VDE 20-05-2024

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

library('tidyr')
library('readr')

## Warning: package 'readr' 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('ggplot2')

setwd("C:/Users/Students/Downloads")
train = read.csv("train (1).csv",header = T)
train = 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              Q

p_age = ggplot(train) +
  geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
  theme(legend.position = "right")

p_sex = ggplot(train, mapping = aes(x = Sex, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Sex') +
  scale_fill_discrete(name="Surv")

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")

p_emb = ggplot(train, aes(Embarked, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Embarked') +
  theme(legend.position = "none")

p_sib = ggplot(train, aes(SibSp, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'SibSp') +
  theme(legend.position = "none")

p_par = ggplot(train, aes(Parch, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Parch') +
  theme(legend.position = "none")

p_fare = ggplot(train) +
  geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
  scale_x_log10() +
  theme(legend.position = "none")

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