Kuizzz

data <-read.csv("df_mahasiswa.csv")
head(data)

##   X id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 1 1       MHS001             L                    4                   1
## 2 2       MHS002             P                    4                   2
## 3 3       MHS003             P                    2                   6
## 4 4       MHS004             P                    5                   3
## 5 5       MHS005             L                    3                   2
## 6 6       MHS006             L                    3                   7
##   motivasi_belajar  ipk
## 1               82 3.12
## 2               73 3.45
## 3               71 3.07
## 4               98 3.43
## 5               81 2.83
## 6               61 3.10

str(data)

## 'data.frame':    55 obs. of  7 variables:
##  $ X                   : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ id_mahasiswa        : chr  "MHS001" "MHS002" "MHS003" "MHS004" ...
##  $ jenis_kelamin       : chr  "L" "P" "P" "P" ...
##  $ jam_belajar_per_hari: int  4 4 2 5 3 3 1 3 2 1 ...
##  $ frekuensi_login_lms : int  1 2 6 3 2 7 7 4 6 5 ...
##  $ motivasi_belajar    : int  82 73 71 98 81 61 44 69 44 46 ...
##  $ ipk                 : num  3.12 3.45 3.07 3.43 2.83 3.1 2.98 3.08 2.82 2.93 ...

colSums(is.na(data))

##                    X         id_mahasiswa        jenis_kelamin 
##                    0                    0                    0 
## jam_belajar_per_hari  frekuensi_login_lms     motivasi_belajar 
##                    0                    0                    0 
##                  ipk 
##                    0

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

table(data$jenis_kelamin)

## 
##  L  P 
## 32 23

aggregate(ipk ~ jenis_kelamin, data = data, FUN = mean)

##   jenis_kelamin      ipk
## 1             L 3.158125
## 2             P 3.176957

data[order(-data$motivasi_belajar), c("id_mahasiswa", "motivasi_belajar")] |> head(1)

##    id_mahasiswa motivasi_belajar
## 54       MHS054              100

library(dplyr)
table(data$ipk > 3.5)

## 
## FALSE  TRUE 
##    46     9

mahasiswa_login_tertinggi <- data %>%
  arrange(desc(frekuensi_login_lms)) %>%
  slice(1)

mahasiswa_login_tertinggi %>%
  select(id_mahasiswa, frekuensi_login_lms, ipk) 

##   id_mahasiswa frekuensi_login_lms ipk
## 1       MHS006                   7 3.1

data %>%
  mutate(Kategori_Jam_Belajar = ifelse(jam_belajar_per_hari >= 4, "≥ 4 Jam", "< 4 Jam")) %>%
  group_by(Kategori_Jam_Belajar) %>%
  summarise(
    Rata_rata_IPK = mean(ipk, na.rm = TRUE),
    Jumlah_Mahasiswa = n()
  ) %>%
  arrange(desc(Rata_rata_IPK))

## # A tibble: 2 × 3
##   Kategori_Jam_Belajar Rata_rata_IPK Jumlah_Mahasiswa
##   <chr>                        <dbl>            <int>
## 1 ≥ 4 Jam                       3.41               27
## 2 < 4 Jam                       2.94               28

data %>%
  arrange(desc(ipk)) %>%       
  slice(1) %>%                 
  select(id_mahasiswa, ipk, motivasi_belajar)

##   id_mahasiswa  ipk motivasi_belajar
## 1       MHS018 3.89               92

data %>%
  filter(ipk > 3.5, motivasi_belajar > 85) %>%   
  group_by(jenis_kelamin) %>%                   
  summarise(Jumlah = n())

## # A tibble: 2 × 2
##   jenis_kelamin Jumlah
##   <chr>          <int>
## 1 L                  4
## 2 P                  1