quiz

getwd()

## [1] "C:/Users/Asus/OneDrive/Documents"

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

##   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(df_mahasiswa)

## '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(df_mahasiswa))

##                    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(df_mahasiswa$jenis_kelamin)

## 
##  L  P 
## 32 23

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

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

df_mahasiswa[order(-df_mahasiswa$motivasi_belajar), c("id_mahasiswa", 
"motivasi_belajar")] |> head(5)

##    id_mahasiswa motivasi_belajar
## 54       MHS054              100
## 4        MHS004               98
## 45       MHS045               96
## 18       MHS018               92
## 48       MHS048               92

df_mahasiswa[order(-df_mahasiswa$ipk), c("id_mahasiswa", 
"ipk")] |> head(5)

##    id_mahasiswa  ipk
## 18       MHS018 3.89
## 41       MHS041 3.73
## 48       MHS048 3.70
## 22       MHS022 3.69
## 37       MHS037 3.67

mean(df_mahasiswa$ipk[df_mahasiswa$jam_belajar_per_hari >= 4])

## [1] 3.405185

mean(df_mahasiswa$ipk[df_mahasiswa$jam_belajar_per_hari < 4])

## [1] 2.935357

mahasiswa_lms_tertinggi <- df_mahasiswa %>%
  filter(ipk > 3.5, motivasi_belajar > 85)
hasil_analisis <- mahasiswa_lms_tertinggi %>%
  mutate(ipk = ifelse(ipk > 3.5, "YA (>3.5)", "TIDAK(<=3.5)"))
print(hasil_analisis)

##    X id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 1 18       MHS018             L                    5                   7
## 2 34       MHS034             P                    5                   4
## 3 41       MHS041             L                    5                   7
## 4 48       MHS048             L                    5                   4
## 5 51       MHS051             L                    4                   6
##   motivasi_belajar       ipk
## 1               92 YA (>3.5)
## 2               87 YA (>3.5)
## 3               90 YA (>3.5)
## 4               92 YA (>3.5)
## 5               92 YA (>3.5)

df_filtered <- subset(df_mahasiswa, ipk > 3.5 & motivasi_belajar >85)
table(df_filtered$jenis_kelamin)

## 
## L P 
## 4 1