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
library (ggplot2)
MAHASISWA <- read.csv("df_mahasiswa.csv")
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
## 7 7 MHS007 P 1 7
## 8 8 MHS008 L 3 4
## 9 9 MHS009 P 2 6
## 10 10 MHS010 L 1 5
## 11 11 MHS011 L 1 1
## 12 12 MHS012 P 1 2
## 13 13 MHS013 P 2 6
## 14 14 MHS014 L 4 2
## 15 15 MHS015 L 1 2
## 16 16 MHS016 L 5 1
## 17 17 MHS017 L 2 7
## 18 18 MHS018 L 5 7
## 19 19 MHS019 L 5 2
## 20 20 MHS020 L 3 1
## 21 21 MHS021 L 1 6
## 22 22 MHS022 P 4 7
## 23 23 MHS023 L 4 4
## 24 24 MHS024 P 5 4
## 25 25 MHS025 L 3 1
## 26 26 MHS026 L 4 6
## 27 27 MHS027 L 2 3
## 28 28 MHS028 P 2 6
## 29 29 MHS029 L 2 2
## 30 30 MHS030 P 5 3
## 31 31 MHS031 P 2 7
## 32 32 MHS032 L 1 2
## 33 33 MHS033 P 1 7
## 34 34 MHS034 P 5 4
## 35 35 MHS035 L 4 1
## 36 36 MHS036 P 3 1
## 37 37 MHS037 L 4 6
## 38 38 MHS038 L 4 1
## 39 39 MHS039 P 1 1
## 40 40 MHS040 L 4 2
## 41 41 MHS041 L 5 7
## 42 42 MHS042 P 4 6
## 43 43 MHS043 P 4 5
## 44 44 MHS044 P 2 7
## 45 45 MHS045 P 5 2
## 46 46 MHS046 L 1 3
## 47 47 MHS047 L 4 5
## 48 48 MHS048 L 5 4
## 49 49 MHS049 P 4 5
## 50 50 MHS050 P 2 4
## 51 51 MHS051 L 4 6
## 52 52 MHS052 L 4 4
## 53 53 MHS053 L 3 4
## 54 54 MHS054 L 5 4
## 55 55 MHS055 P 2 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
## 7 44 2.98
## 8 69 3.08
## 9 44 2.82
## 10 46 2.93
## 11 56 2.64
## 12 35 2.71
## 13 59 3.11
## 14 81 3.31
## 15 44 2.90
## 16 90 3.46
## 17 52 3.06
## 18 92 3.89
## 19 84 3.09
## 20 73 2.73
## 21 47 2.96
## 22 72 3.69
## 23 83 3.54
## 24 81 3.61
## 25 70 2.65
## 26 89 3.32
## 27 59 2.94
## 28 53 3.14
## 29 48 2.89
## 30 87 3.40
## 31 71 3.22
## 32 39 2.66
## 33 46 3.11
## 34 87 3.56
## 35 91 3.13
## 36 66 2.95
## 37 68 3.67
## 38 90 3.29
## 39 52 2.52
## 40 80 3.17
## 41 90 3.73
## 42 73 3.05
## 43 91 3.29
## 44 63 3.15
## 45 96 3.33
## 46 43 2.49
## 47 82 3.13
## 48 92 3.70
## 49 73 3.22
## 50 57 3.05
## 51 92 3.65
## 52 88 3.30
## 53 80 3.29
## 54 100 3.41
## 55 71 3.21
MAHASISWA_selected <- select(MAHASISWA, id_mahasiswa, jenis_kelamin, jam_belajar_per_hari, frekuensi_login_lms, motivasi_belajar, ipk )
head(MAHASISWA_selected)
## id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 1 MHS001 L 4 1
## 2 MHS002 P 4 2
## 3 MHS003 P 2 6
## 4 MHS004 P 5 3
## 5 MHS005 L 3 2
## 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(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(MAHASISWA))
## X id_mahasiswa jenis_kelamin
## 0 0 0
## jam_belajar_per_hari frekuensi_login_lms motivasi_belajar
## 0 0 0
## ipk
## 0
summary(MAHASISWA)
