Exercise_Week12
Putri Amalia Farhana
2024-05-17
knitr::opts_chunk$set(echo=TRUE)
options(repos=c(CRAN="https://cloud.r-project.org"))##Materi 1
setwd('C:/Users/ACER/Downloads')
netflix = read.csv('netflix_titles.csv')
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.3.3pie <- ggplot(netflix, aes(x = "", fill = factor(type))) +
geom_bar(width = 1) + theme(axis.line = element_blank(),
plot.title = element_text(hjust = 0.5, size = 22)) + labs(fill = "class",
x=NULL,
y=NULL,
title = " Pie Chart of Netflix shows ") +
coord_polar(theta = "y",start=0)
pie
par(c(2,1))## Warning in par(c(2, 1)): argument 1 does not name a graphical parameter## NULLggplot(netflix, aes(x = "", fill = factor(type))) +
geom_bar()
ggplot(netflix, aes(y = "", fill = factor(type))) +
geom_bar()
setwd('C:/Users/ACER/Downloads')
netflix = read.csv('netflix_titles.csv')
library(ggplot2)
custom_col <- c("red", "green", "orange")
ggplot(netflix, aes(x = "", fill = factor(type)))+ geom_bar(width=1) + theme(axis.line = element_blank(),
plot.title = element_text(hjust = 0.5, size = 22)) + labs(fill = "class",
x=NULL,
y=NULL,
title = " Pie Chart of Netflix shows ") +
coord_polar(theta = "y",start=0) + scale_fill_manual(values=custom_col)
#wrangle
install.packages("readr")## Installing package into 'C:/Users/ACER/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'readr' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'readr'## Warning in file.copy(savedcopy, lib, recursive = TRUE): problem copying
## C:\Users\ACER\AppData\Local\R\win-library\4.3\00LOCK\readr\libs\x64\readr.dll
## to C:\Users\ACER\AppData\Local\R\win-library\4.3\readr\libs\x64\readr.dll:
## Permission denied## Warning: restored 'readr'##
## The downloaded binary packages are in
## C:\Users\ACER\AppData\Local\Temp\RtmpSkN19w\downloaded_packagesinstall.packages("forcats")## Installing package into 'C:/Users/ACER/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'forcats' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\ACER\AppData\Local\Temp\RtmpSkN19w\downloaded_packagesinstall.packages("modelr")## Installing package into 'C:/Users/ACER/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'modelr' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\ACER\AppData\Local\Temp\RtmpSkN19w\downloaded_packageslibrary('dplyr') #data manipulation## Warning: package 'dplyr' was built under R version 4.3.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary('tidyr') #data manipulation## Warning: package 'tidyr' was built under R version 4.3.3library('readr') #data input## Warning: package 'readr' was built under R version 4.3.3library('stringr') #string manipulation## Warning: package 'stringr' was built under R version 4.3.3library('forcats') #factor manipulation## Warning: package 'forcats' was built under R version 4.3.3library('modelr') #factor manipulation## Warning: package 'modelr' was built under R version 4.3.3train <- train %>% mutate(
Survived = factor(Survived),
Pclass = factor(Pclass),
Embarked = factor(Embarked),
Sex = factor(Sex)
)
head(train)summary(train)## PassengerId Survived Pclass Name Sex
