1. Đọc dữ liệu
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(DT)
library(scales)
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
d <- read.csv(file = "C:/Users/PC_Dell/Downloads/Supermarket Transactions.csv", header = T)
datatable(head(d), options = list(scrollX = TRUE))
2. Biến định tính
2.1. Biến Gender
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