library(ggplot2)

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

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 ...

library(dplyr)

df_mahasiswa %>%
  group_by(jenis_kelamin) %>%
  summarise(Total = n())

## # A tibble: 2 × 2
##   jenis_kelamin Total
##   <chr>         <int>
## 1 L                32
## 2 P                23

library(dplyr)

df_mahasiswa %>%
  group_by(jenis_kelamin) %>%
  summarise(ipk = mean(ipk, na.rm = TRUE)) %>%
  arrange(desc(ipk))

## # A tibble: 2 × 2
##   jenis_kelamin   ipk
##   <chr>         <dbl>
## 1 P              3.18
## 2 L              3.16

library(dplyr)

df_mahasiswa %>%
  filter(motivasi_belajar == max(motivasi_belajar, na.rm = TRUE)) %>%
  select(id_mahasiswa, motivasi_belajar)

##   id_mahasiswa motivasi_belajar
## 1       MHS054              100

# Cari nilai frekuensi login tertinggi
max_login <- max(df_mahasiswa$Frekuensi.Login.LMS, na.rm = TRUE)

## Warning in max(df_mahasiswa$Frekuensi.Login.LMS, na.rm = TRUE): no non-missing
## arguments to max; returning -Inf

# Ambil data mahasiswa dengan frekuensi login tertinggi
top_login <- df_mahasiswa[df_mahasiswa$Frekuensi.Login.LMS == max_login, ]

top_login

## [1] X                    id_mahasiswa         jenis_kelamin       
## [4] jam_belajar_per_hari frekuensi_login_lms  motivasi_belajar    
## [7] ipk                 
## <0 rows> (or 0-length row.names)

top_login$ipk > 3.5

## logical(0)

maks_login = max(df_mahasiswa$frekuensi_login_lms)

mahasiswa_login_tertinggi = subset(df_mahasiswa, frekuensi_login_lms == maks_login)

mahasiswa_login_tertinggi$ipk_tinggi = mahasiswa_login_tertinggi$ipk > 3.5

print(mahasiswa_login_tertinggi[, c("id_mahasiswa", "frekuensi_login_lms", "ipk","ipk_tinggi")])

##    id_mahasiswa frekuensi_login_lms  ipk ipk_tinggi
## 6        MHS006                   7 3.10      FALSE
## 7        MHS007                   7 2.98      FALSE
## 17       MHS017                   7 3.06      FALSE
## 18       MHS018                   7 3.89       TRUE
## 22       MHS022                   7 3.69       TRUE
## 31       MHS031                   7 3.22      FALSE
## 33       MHS033                   7 3.11      FALSE
## 41       MHS041                   7 3.73       TRUE
## 44       MHS044                   7 3.15      FALSE
## 55       MHS055                   7 3.21      FALSE

library(dplyr)

df_mahasiswa %>%
  mutate(jam_belajar_per_hari = ifelse(jam_belajar_per_hari >= 4, "≥4 Jam", "<4 Jam")) %>%
  group_by(jam_belajar_per_hari) %>%
  summarise(ipk = mean(ipk, na.rm = TRUE),
            jumlah_mahasiswa = n())

## # A tibble: 2 × 3
##   jam_belajar_per_hari   ipk jumlah_mahasiswa
##   <chr>                <dbl>            <int>
## 1 <4 Jam                2.94               28
## 2 ≥4 Jam                3.41               27

library(dplyr)

df_mahasiswa %>%
  filter(ipk == max(ipk, na.rm = TRUE)) %>%
  select(id_mahasiswa, ipk, motivasi_belajar)

##   id_mahasiswa  ipk motivasi_belajar
## 1       MHS018 3.89               92

library(dplyr)

df_mahasiswa %>%
  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