## Min. : 1.0 0:549 1:216 Length:891 female:314
## 1st Qu.:223.5 1:342 2:184 Class :character male :577
## Median :446.0 3:491 Mode :character
## Mean :446.0
## 3rd Qu.:668.5
## Max. :891.0
##
## Age SibSp Parch Ticket
## Min. : 0.42 Min. :0.000 Min. :0.0000 Length:891
## 1st Qu.:20.12 1st Qu.:0.000 1st Qu.:0.0000 Class :character
## Median :28.00 Median :0.000 Median :0.0000 Mode :character
## Mean :29.70 Mean :0.523 Mean :0.3816
## 3rd Qu.:38.00 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :80.00 Max. :8.000 Max. :6.0000
## NA's :177
## Fare Cabin Embarked
## Min. : 0.00 Length:891 : 2
## 1st Qu.: 7.91 Class :character C:168
## Median : 14.45 Mode :character Q: 77
## Mean : 32.20 S:644
## 3rd Qu.: 31.00
## Max. :512.33
## summary(train)## PassengerId Survived Pclass Name Sex
## Min. : 1.0 0:549 1:216 Length:891 female:314
## 1st Qu.:223.5 1:342 2:184 Class :character male :577
## Median :446.0 3:491 Mode :character
## Mean :446.0
## 3rd Qu.:668.5
## Max. :891.0
##
## Age SibSp Parch Ticket
## Min. : 0.42 Min. :0.000 Min. :0.0000 Length:891
## 1st Qu.:20.12 1st Qu.:0.000 1st Qu.:0.0000 Class :character
## Median :28.00 Median :0.000 Median :0.0000 Mode :character
## Mean :29.70 Mean :0.523 Mean :0.3816
## 3rd Qu.:38.00 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :80.00 Max. :8.000 Max. :6.0000
## NA's :177
## Fare Cabin Embarked
## Min. : 0.00 Length:891 : 2
## 1st Qu.: 7.91 Class :character C:168
## Median : 14.45 Mode :character Q: 77
## Mean : 32.20 S:644
## 3rd Qu.: 31.00
## Max. :512.33
## setwd('C:/Users/ACER/Downloads')
train <- read.csv('train.csv')
#memberi warna
custom_col <- c("#d90429","#ef233c","#edf2f4")
pclass_counts <- as.data.frame(table(train$Pclass))
colnames(pclass_counts) <- c("Pclass", "Frequency")
#membuat pie chart
pie <- ggplot(pclass_counts, aes(x = "",
y = Frequency,
fill = factor(Pclass))) +
geom_bar(width = 1, stat = "identity") +
coord_polar(theta = "y", start = 0) +
scale_fill_manual(values = custom_col) +
labs(fill = "Class",
x = NULL,
y = NULL,
title = "Pie Chart of Pclass") +
theme_void() +
theme(axis.line = element_blank(),
plot.title = element_text(hjust = 0.5,
size = 22))
pie
##others
p_age = ggplot(train) +
geom_freqpoly(mapping = aes(x = Age, color = as.factor(Survived)), binwidth = 1) +
theme(legend.position = "right") + scale_fill_manual(values = custom_col)
p_age
Fig.2
p_sex = ggplot(train, mapping = aes(x = Sex, fill = as.factor(Survived))) +
geom_bar(stat='count', position='fill') +
labs(x = 'Sex') +
scale_fill_discrete(name="Survived") + scale_fill_manual(values = custom_col)## Scale for fill is already present.
## Adding another scale for fill, which will replace the existing scale.p_sex
Fig.2
p_class = ggplot(train, mapping = aes(x = Pclass, fill = as.factor(Survived), colour = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Pclass') +
theme(legend.position = "none") + scale_fill_manual(values = custom_col)
p_class
Fig.2
p_emb = ggplot(train, aes(Embarked, fill = as.factor(Survived))) +
geom_bar(stat='count', position='fill') +
labs(x = 'Embarked') +
theme(legend.position = "none") + scale_fill_manual(values = custom_col)
p_emb
Fig.2
p_sib = ggplot(train, aes(SibSp, fill = as.factor(Survived))) +
geom_bar(stat='count', position='fill') +
labs(x = 'SibSp') +
theme(legend.position = "none") + scale_fill_manual(values = custom_col)
p_sib
Fig.2
p_par = ggplot(train, aes(Parch, fill = as.factor(Survived))) +
geom_bar(stat='count', position='fill') +
labs(x = 'Parch') +
theme(legend.position = "none")+ scale_fill_manual(values = custom_col)
p_par
Fig.2
p_fare = ggplot(train) +
geom_freqpoly(mapping = aes(Fare, color = as.factor(Survived)), binwidth = 0.05) +
scale_x_log10() +
theme(legend.position = "none")+ scale_fill_manual(values = custom_col)
p_fare
Fig.2