 16.5
## Nevada           12.2     252       81 46.0
## New Hampshire     2.1      57       56  9.5
## New Jersey        7.4     159       89 18.8
## New Mexico       11.4     285       70 32.1
## New York         11.1     254       86 26.1
## North Carolina   13.0     337       45 16.1
## North Dakota      0.8      45       44  7.3
## Ohio              7.3     120       75 21.4
## Oklahoma          6.6     151       68 20.0
## Oregon            4.9     159       67 29.3
## Pennsylvania      6.3     106       72 14.9
## Rhode Island      3.4     174       87  8.3
## South Carolina   14.4     279       48 22.5
## South Dakota      3.8      86       45 12.8
## Tennessee        13.2     188       59 26.9
## Texas            12.7     201       80 25.5
## Utah              3.2     120       80 22.9
## Vermont           2.2      48       32 11.2
## Virginia          8.5     156       63 20.7
## Washington        4.0     145       73 26.2
## West Virginia     5.7      81       39  9.3
## Wisconsin         2.6      53       66 10.8
## Wyoming           6.8     161       60 15.6

Discussion:

What are the variables available? The type of felony they were arrested for and the percent urban population for each state

How is each variable defined or calculated? Murder, Assault, and Rape are all arrests per 100,000 and Urban population is a percentage

Is each one numerical or categorical? they are all numerical

## GGplot Graphic Code

ggplot(mtcars, aes(x = mpg, y = hp)) +
  geom_point(aes(color = cyl), size = 2.4, shape = 8) +
  scale_color_manual(aesthetics = c("8" = "#298c9c")) +
  theme_minimal() +
  theme(legend.position = "bottom") +
  labs(
    title = "Effect of Horsepower on Fuel Efficiency", 
    subtitle = "Categorized by Number of Cylinders", 
    x = "Horsepower", y = "Fuel Efficiency (MPG)"
  )

Question: I am a bit confused with the coloring. I thought the color I chose was the one appearing in the graph but its not. I tried to change the color of the points and I couldn’t get it to work. What did I do wrong?

## GGplot Graphic Code 

ggplot(USArrests, aes(x = UrbanPop, y = Murder))+
  geom_point(color = "purple", size = 2.5, shape = 19)+
  geom_smooth(method = lm, se = TRUE, color = "gold", level = 0.95)+
  theme_gray()+
  labs(
    title = "The Effect of Urban Populaton on Murder Arrest Rates",
    x = "Percent Urban Population (By State)", y = "Murder Arrests (per 100,000)"
  )

ggplot(USArrests, aes(x = UrbanPop, y = Assault))+
  geom_point(color = "purple", size = 2.5, shape = 19)+
  geom_smooth(method = lm, se = TRUE, color = "gold", level = 0.95)+
  theme_gray()+
  labs(
    title = "The Effect of Urban Populaton on Assualt Arrest Rates",
    x = "Percent Urban Population (By State)", y = "Assualt Arrests (per 100,000)"
  )

ggplot(USArrests, aes(x = UrbanPop, y = Rape))+
  geom_point(color = "purple", size = 2.5, shape = 19)+
  geom_smooth(method = lm, se = TRUE, color = "gold", level = 0.95)+
  theme_gray()+
  labs(
    title = "The Effect of Urban Populaton on Rape Arrest Rates",
    x = "Percent Urban Population (By State)", y = "Rape Arrests (per 100,000)"
  )

ggplot(USArrests, aes(x = Murder, y = Assault))+
  geom_point(aes(color = UrbanPop), size = 2.5, shape = 19)+
  geom_smooth(method = lm, se = TRUE, color = "blue")+
  theme_gray()+
  labs(
    title = "The Effect of Murder Arrest Rates on Assualt Arrest Rates",
    subtitle = "Categorized by Urban Population Percentage",
    x = "Murder Arrests (per 100,000)", y = "Assualt Arrests (per 100,000)"
  )

Question: Same thing with the last graph couldn’t change the scale color but don’t know why.