In class exercise4

# data management and graphics package
library(tidyverse)

## -- Attaching packages ------------------------------------------ tidyverse 1.3.0 --

## √ ggplot2 3.3.0     √ purrr   0.3.3
## √ tibble  2.1.3     √ dplyr   0.8.5
## √ tidyr   1.0.2     √ stringr 1.4.0
## √ readr   1.3.1     √ forcats 0.5.0

## -- Conflicts --------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

input data

dta <- read.csv("D:/sheu/langMath.csv", h=T)

compute averages by school

library(dplyr)
library(ggplot2)
dta_a <- dta %>%
        group_by(School) %>%
        summarize(ave_lang = mean(Lang, na.rm=TRUE),
                  ave_arith = mean(Arith, na.rm=TRUE))

# superimpose two plots
ggplot(data=dta, aes(x=Arith, y=Lang)) +
 geom_point(color="skyblue") +
 stat_smooth(method="lm", formula=y ~ x, se=F, col="skyblue") +
 geom_point(data=dta_a, aes(ave_arith, ave_lang), color="steelblue") +
 stat_smooth(data=dta_a, aes(ave_arith, ave_lang),
             method="lm", formula= y ~ x, se=F, color="steelblue") +
 labs(x="Arithmetic score", 
      y="Language score") +
 theme_bw()

##