library(plotly)## Warning: package 'plotly' was built under R version 4.3.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.3.3##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutlibrary(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, unionsetwd("D:/kulyeah/6. semester 6/Big Data")
data <- read.table("fdata_cleaned.txt", sep = ',', header = T)
head(data)## X country birthYear gender internationalGrade talkAboutMaths
## 1 105097 Switzerland 1996 Male 10 Sometimes
## 2 270652 Italy 1996 Male 10 Never or rarely
## 3 131414 Czech Republic 1996 Male 8 Never or rarely
## 4 447976 Sweden 1996 Male 10
## 5 243870 Italy 1996 Female 10 Sometimes
## 6 384162 Portugal 1996 Female 9
## helpFriendsMaths extracurricularActivity participateInCompetitions
## 1 Sometimes 2 1
## 2 Sometimes 1 3
## 3 Sometimes 1 1
## 4 NA NA
## 5 Never or rarely 1 1
## 6 NA NA
## studyMoreThan2ExtraHoursADay playChess computerProgramming
## 1 2 1 1
## 2 2 3 2
## 3 1 1 2
## 4 NA NA NA
## 5 1 2 2
## 6 NA NA NA
## participateInMathClub Math_InterestsEnjoysReading Math_LookForwardtoLessons
## 1 1 2 3
## 2 1 3 2
## 3 1 2 3
## 4 NA NA NA
## 5 1 1 1
## 6 NA NA NA
## Math.EnjoyMaths Math.Interested Motivation_
## 1 4 4 4
## 2 3 3 3
## 3 2 2 3
## 4 NA NA NA
## 5 1 1 2
## 6 NA NA NA
## MotivationWorthwhileForCareerChances MotivationImportantForFutureStudy
## 1 4 3
## 2 3 3
## 3 2 3
## 4 NA NA
## 5 1 1
## 6 NA NA
## MotivationHelpsGetJob ProblemSolvingCanHandleLotofInformation
## 1 3 4
## 2 4 4
## 3 4 3
## 4 NA NA
## 5 1 1
## 6 NA NA
## ProblemSolvingQuicktoUnderstand ProblemSolvingSeekExplanations
## 1 3 4
## 2 3 2
## 3 3 4
## 4 NA NA
## 5 2 2
## 6 NA NA
## ProblemSolvingCanLinkFacts ProblemSolvingLikeSolveComplexProblems MathScore
## 1 4 4 492.1405
## 2 2 5 533.7358
## 3 3 2 506.4730
## 4 NA NA 520.4938
## 5 2 4 439.6401
## 6 NA NA 434.1876
## ReadScore ScienceScore motivation interest behaivior prob_solv_skills
## 1 392.9348 426.2775 3.50 3.25 1.333333 3.8
## 2 506.8110 515.4233 3.25 2.75 2.000000 3.2
## 3 482.6725 532.8609 3.00 2.25 1.166667 3.0
## 4 516.4344 492.1112 NA NA NA NA
## 5 490.0139 454.9981 1.25 1.00 1.333333 2.2
## 6 459.8301 536.1246 NA NA NA NAData berjumlah sebanyak 97098 baris / observasi dengan 33 variabel
skormath <- data %>% filter(!is.na(MathScore)) %>% group_by(country) %>% summarise(meanMath = mean(MathScore)) %>% arrange(desc(meanMath)) %>% select(country, meanMath)
