Data Train
Khansa Amelia (5052231014)
2024-05-17
library('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 4.3.3library('ggplot2')## Warning: package 'ggplot2' was built under R version 4.3.3train <- read.csv("C:/Users/khansa amelia/OneDrive/Documents/train.csv")
head(train)## 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 Qtrain <- train %>% mutate (
Survived = factor(Survived),
Pclass = factor(Pclass),
Embarked = factor(Embarked),
Sex = factor(Sex)
)
head(train)## 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 Qsummary(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
## ## 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 Qp_age = ggplot(train) +
geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
theme(legend.position = "right") +
scale_color_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_sex = ggplot(train, mapping = aes(x = Sex, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Sex') +
scale_fill_discrete(name="Surv") +
scale_fill_manual(name = "Surv", values = c("0" = "#74512D", "1" = "#AF8F6F"))## Scale for fill is already present.
## Adding another scale for fill, which will replace the existing scale.p_class = ggplot(train, mapping = aes(x = Pclass, fill = Survived, colour = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Pclass') +
theme(legend.position = "none") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F")) +
scale_color_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_emb = ggplot(train, aes(Embarked, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Embarked') +
theme(legend.position = "none") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_sib = ggplot(train, aes(SibSp, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'SibSp') +
theme(legend.position = "none") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_par = ggplot(train, aes(Parch, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Parch') +
theme(legend.position = "none") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_fare = ggplot(train) +
geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
scale_x_log10() +
theme(legend.position = "none") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_age
Fig.2
p_sex
Fig.2
p_fare
Fig.2
p_class
Fig.2
p_emb
Fig.2
p_sib
Fig.2
p_par
Fig.2
survived_counts <- train %>%
group_by(Survived) %>%
summarise(count = n())
p_survived_pie <- ggplot(survived_counts, aes(x = "", y = count, fill = factor(Survived))) +
geom_bar(stat = "identity", width = 1) +
coord_polar(theta = "y") +
theme_void() +
labs(fill = "Survived") +
theme(legend.position = "right") +
scale_fill_manual(values = c("0" = "#74512D", "1" = "#AF8F6F"))
p_survived_pie
sex_counts <- train %>%
group_by(Sex) %>%
summarise(count = n())
p_sex_pie <- ggplot(sex_counts, aes(x = "", y = count, fill = Sex)) +
geom_bar(stat = "identity", width = 1) +
coord_polar(theta = "y") +
theme_void() +
labs(fill = "Sex") +
theme(legend.position = "right") +
scale_fill_manual(values = c("male" = "#74512D", "female" = "#AF8F6F"))
p_sex_pie
p_class_bar <- ggplot(train, aes(x = Pclass, fill = Pclass)) +
geom_bar() +
labs(x = 'Pclass', y = 'Count', fill = 'Pclass') +
theme_minimal() +
theme(legend.position = "right") +
scale_fill_manual(values = c("1" = "#74512D", "2" = "#AF8F6F", "3" = "#D3C6A3"))
p_class_bar