Materi

setwd("~/Belajar Coding/Kelas/R")

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(ggplot2)

dataku <- read.csv("netflix_titles.csv")

custom_col <- c("blue","purple","orange")

ggplot(dataku, aes(y = "", fill = factor(type))) +
  geom_bar(width = 1) +
  coord_polar(start = 0) +
  theme(axis.line = element_blank(),
        plot.title = element_text(hjust = 0.5, size = 22)) +
  labs(x="",
       y="",
       title = "Pie chart of Netflix shows") +
  scale_fill_manual(values = custom_col)

Study Case

data <- read.csv("train2.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
library(dplyr)
library(tidyr)
library(stringr)
library(ggplot2)
##   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                              
## 
warna1 <- c("navy","blue","purple")

ggplot(train, aes(y = "", fill = factor(Pclass))) +
  geom_bar() +
  coord_polar(start = 0) +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5, size = 20)) +
  labs(x = "",
       y = "",
       title = "Komposisi Kelas Tiket",
       fill = "Pclass") +
  scale_fill_manual(values = warna1)

## guides=false untuk menghilangkan legend
train_clear <- na.omit(train)

warna2 <- c("yellow","orange")

ggplot(train_clear, aes(Sex,Age)) + 
  geom_boxplot(fill = warna2) +
  labs(x = "Gender",
       y = "Umur",
       title = "Persebaran Umur Setiap Gender") +
  theme(plot.title = element_text(hjust = 0.5, size = 20))

ggplot(train) +
  geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
  theme(legend.position = "right")
Fig. 2

Fig. 2 

ggplot(train, mapping = aes(x = Pclass, fill = Age)) +
  geom_bar(stat = "count", fill = "red") +
  scale_fill_manual(values = custom_col, name = "Age Category") +
  labs(x = "Pclass", y = "Count") +
  theme(legend.position = "right")
Fig. 2

Fig. 2 

ggplot(train) +
  geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
  scale_x_log10() +
  theme(legend.position = "none")
Fig. 2

Fig. 2