head(skormath)## # A tibble: 6 × 2
## country meanMath
## <chr> <dbl>
## 1 "China (Shanghai) " 610.
## 2 "Singapore" 567.
## 3 "Hong Kong-China" 561.
## 4 "Chinese Taipei " 555.
## 5 "Republic of Korea" 553.
## 6 "Japan" 538.fig1 <- plot_ly(
x = c(skormath$country),
y = c(skormath$meanMath),
name = "Skor Matematika",
type = "bar"
)
mathgender <- data %>% filter(!is.na(gender) & !is.na(MathScore)) %>% select(gender, MathScore)
boxmath <- plot_ly(mathgender, x= ~gender, y = ~MathScore, color = ~gender, type = "box")
talkmath <- data %>% filter(!is.na(talkAboutMaths)) %>% count(talkAboutMaths)
talkmath <- talkmath[-1,]
piemath <- plot_ly(talkmath, labels = ~talkAboutMaths, values = ~n, type = "pie")
mathchart <- subplot(fig1, boxmath, nrows = 2, margin = 0.07)## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levels
## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levelsmathchart <- mathchart %>% layout(title = "Skor Matematika PISA Tahun 2015",
xaxis = list(zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'),
yaxis = list(
zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'))
mathchartpiemath %>% layout(title= "Persentase Siswa yang membicarakan matematika")Dapat dilihat bahwa negara china mendominasi skor matematika dengan mendapatkan rataan tertinggi. Selain itu, ternyata secara keseluruhan skor matematika laki - laki lebih tinggi dibandingkan wanita
Peserta Tes PISA, ternyata tidak selalu membicarakan matematika. Bahkan yang jarang dan tidak pernah berbincang matematika ada sebanyak >30%
skorbaca <- data %>% filter(!is.na(ReadScore)) %>% group_by(country) %>% summarise(meanread = mean(ReadScore)) %>% arrange(desc(meanread)) %>% select(country, meanread)
head(skorbaca)## # A tibble: 6 × 2
## country meanread
## <chr> <dbl>
## 1 "China (Shanghai) " 567.
## 2 "Hong Kong-China" 541.
## 3 "Japan" 538.
## 4 "Republic of Korea" 537.
## 5 "Singapore" 536.
## 6 "Poland " 524.fig2 <- plot_ly(
x = c(skorbaca$country),
y = c(skorbaca$meanread),
name = "Skor Baca",
type = "bar",
marker = list(color = 'rgb(158,202,225)')
)
readgender <- data %>% select(gender, ReadScore)
boxread <- plot_ly(readgender, x = ~gender, y = ~ReadScore, color = ~gender ,type = "box")
readchart <- subplot(fig2, boxread, nrows = 2, margin = 0.07)## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levels
## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levelsreadchart <- readchart %>% layout(title = "Skor Literasi PISA Tahun 2015",
xaxis = list(zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'),
yaxis = list(
zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'))
readchartstudy <- data %>% filter(!is.na(studyMoreThan2ExtraHoursADay)) %>% count(studyMoreThan2ExtraHoursADay)
piestudy <- plot_ly(study, labels = ~studyMoreThan2ExtraHoursADay, values = ~n, type = "pie")
piestudy %>% layout(title = "Persentase Tingkatan Lama Belajar Tambahan Siswa")Lagi - lagi negara China memegang skor tertinggi dalam hal membaca. Hal ini berbanding lurus dengan skor matematika yang dijelaskan sebelumnya.
Sedangkan berdasar gender, didapat bahwa secara keseluruhan rata - rata wanita mendapatkan skor baca lebih baik dibandingkan laki - laki.
Ternyata, peserta pisa mayoritas tidak banyak menambah jam belajar mereka. Hal ini wajar karena peserta PIsA bukanlah siswa terbaik setiap negara melainkan rata - rata yang menggambarkan negara tersebut.
skorscience <- data %>% filter(!is.na(ScienceScore)) %>% group_by(country) %>% summarise(meanscience = mean(ScienceScore)) %>% arrange(desc(meanscience)) %>% select(country, meanscience)
