vlookup di r dplyr
# Merge by multiple columns
merge(life_expectancy, income_disparity, by = c("country", "city"))
MF
# Merge by multiple columns
merge(life_expectancy, income_disparity, by = c("country", "city"))
library(dplyr)
desired_result =
df_b %>% select(-price,-sale_price) %>%
left_join(
df_a %>%
transmute(id = SKU, price = PRECIO_LISTA, sale_price = PRECIO_INDEXADO) %>%
distinct()
)life_expectancy = read.csv("life_expectancy.csv", skip = 2, header = TRUE, stringsAsFactors = FALSE)
sanitation = read.csv("sanitation.csv", skip = 2, header = TRUE, stringsAsFactors = FALSE)
## rename all yearly metric columns. E.g., X1995 becomes le_1995 (for life expectancy)
names(life_expectancy)[grepl("\\bX", names(life_expectancy))] = gsub("X", "le_", names(le)[grepl("\\bX", names(life_expectancy))])
names(sanitation)[grepl("\\bX", names(sanitation))] = gsub("X", "san_", names(sanitation)[grepl("\\bX", names(sanitation))])
## lowercase column names
names(life_expectancy) = tolower(names(life_expectancy))
names(sanitation) = tolower(names(sanitation))
data_2012 = merge(life_expectancy[, c("country.name", "le_2012")],
sanitation[, c("country.name", "san_2012")])
head(data_2012, 10)
# Merge by columns with different names
merge(life_expectancy, sanitation, by.x = "cntr_nm", by.y = "country.name")