R Notebook

library(tidyverse)
library(dplyr)

df_housing <- read.csv("../data/belgium.csv", header = F)
colnames(df_housing) <- c("id","name", "number_one", "adress_one", "country", "mail", "telephone", "adress_two", "roll")

hoeveel unieke namen zitten in de dataset?

nrow(df_housing %>% distinct(name))

[1] 138

wie komt het vaakst voor?

df_housing %>% 
  group_by(name) %>% count() %>% arrange(desc(n))

welke locatie komt het vaakst voor?

df_housing %>% 
  group_by(adress_two) %>% count() %>% arrange(desc(n))

welke transacties komen het vaakst voor?

df_housing %>% 
  group_by(name, adress_two) %>% summarise(count = n()) %>% arrange(desc(count))