install.packages(“mosaicData”) # library(mosaicData)

#Calling the CPS85 dataset from the mosaicData package data(CPS85, package=“mosaicData”) View(CPS85) ?CPS85 dim(CPS85)

#Using ggplot2 for data visualization

library(ggplot2) ggplot(data = CPS85, mapping = aes(x = exper, y = wage))

ggplot(data = CPS85, mapping = aes(x = exper, y = wage)) + geom_point()

library(dplyr) plotdata <- filter(CPS85, wage < 40) dim(plotdata) ggplot(data = plotdata, mapping = aes(x = exper, y = wage)) + geom_point()

ggplot(data = plotdata, mapping = aes(x = exper, y = wage)) + geom_point(color = “blue”, alpha = .6, size = 2, pch=18)

ggplot(data = plotdata, mapping = aes(x = exper, y = wage)) + geom_point(color = “cornflowerblue”, alpha = .7, size = 3, pch = 8) + geom_smooth(method = “lm”, lty=1, color = “red”) #lm is linear model and lty is line type

#grouping ggplot(data = plotdata, mapping = aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7, size = 3) + geom_smooth(method = “lm”, se = TRUE, size = 1.5)

#Scaling library(scales) ggplot(data = plotdata, mapping = aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7, size = 3) + geom_smooth(method = “lm”, se = FALSE, size = 1.5) + scale_x_continuous(breaks = seq(0, 60, 10)) + scale_y_continuous(breaks = seq(0, 30, 5), label = scales::dollar) + scale_color_manual(values = c(“indianred3”, “cornflowerblue”))

ggplot(data = plotdata, mapping = aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7) + geom_smooth(method = “lm”, se = FALSE) + scale_x_continuous(breaks = seq(0, 60, 10)) + scale_y_continuous(breaks = seq(0, 30, 5), label = scales::dollar) + scale_color_manual(values = c(“indianred3”, “cornflowerblue”)) + facet_wrap(~sector)

#Labels ggplot(data = plotdata, mapping = aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7) + geom_smooth(method = “lm”, se = FALSE) + scale_x_continuous(breaks = seq(0, 60, 10)) + scale_y_continuous(breaks = seq(0, 30, 5), label = scales::dollar) + scale_color_manual(values = c(“indianred3”, “cornflowerblue”)) + facet_wrap(~sector) + labs(title = “Relationship between wages and experience”, subtitle = “Current Population Survey”, caption = “source: http://mosaic-web.org/”, x = ” Years of Experience”, y = “Hourly Wage”, color = “Gender”)

#Themes ggplot(data = plotdata, mapping = aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7) + geom_smooth(method = “lm”, se = FALSE) + scale_x_continuous(breaks = seq(0, 60, 10)) + scale_y_continuous(breaks = seq(0, 30, 5), label = scales::dollar) + scale_color_manual(values = c(“indianred3”, “cornflowerblue”)) + facet_wrap(~sector) + labs(title = “Relationship between wages and experience”, subtitle = “Current Population Survey”, caption = “source: http://mosaic-web.org/”, x = ” Years of Experience”, y = “Hourly Wage”, color = “Gender”)+ theme_dark()

myplot <- ggplot(plotdata, aes(x = exper, y = wage, color = sex)) + geom_point(alpha = .7, size = 3) + geom_smooth(method = “lm”, formula = y ~ poly(x,2), se = FALSE, size = 1.5)

myplot

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.