HUDK4050-test2-answers

#Q4
D3 <- filter(D1, id_assessment == 37426)
mean.score <- mean(D3$score)

wrongscore <- mean(D1$score, na.rm = TRUE)

#Q5
hist(D1$studied_credits, breaks = 100)

#Q6
plot(D1$age_band, D1$studied_credits)

boxplot(data = D1, studied_credits ~ age_band, col = D1$age_band)

#Q7 - remove gender
D3 <- select(D1, id_student, age_band, studied_credits)

#Q8
D3 <- slice(D3, 1:200)

studentid <- unique(D3$id_student)

#Q9
D4 <- spread(D3, age_band, studied_credits)

#Q10
D4 <- unite(D4, "0-35", "35-55", "55<=", sep = "~")

#Q11
studentID <- unique(D1$id_student)

#Q12
#Days since module starts

#Q13
D5 <- filter(D2, is_banked == 1)

#Q14
D6 <- D2 %>% group_by(id_student) %>% summarise(avg.score = mean(score, na.rm = TRUE))

#Q15
#A data frame can incorporate columns of differing types, a matrix cannot

#Q16
D7 <- inner_join(D2, D1, by = "id_student")

#Q17
D8 <- transmute(D1, attempt.credits = studied_credits - num_of_prev_attempts*10)

#Q18
D9 <- D7 %>% group_by(region) %>% mutate(av.credits = mean(studied_credits), av.score = mean(score, na.rm = TRUE))

#Q19
library(ggplot2)
ggplot(D9, aes(av.credits, av.score, col = region)) + geom_point()