data train vde
Nadine Amalia
2024-05-17
MATERI
# wrangle
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 4.3.3setwd( "C:/Users/ASUS/Documents")
data = read.csv("C:/Users/ASUS/Downloads/train.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 Qdata$Survived <- factor(data$Survived)
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 Qsummary(data)## PassengerId Survived Pclass Name Sex
## Min. : 1.0 0:549 Min. :1.000 Length:891 Length:891
## 1st Qu.:223.5 1:342 1st Qu.:2.000 Class :character Class :character
## Median :446.0 Median :3.000 Mode :character Mode :character
## Mean :446.0 Mean :2.309
## 3rd Qu.:668.5 3rd Qu.:3.000
## Max. :891.0 Max. :3.000
##
## 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 Length:891
## 1st Qu.: 7.91 Class :character Class :character
## Median : 14.45 Mode :character Mode :character
## Mean : 32.20
## 3rd Qu.: 31.00
## Max. :512.33
## # Visualisasi data dengan ggplot2
# Age vs. Survival dengan warna khusus
p_age = ggplot(data) +
geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
scale_color_manual(values = c("red", "blue")) + # Warna khusus untuk Survived
theme(legend.position = "right")
# Sex vs. Survival dengan warna khusus
p_sex = ggplot(data, mapping = aes(x = Sex, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Sex') +
scale_fill_manual(name = "Surv", values = c("#DFD0B8","#3C5B6F")) # Warna khusus untuk Survived
# Passenger Class vs. Survival dengan warna khusus
p_class = ggplot(data, mapping = aes(x = Pclass, fill = Survived, colour = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Pclass') +
scale_fill_manual(values = c("#E1AFD1", "#8E3E63")) + # Warna isi khusus
scale_color_manual(values = c("#E1AFD1", "#8E3E63")) + # Warna garis khusus
theme(legend.position = "none")
# Embarked vs. Survival dengan warna khusus
p_emb = ggplot(data, aes(Embarked, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Embarked') +
scale_fill_manual(values = c("#E5DDC5", "#B3C8CF")) + # Warna khusus untuk Survived
theme(legend.position = "none")
# Siblings/Spouses aboard vs. Survival dengan warna khusus
p_sib = ggplot(data, aes(SibSp, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'SibSp') +
scale_fill_manual(values = c("brown", "pink")) + # Warna khusus untuk Survived
theme(legend.position = "none")
# Parents/Children aboard vs. Survival dengan warna khusus
p_par = ggplot(data, aes(Parch, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Parch') +
scale_fill_manual(values = c("darkgreen", "lightblue")) + # Warna khusus untuk Survived
theme(legend.position = "none")
# Fare vs. Survival dengan warna khusus
p_fare = ggplot(data) +
geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
scale_x_log10() +
scale_color_manual(values = c("darkred", "darkblue")) + # Warna khusus untuk Survived
theme(legend.position = "none")
# Tampilkan plot
print(p_age)## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).
print(p_sex)
print(p_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()`).
print(p_class)
print(p_emb)
print(p_sib)
print(p_par)
# Visualisasi boxplot untuk variabel Age dengan warna khusus
boxplot_age <- ggplot(data, aes(x = Survived, y = Age, fill = Survived)) +
geom_boxplot(color = "black") + # warna garis
labs(x = "Survived", y = "Age", title = "Boxplot of Age by Survival Status") +
scale_fill_manual(values = c("pink", "skyblue")) + # warna khusus untuk Survived
theme_minimal()
# Visualisasi boxplot untuk variabel Fare dengan warna khusus
boxplot_fare <- ggplot(data, aes(x = Survived, y = Fare, fill = Survived)) +
geom_boxplot(color = "black") + # warna garis
labs(x = "Survived", y = "Fare", title = "Boxplot of Fare by Survival Status") +
scale_fill_manual(values = c("orange", "brown")) + # warna khusus untuk Survived
theme_minimal()
# Visualisasi boxplot untuk variabel Pclass dengan warna khusus
boxplot_pclass <- ggplot(data, aes(x = factor(Pclass), y = Fare, fill = factor(Pclass))) +
geom_boxplot(color = "black") + # warna garis
labs(x = "Pclass", y = "Fare", title = "Boxplot of Fare by Passenger Class") +
scale_fill_manual(values = c("#FDFFC2", "#EEEEEE", "#A3D8FF")) + # warna khusus untuk Pclass
theme_minimal()
# Tampilkan boxplot
boxplot_age## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
boxplot_fare
boxplot_pclass
# Histogram untuk variabel Age
hist_age <- ggplot(data, aes(x = Age)) +
geom_histogram(fill = "#74512D", color = "white", bins = 20) +
labs(x = "Age", y = "Frequency", title = "Histogram of Age") +
theme_minimal()
# Histogram untuk variabel Fare
hist_fare <- ggplot(data, aes(x = Fare)) +
geom_histogram(fill = "#006769", color = "#344C64", bins = 20) +
labs(x = "Fare", y = "Frequency", title = "Histogram of Fare") +
theme_minimal()
# Tampilkan histogram
hist_age## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).
hist_fare
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.