Untitled

data_example <- data.frame(
  region = c("North", "South", "East", "West", "North", "South", "East", "West"),
  product = c("A", "A", "A", "A", "B", "B", NA, "B"),
  sales = c(100, 150, NA, 250, 120, 170, 220, 270),
  year = c(2020, 2020, 2020, NA, 2021, 2021, 2021, 2021),
  gender = c("male", "female", "male", "female", "male", "female", "male", "female"),
  satisfaction = c("very satisfied", "satisfied", "neutral", "unsatisfied", "very unsatisfied", "satisfied", "neutral", "very satisfied")
)

head(data_example)

##   region product sales year gender     satisfaction
## 1  North       A   100 2020   male   very satisfied
## 2  South       A   150 2020 female        satisfied
## 3   East       A    NA 2020   male          neutral
## 4   West       A   250   NA female      unsatisfied
## 5  North       B   120 2021   male very unsatisfied
## 6  South       B   170 2021 female        satisfied

colSums(is.na(data_example))

##       region      product        sales         year       gender satisfaction 
##            0            1            1            1            0            0

mean_scores <- mean(data_example$sales, na.rm = TRUE)
data_example$sales[is.na(data_example$sales)] <- mean_scores

Menghampus colom

clean_df<-na.omit(data_example)
head(clean_df)

##   region product    sales year gender     satisfaction
## 1  North       A 100.0000 2020   male   very satisfied
## 2  South       A 150.0000 2020 female        satisfied
## 3   East       A 182.8571 2020   male          neutral
## 5  North       B 120.0000 2021   male very unsatisfied
## 6  South       B 170.0000 2021 female        satisfied
## 8   West       B 270.0000 2021 female   very satisfied

head(data_example)

##   region product    sales year gender     satisfaction
## 1  North       A 100.0000 2020   male   very satisfied
## 2  South       A 150.0000 2020 female        satisfied
## 3   East       A 182.8571 2020   male          neutral
## 4   West       A 250.0000   NA female      unsatisfied
## 5  North       B 120.0000 2021   male very unsatisfied
## 6  South       B 170.0000 2021 female        satisfied

data_example$gende_num <- as.numeric(factor(data_example$gender, levels= c("male","female")))
data_example$satisfaction_num <-as.numeric(factor(data_example$satisfaction,levels=c("unsatisfied","neutral","satisfied","very satisfied")))

head(data_example)

##   region product    sales year gender     satisfaction gende_num
## 1  North       A 100.0000 2020   male   very satisfied         1
## 2  South       A 150.0000 2020 female        satisfied         2
## 3   East       A 182.8571 2020   male          neutral         1
## 4   West       A 250.0000   NA female      unsatisfied         2
## 5  North       B 120.0000 2021   male very unsatisfied         1
## 6  South       B 170.0000 2021 female        satisfied         2
##   satisfaction_num
## 1                4
## 2                3
## 3                2
## 4                1
## 5               NA
## 6                3

library(ggplot2)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

g<-ggplot(data_example,aes(x = region,y = sales,fill=region))+geom_col(size = 3,alpha =0.5)

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

g<-ggplotly(g)
g

g <- ggplot(data_example, aes(x = region)) +
  geom_density(size= 1,alpha = 0.5,fill="red" ) + theme_minimal()+ facet_wrap(~region)

# Menampilkan plot
print(g)

x<-ggplot(data_example,aes(y = sales))+ geom_boxplot(alpha = 0.5)
x <- ggplotly(x)
x

g <- ggplot(data_example, aes(x = region, y = sales, fill = region)) +
  geom_boxplot(alpha = 0.5) 

g