## X id_mahasiswa jenis_kelamin jam_belajar_per_hari
## Min. : 1.0 Length:55 Length:55 Min. :1.000
## 1st Qu.:14.5 Class :character Class :character 1st Qu.:2.000
## Median :28.0 Mode :character Mode :character Median :3.000
## Mean :28.0 Mean :3.127
## 3rd Qu.:41.5 3rd Qu.:4.000
## Max. :55.0 Max. :5.000
## frekuensi_login_lms motivasi_belajar ipk
## Min. :1.000 Min. : 35.0 Min. :2.490
## 1st Qu.:2.000 1st Qu.: 56.5 1st Qu.:2.955
## Median :4.000 Median : 73.0 Median :3.130
## Mean :4.018 Mean : 71.0 Mean :3.166
## 3rd Qu.:6.000 3rd Qu.: 87.0 3rd Qu.:3.365
## Max. :7.000 Max. :100.0 Max. :3.890
aggregate(ipk ~ jenis_kelamin, data = MAHASISWA, mean)
## jenis_kelamin ipk
## 1 L 3.158125
## 2 P 3.176957
sort(table(MAHASISWA$motivasi_belajar), decreasing = TRUE)[1]
## 73
## 4
tertinggi <- MAHASISWA[which.max(MAHASISWA$ipk), ]
tertinggi
## X id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 18 18 MHS018 L 5 7
## motivasi_belajar ipk
## 18 92 3.89
terpilih <- subset(MAHASISWA, ipk > 3.5 & motivasi_belajar > 85)
terpilih
## X id_mahasiswa jenis_kelamin jam_belajar_per_hari frekuensi_login_lms
## 18 18 MHS018 L 5 7
## 34 34 MHS034 P 5 4
## 41 41 MHS041 L 5 7
## 48 48 MHS048 L 5 4
## 51 51 MHS051 L 4 6
## motivasi_belajar ipk
## 18 92 3.89
## 34 87 3.56
## 41 90 3.73
## 48 92 3.70
## 51 92 3.65
max_login <- max(MAHASISWA$frekuensi_login_lms, na.rm = TRUE)
mahasiswa_login_tertinggi <- subset(MAHASISWA, frekuensi_login_lms == max_login)
mahasiswa_login_tertinggi$ipk_tinggi <- mahasiswa_login_tertinggi$ipk > 3.5
mahasiswa_login_tertinggi[, c("id_mahasiswa", "frekuensi_login_lms", "ipk", "ipk_tinggi")]
## id_mahasiswa frekuensi_login_lms ipk ipk_tinggi
## 6 MHS006 7 3.10 FALSE
## 7 MHS007 7 2.98 FALSE
## 17 MHS017 7 3.06 FALSE
## 18 MHS018 7 3.89 TRUE
## 22 MHS022 7 3.69 TRUE
## 31 MHS031 7 3.22 FALSE
## 33 MHS033 7 3.11 FALSE
## 41 MHS041 7 3.73 TRUE
## 44 MHS044 7 3.15 FALSE
## 55 MHS055 7 3.21 FALSE
mahasiswa_4jam_lebih <- subset(MAHASISWA, jam_belajar_per_hari >= 4)
mahasiswa_kurang_4jam <- subset(MAHASISWA, jam_belajar_per_hari < 4)
rata_ipk_4jam_lebih <- mean(mahasiswa_4jam_lebih$ipk, na.rm = TRUE)
rata_ipk_kurang_4jam <- mean(mahasiswa_kurang_4jam$ipk, na.rm = TRUE)
rata_ipk_4jam_lebih
## [1] 3.405185
rata_ipk_kurang_4jam
## [1] 2.935357