R Markdown
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 <- as.data.frame(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
sort(table(df_mahasiswa$jenis_kelamin))
##
## P L
## 23 32
aggregate(ipk ~ jenis_kelamin, data = df_mahasiswa, mean)
## jenis_kelamin ipk
## 1 L 3.158125
## 2 P 3.176957
df_mahasiswa[order(-df_mahasiswa$motivasi_belajar), c("id_mahasiswa", "motivasi_belajar")]|>
head(1)
## id_mahasiswa motivasi_belajar
## 54 MHS054 100
df_mahasiswa[order(-df_mahasiswa$frekuensi_login_lms), c("id_mahasiswa", "frekuensi_login_lms", "ipk")]
## id_mahasiswa frekuensi_login_lms ipk
## 6 MHS006 7 3.10
## 7 MHS007 7 2.98
## 17 MHS017 7 3.06
## 18 MHS018 7 3.89
## 22 MHS022 7 3.69
## 31 MHS031 7 3.22
## 33 MHS033 7 3.11
## 41 MHS041 7 3.73
## 44 MHS044 7 3.15
## 55 MHS055 7 3.21
## 3 MHS003 6 3.07
## 9 MHS009 6 2.82
## 13 MHS013 6 3.11
## 21 MHS021 6 2.96
## 26 MHS026 6 3.32
## 28 MHS028 6 3.14
## 37 MHS037 6 3.67
## 42 MHS042 6 3.05
## 51 MHS051 6 3.65
## 10 MHS010 5 2.93
## 43 MHS043 5 3.29
## 47 MHS047 5 3.13
## 49 MHS049 5 3.22
## 8 MHS008 4 3.08
## 23 MHS023 4 3.54
## 24 MHS024 4 3.61
## 34 MHS034 4 3.56
## 48 MHS048 4 3.70
## 50 MHS050 4 3.05
## 52 MHS052 4 3.30
## 53 MHS053 4 3.29
## 54 MHS054 4 3.41
## 4 MHS004 3 3.43
## 27 MHS027 3 2.94
## 30 MHS030 3 3.40
## 46 MHS046 3 2.49
## 2 MHS002 2 3.45
## 5 MHS005 2 2.83
## 12 MHS012 2 2.71
## 14 MHS014 2 3.31
## 15 MHS015 2 2.90
## 19 MHS019 2 3.09
## 29 MHS029 2 2.89
## 32 MHS032 2 2.66
## 40 MHS040 2 3.17
## 45 MHS045 2 3.33
## 1 MHS001 1 3.12
## 11 MHS011 1 2.64
## 16 MHS016 1 3.46
## 20 MHS020 1 2.73
## 25 MHS025 1 2.65
## 35 MHS035 1 3.13
## 36 MHS036 1 2.95
## 38 MHS038 1 3.29
## 39 MHS039 1 2.52
rajin <- df_mahasiswa %>%
filter(jam_belajar_per_hari >= 4) %>%
select(ipk, jam_belajar_per_hari) %>%
summarise(mean = mean(ipk))
malas <-df_mahasiswa %>%
filter(jam_belajar_per_hari < 4) %>%
select(ipk, jam_belajar_per_hari) %>%
summarise(mean = mean(ipk))
rajin
## mean
## 1 3.405185
malas
## mean
## 1 2.935357
mahasiswa_baik <- df_mahasiswa[which.max(df_mahasiswa$ipk),]
mahasiswa_baik
## 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
ipktinggi <- df_mahasiswa|>
filter(ipk > 3.5 & motivasi_belajar > 85)|>
select(jenis_kelamin,motivasi_belajar,ipk)|>
group_by(jenis_kelamin)|>
summarise(sum = n())
ipktinggi
## # A tibble: 2 × 2
## jenis_kelamin sum
## <chr> <int>
## 1 L 4
## 2 P 1