Scribd
Upload
15 views10 pages

4 TH

Uploaded by

MATHAN KUMAR M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
15 views10 pages

4 TH

Uploaded by

MATHAN KUMAR M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Explore various variable and row filters in R

AIM:
TO Explore various variable and row filters in R for cleaning data. Apply various plot features in
R on sample data sets and visualize.

PROGRAM:
library(tidyverse)
x=read.csv('/content/income.csv')
head(df)

OUTPUT:
summary(x)

OUTPUT:
print(colSums(is.na(x)))

OUTPUT:

num.zero = colSums(x==0)
print(num.zero)

OUTPUT:

age=df$age
hist(age)
library(ggplot2)

ggplot(df, aes(x = hours.per.week)) +


geom_histogram(aes(y = ..density..), binwidth = 3, color = 'black',
fill = 'white') +
geom_density(aes(y = ..density..), alpha = 0.2, fill = 'blue')

OUTPUT:
ggplot(data=df,mapping = aes(x=Age,y=BloodPressure))+
geom_point()

OUTPUT:
library(ggplot2)
heatmap_plot<- ggplot(df, aes(x = age, y =income..50K , fill = age)) +
geom_tile() +
scale_fill_gradient(low = "blue", high = "red") +
labs(title = "Heatmap of age and income 50k ") +
theme_minimal()
print(heatmap_plot)

OUTPUT:
install.packages("gridExtra")
library(gridExtra)
library(ggplot2)
library(gridExtra)
variable_name<- "age"
plot1 <- ggplot(x, aes(x = age)) +
geom_histogram(bins = 20, fill = "red", alpha = 0.7)
plot2 <- ggplot(x, aes(x = age)) +
geom_boxplot(fill = "darkgreen", alpha = 0.7)
plot3 <- ggplot(x, aes(x = age, group = .data[[variable_name]])) +
geom_density(lwd = 0.1, aes(fill = .data[[variable_name]]), alpha = 0.5)
plot4 <- ggplot(x, aes(x = .data[[variable_name]], y =income..50K)) +
geom_boxplot(aes(fill = .data[[variable_name]]))
grid.arrange(plot1, plot2, plot3, plot4, ncol = 2)

OUTPUT:

install.packages("gridExtra")
library(gridExtra)
library(ggplot2)
library(gridExtra)
variable_name<- "age"
plot1 <- ggplot(x, aes(x = education.num)) +
geom_histogram(bins = 20, fill = "red", alpha = 0.7)
plot2 <- ggplot(x, aes(x = education.num)) +
geom_boxplot(fill = "darkgreen", alpha = 0.7)
plot3 <- ggplot(x, aes(x = education.num, group
= .data[[variable_name]])) +
geom_density(lwd = 0.1, aes(fill = .data[[variable_name]]), alpha =
0.5)
plot4 <- ggplot(x, aes(x = .data[[variable_name]], y =income..50K)) +
geom_boxplot(aes(fill = .data[[variable_name]]))
grid.arrange(plot1, plot2, plot3, plot4, ncol = 2)

OUTPUT:

install.packages("gridExtra")
library(gridExtra)
library(ggplot2)
library(gridExtra)
variable_name<- "age"
plot1 <- ggplot(x, aes(x = hours.per.week)) +
geom_histogram(bins = 20, fill = "red", alpha = 0.7)
plot2 <- ggplot(x, aes(x = hours.per.week)) +
geom_boxplot(fill = "darkgreen", alpha = 0.7)
plot3 <- ggplot(x, aes(x = hours.per.week, group = .data[[variable_name]])) +
geom_density(lwd = 0.1, aes(fill = .data[[variable_name]]), alpha = 0.5)
plot4 <- ggplot(x, aes(x = .data[[variable_name]], y =income..50K)) +
geom_boxplot(aes(fill = .data[[variable_name]]))
grid.arrange(plot1, plot2, plot3, plot4, ncol = 2)

OUTPUT:

RESULT:
The above program was completed and successfully executed.

You might also like