Kuis Pengantar Sains Data-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 ...

anyNA(df_mahasiswa)

## [1] FALSE

table(df_mahasiswa$jenis_kelamin)

## 
##  L  P 
## 32 23

library(readr)
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

hitung <- df_mahasiswa %>%
  group_by(jenis_kelamin) %>%
  summarise(rata_rata_ipk = mean(ipk, na.rm = TRUE)) %>%
  arrange(desc(rata_rata_ipk))
tertinggi <- hitung %>% slice(1)
tertinggi

## # A tibble: 1 × 2
##   jenis_kelamin rata_rata_ipk
##   <chr>                 <dbl>
## 1 P                      3.18

max_motivasi <- max(df_mahasiswa$motivasi_belajar, na.rm = TRUE)
hasil <- df_mahasiswa %>% 
  filter(motivasi_belajar == max_motivasi) %>% 
  select(id_mahasiswa, motivasi_belajar)
print(hasil)

##   id_mahasiswa motivasi_belajar
## 1       MHS054              100

mx <- max(df_mahasiswa$frekuensi_login_lms, na.rm = TRUE)
res <- df_mahasiswa %>%
  filter(frekuensi_login_lms == mx) %>%
  transmute(id_mahasiswa, frekuensi_login_lms, ipk, ipk_tinggi = ipk > 3.5)
print(res)

##    id_mahasiswa frekuensi_login_lms  ipk ipk_tinggi
## 1        MHS006                   7 3.10      FALSE
## 2        MHS007                   7 2.98      FALSE
## 3        MHS017                   7 3.06      FALSE
## 4        MHS018                   7 3.89       TRUE
## 5        MHS022                   7 3.69       TRUE
## 6        MHS031                   7 3.22      FALSE
## 7        MHS033                   7 3.11      FALSE
## 8        MHS041                   7 3.73       TRUE
## 9        MHS044                   7 3.15      FALSE
## 10       MHS055                   7 3.21      FALSE

df_mahasiswa %>%
  group_by(jam_belajar_per_hari) %>%
  summarise(rata_rata_ipk = mean(ipk))

## # A tibble: 5 × 2
##   jam_belajar_per_hari rata_rata_ipk
##                  <int>         <dbl>
## 1                    1          2.79
## 2                    2          3.06
## 3                    3          2.95
## 4                    4          3.33
## 5                    5          3.51

max_ipk <- max(df_mahasiswa$ipk, na.rm = TRUE)
hasil <- df_mahasiswa %>%
  filter(ipk == max_ipk) %>%
  select(id_mahasiswa, ipk, motivasi_belajar)
print(hasil)

##   id_mahasiswa  ipk motivasi_belajar
## 1       MHS018 3.89               92

rekap_jenis_kelamin <- df_mahasiswa %>%
  filter(ipk > 3.5, motivasi_belajar > 85) %>%
  count(jenis_kelamin, name = "jumlah")
L <- rekap_jenis_kelamin$jumlah[rekap_jenis_kelamin$jenis_kelamin == "L"]; if (length(L) == 0) L <- 0
P <- rekap_jenis_kelamin$jumlah[rekap_jenis_kelamin$jenis_kelamin == "P"]; if (length(P) == 0) P <- 0
cat("L =", L, "; P =", P, "\n")

## L = 4 ; P = 1