Sample Test 1 Solution Key
Question 1: False
Question 2:
DF2 %>% mutate(date = dmy(date))
Question 3:
sales<- read.csv("sales_data.csv")
sales_long <- sales %>% pivot_longer(-firm_id, names_to= "year",
values_to = "sales", names_prefix = "sales_")
sales_long %>% filter(firm_id == 200) %>% summarise(mean_sales = mean(sales, na.rm=T))
Question 4:
quakes %>% filter(stations == 14) %>% summarise(sd_mag = sd(mag))
quakes %>% filter(stations == 12) %>% summarise(sd_mag = sd(mag))
quakes %>% filter(stations == 21) %>% summarise(sd_mag = sd(mag))
Question 5:
crime<- read.csv("crime.csv")
police<- read.csv("police.csv")
df<- inner_join(crime, police, by="county_year")
df %>% filter(county.x == 25) %>% summarise(average_crime = mean(crime_rate, na.rm=T)
df %>% ggplot(aes(x=crime_rate, y= police_per_capita)) + geom_point()
+ labs(x = "Crime rate", y = "Police per capita")
Question 6:
df %>% group_by(state) %>% summarise(sum_spending = sum(spending)) %>%
arrange(desc(sum_spending)) %>% head(5)
df %>% filter(name == "Ada") %>% group_by(state) %>% summarise(mean_spending = mean(spending)) %>%
arrange(desc(mean_spending)) %>% head(1)
IQR <- quantile(df$spending, 0.75) - quantile(df$spending, 0.25)
upper_bound <- 1.5*IQR + quantile(df$spending, 0.75)
lower_bound <- quantile(df$spending, 0.25) - 1.5*IQR
df %>% filter(spending > upper_bound | spending < lower_bound)