library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.3
library(dplyr)
## 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, union
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.3.3
library(stringr)
## Warning: package 'stringr' was built under R version 4.3.3
library(forcats)
## Warning: package 'forcats' was built under R version 4.3.3
library(modelr)
## Warning: package 'modelr' was built under R version 4.3.3
library(magrittr)
## Warning: package 'magrittr' was built under R version 4.3.3
##
## Attaching package: 'magrittr'
## The following object is masked from 'package:tidyr':
##
## extract
PIE CHART
Netflix <- read.csv("netflix_titles.csv")
color <- c("cyan","purple","blue","pink3")
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=color)
STUDY CASE
data <- read.csv("train(2).csv")
head(data)
## PassengerId Survived Pclass
## 1 1 0 3
## 2 2 1 1
## 3 3 1 3
## 4 4 1 1
## 5 5 0 3
## 6 6 0 3
## Name Sex Age SibSp Parch
## 1 Braund, Mr. Owen Harris male 22 1 0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0
## 3 Heikkinen, Miss. Laina female 26 0 0
## 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0
## 5 Allen, Mr. William Henry male 35 0 0
## 6 Moran, Mr. James male NA 0 0
## Ticket Fare Cabin Embarked
## 1 A/5 21171 7.2500 S
## 2 PC 17599 71.2833 C85 C
## 3 STON/O2. 3101282 7.9250 S
## 4 113803 53.1000 C123 S
## 5 373450 8.0500 S
## 6 330877 8.4583 Q
data <- data %>% mutate(
Survived = factor(Survived),
Pclass = factor(Pclass),
Embarked = factor(Embarked),
Sex = factor(Sex)
)
head(data)
## PassengerId Survived Pclass
## 1 1 0 3
## 2 2 1 1
## 3 3 1 3
## 4 4 1 1
## 5 5 0 3
## 6 6 0 3
## Name Sex Age SibSp Parch
## 1 Braund, Mr. Owen Harris male 22 1 0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0
## 3 Heikkinen, Miss. Laina female 26 0 0
## 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0
## 5 Allen, Mr. William Henry male 35 0 0
## 6 Moran, Mr. James male NA 0 0
## Ticket Fare Cabin Embarked
## 1 A/5 21171 7.2500 S
## 2 PC 17599 71.2833 C85 C
## 3 STON/O2. 3101282 7.9250 S
## 4 113803 53.1000 C123 S
## 5 373450 8.0500 S
## 6 330877 8.4583 Q
summary(data)
## 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
##
color <- c("#662400","#B33F00","#FF6B1A","#006663")
pie1<- ggplot(data, aes(x = " ", fill = factor(Pclass))) + geom_bar(width = 0.5) +
theme(axis.line = element_blank(), plot.title = element_text(hjust=2,size=22)) +
labs(fill="Kategori",
x=NULL,
y=NULL,
title ="Pie Chart of Pclass Train " ) +
coord_polar(theta = "y", start=0) +
scale_fill_manual(values=color)
pie1
age = ggplot(data) +
geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
theme(legend.position = "right")
age
## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).
color <- c("#662400","#B33F00","#FF6B1A","#006663")
sex <- ggplot(data, mapping = aes(Sex, fill=Survived)) +
geom_bar(stat ='count', position = 'fill') +
labs(x = 'sex')+
scale_fill_discrete(name = "Surv") + scale_fill_manual(values=color)
## Scale for fill is already present.
## Adding another scale for fill, which will replace the existing scale.
sex
color <- c("#FF6B1A","#006663")
emb = ggplot(data, aes(Embarked, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Embarked') + scale_fill_manual(values=color)
emb
color <- c("#662400","#B33F00")
sib = ggplot(data, aes(SibSp, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'SibSp') + scale_fill_manual(values=color)
sib
color <- c("#662400","#B33F00","#FF6B1A","#006663")
par = ggplot(data, aes(Parch, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Parch') + scale_fill_manual(values=color)
par
color <- c("#FF6B1A","#006663")
fare = ggplot(data) +
geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
scale_x_log10() + scale_fill_manual(values=color)
fare
## Warning in scale_x_log10(): log-10 transformation introduced infinite values.
## Warning: Removed 15 rows containing non-finite outside the scale range
## (`stat_bin()`).