head(skorscience)## # A tibble: 6 × 2
## country meanscience
## <chr> <dbl>
## 1 "China (Shanghai) " 579.
## 2 "Hong Kong-China" 554.
## 3 "Japan" 548.
## 4 "Singapore" 545.
## 5 "Estonia" 542.
## 6 "Republic of Korea" 538.fig3 <- plot_ly(
x = c(skorscience$country),
y = c(skorscience$meanscience),
name = "Skor Science",
type = "bar",
marker = list(color = 'rgb(58,200,225)')
)
sciencegender <- data %>% select(gender, ScienceScore)
boxscience <- plot_ly(sciencegender, x = ~gender, y = ~ScienceScore, color = ~gender, type = "box" )
sciencechart <- subplot(fig3, boxscience, nrows = 2, margin = 0.07)## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levels
## Warning in RColorBrewer::brewer.pal(N, "Set2"): minimal value for n is 3, returning requested palette with 3 different levelssciencechart <- sciencechart %>% layout(title = "Skor Science PISA Tahun 2015",
xaxis = list(zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'),
yaxis = list(
zerolinecolor = '#ffff',
zerolinewidth = 1,
gridcolor = 'ffff'))
sciencechartprobsolv <- data %>% filter(!is.na(prob_solv_skills)) %>% select(prob_solv_skills)
histps <- plot_ly(x = ~probsolv$prob_solv_skills, type = "histogram")
histps <- histps %>% layout(title = "Histogram Problem Solving Skills", bargap = 0.1)
histpsUntuk ke-3 kalinya, pada penyelenggaraan PISA tahun 2015, China berhasil mengungguli bidang science. Sama dengan 2 bidang sebelumnya, China mendapatkan skor tertinggi dengan nilai rata - rata 578.9.
Pada sebaran nilai berdasar gender, untuk nilai science baik laki - laki maupun wanita memiliki sebaran nilai yang tidak jauh berbeda. Artinya kemampuan rata - rata science siswa di dunia tidak berbeda antara pria dan wanita.
Sebaran data histogram problem solving menunjukan mayoritas siswa memiliki skor 2 sampai 3.
skorbaca <- skorbaca %>% arrange(country)
skormath <- skormath %>% arrange(country)
skorscience <- skorscience %>% arrange(country)
databaru <- data.frame(skorbaca$country, skormath$meanMath, skorbaca$meanread, skorscience$meanscience)
colnames(databaru) <- c("country", "meanmath", "meanread", "meanscience")
skorgrup <- databaru %>% plot_ly()
skorgrup <- skorgrup %>% add_trace(x = ~country, y = ~meanmath, type = 'bar', name = "meanmath", text = databaru$meanmath, textposition = 'auto', marker = list(color = "#22a7f0", line = list(color = 'rgb(8,48,107)', width = 1.5)))
skorgrup <- skorgrup %>% add_trace(x = ~country, y = ~meanread, type = 'bar', name = "meanread", text = databaru$meanread, textposition = 'auto', marker = list(color = "#76c68f", line = list(color = 'rgb(8,48,107)', width = 1.5)))
skorgrup <- skorgrup %>% add_trace(x = ~country, y = ~meanscience, type = 'bar', name = "meanscience" , text = databaru$meanscience, textposition = 'auto', marker = list(color = "#c9e52f", line = list(color = 'rgb(8,48,107)', width = 1.5)))
skorgrup <- skorgrup %>% layout(title = 'Skor Pisa Dunia 2015',
barmode = 'group',
xaxis = list(title = ""),
yaxis = list(title = ""))
skorgrup# PIE CHART TINGKAT KELAS
dfgrade <- data %>% count(internationalGrade)
dfgrade <- dfgrade[-c(7:8),]
grade <- plot_ly(dfgrade, labels = ~internationalGrade, values = ~n, type = "pie")
grade %>% layout(title = 'Persentase Tingkatan Kelas Peserta PISA 2015')Dapat dilihat ternyata mayoritas peserta berada di kelas 10 (International Grade)
# BUBBLE CHART
hub <- data %>% filter(!is.na(motivation) & !is.na(interest)) %>% rowwise() %>% mutate(meanscore = mean(c(MathScore, ReadScore, ScienceScore))) %>% select(country,meanscore, motivation, interest)
hub <- hub %>% group_by(country) %>% summarise(meanmot = mean(motivation), meanint = mean(interest)) %>% select(country, meanmot, meanint)
bub <- plot_ly(hub, x = ~meanint, y = ~meanmot, text = ~country, type = 'scatter', mode = 'markers', color = ~country) %>% layout(title = "Student Motivation & Interest PISA 2015")
bub## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colorsbub <- plot_ly(hub, x = ~meanint, y = ~meanmot, text = ~country, type = 'scatter', mode = 'markers', color = ~country) %>% add_text(text = ~country, textposition = 'bottom center') %>% layout(title = "Student Motivation & Interest PISA 2015", showlegend = F)
bub ## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors