W12_StudyCase

Study Case

• Call Library

  Library

  dplyr : Data Manipulation

  tidyr : Data Manipulation

  readr : Data Input

  stringr : String Manipulation

  forcats : Factor Manipulation

  modelr : Factor Manipulation

  ggplot2 : Data Visualization

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) 
library(stringr)
library(forcats)
library(modelr) 
library(ggplot2) 

• Call Data Train

train = read.csv('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              Q

• Summary Data

summary(train)

##   PassengerId       Survived          Pclass          Name          
##  Min.   :  1.0   Min.   :0.0000   Min.   :1.000   Length:891        
##  1st Qu.:223.5   1st Qu.:0.0000   1st Qu.:2.000   Class :character  
##  Median :446.0   Median :0.0000   Median :3.000   Mode  :character  
##  Mean   :446.0   Mean   :0.3838   Mean   :2.309                     
##  3rd Qu.:668.5   3rd Qu.:1.0000   3rd Qu.:3.000                     
##  Max.   :891.0   Max.   :1.0000   Max.   :3.000                     
##                                                                     
##      Sex                 Age            SibSp           Parch       
##  Length:891         Min.   : 0.42   Min.   :0.000   Min.   :0.0000  
##  Class :character   1st Qu.:20.12   1st Qu.:0.000   1st Qu.:0.0000  
##  Mode  :character   Median :28.00   Median :0.000   Median :0.0000  
##                     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                                     
##     Ticket               Fare           Cabin             Embarked        
##  Length:891         Min.   :  0.00   Length:891         Length:891        
##  Class :character   1st Qu.:  7.91   Class :character   Class :character  
##  Mode  :character   Median : 14.45   Mode  :character   Mode  :character  
##                     Mean   : 32.20                                        
##                     3rd Qu.: 31.00                                        
##                     Max.   :512.33                                        
## 

• Data Manipulation

train <- train %>% mutate(
  Survived = factor(Survived),
  Pclass = factor(Pclass),
  Embarked = factor(Embarked),
  Sex = factor(Sex))

pclass_counts <- train %>% 
  group_by(Pclass) %>% 
  summarise(count = n()) %>% 
  mutate(percentage = count / sum(count) * 100,
         label = paste0(Pclass, " (", round(percentage, 1), "%)"))

• Create Pie Chart

custom_colors <- c("1" = "#00ADB5", "2" = "#393E46", "3" = "#222831")

p_pie_pclass <- ggplot(pclass_counts, aes(x = "", y = percentage, fill = as.factor(Pclass))) +
  geom_bar(width = 1, stat = "identity") +
  coord_polar("y") +
  theme_void() +
  theme(legend.position = "right") +
  labs(fill = "Pclass",
       x=NULL,
       y=NULL,
       title = "Pie Chart of Pclass ") +
  theme(axis.line = element_blank(), 
        plot.title = element_text(hjust = 0.5, size = 22))+
  geom_text(aes(label = label), position = position_stack(vjust = 0.5), col = "white") +
  scale_fill_manual(values = custom_colors)

p_pie_pclass

• Create

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

p_sex = ggplot(train, mapping = aes(x = Sex, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Sex') +
  scale_fill_manual(values = custom_colors) + theme_minimal()

p_class = ggplot(train, mapping = aes(x = Pclass, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Pclass') +
  theme(legend.position = "none") +scale_fill_manual(values = custom_colors) + theme_minimal()

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 = custom_colors) + theme_minimal()

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 = custom_colors) + theme_minimal()

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 = custom_colors) + theme_minimal()

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

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