#Q1
#loading libraries
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
#load the data
data(tract_covariates)
## Warning in data(tract_covariates): data set 'tract_covariates' not found
tract_covariates<- read.csv("C:/Users/عمر/Desktop/Fall 2024/Rstudio/Week 5/tract_covariates.csv")
#Q2
dataframe <- tract_covariates[, c("czname", "hhinc_mean2000", "popdensity2000")]
#Q3
San_Antonio_DF <- dataframe[dataframe$czname == "San Antonio", ]
#Q4
ggplot(San_Antonio_DF, aes(x = hhinc_mean2000, fill = czname)) +
geom_histogram(binwidth = 5000, position = "identity", alpha = 0.9)
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_bin()`).
#Q5
ggplot(San_Antonio_DF, aes(x = czname, y = popdensity2000, fill = czname)) +
geom_boxplot()
#Q6
ggplot(San_Antonio_DF, aes(x = hhinc_mean2000, color = czname, linetype = czname)) +
geom_density()
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).
#Q7
ggplot(San_Antonio_DF, aes(x = hhinc_mean2000, color = czname)) +
stat_ecdf(geom = "step")
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_ecdf()`).
#Q8
ggplot(San_Antonio_DF, aes(x = popdensity2000, y = hhinc_mean2000)) +
geom_point()
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
#Q9
ggplot(San_Antonio_DF, aes(x = popdensity2000, y = hhinc_mean2000)) +
geom_point() +
labs(x = "Population Density",y = "Household Income")
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
#Q10
p <- ggplot(San_Antonio_DF, aes(x = popdensity2000, y = hhinc_mean2000)) +
geom_point() +
labs(x = "Population Density",y = "Household Income")
ggplotly(p)