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

getwd()

## [1] "C:/Week 7"

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 ...

sum(is.na(df_mahasiswa))

## [1] 0

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[which.max(df_mahasiswa$motivasi_belajar), "id_mahasiswa"]

## [1] "MHS054"

df_mahasiswa[which.max(df_mahasiswa$frekuensi_login_lms), ]

##   X id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 6 6       MHS006             L                    3                   7
##   motivasi_belajar ipk
## 6               61 3.1

aggregate(ipk ~ (jam_belajar_per_hari >= 4), data = df_mahasiswa, mean)

##   jam_belajar_per_hari >= 4      ipk
## 1                     FALSE 2.935357
## 2                      TRUE 3.405185

df_mahasiswa[which.max(df_mahasiswa$ipk), c("id_mahasiswa", "motivasi_belajar")]

##    id_mahasiswa motivasi_belajar
## 18       MHS018               92

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

## 
## L P 
## 4 1