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
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.
years<-c(1980,1980,1985,1990)
scores<-c(34,44,56,83)
df<-data.frame(years,scores)
df[,2] # will access values for scores, [,x]: means return all values in column x
## [1] 34 44 56 83
df$years # to access the values for years
## [1] 1980 1980 1985 1990
df[df$scores <50,] # display all entries where score<50
## years scores
## 1 1980 34
## 2 1980 44
df[df$year==1980,"scores"]
## [1] 34 44
df$initial=c('d','b','s','u')
subject_name<-c("John Doe", "Jahn Doe","Steve Graves")
temperature<-c(98.1,98.6,101.4)
flu_status<-c(FALSE, FALSE,TRUE)
temperature[2]
## [1] 98.6
temperature[2:3]
## [1] 98.6 101.4
temperature[-2] #to exclude the second patient's temperature data i.e. exclude second record here
## [1] 98.1 101.4
subject_name[-2]#to exclude the second patient's name data i.e. exclude second record here
## [1] "John Doe" "Steve Graves"
gender<- factor(c("MALE","FEMALE","MALE"))
gender
## [1] MALE FEMALE MALE
## Levels: FEMALE MALE
#adding a level that might not be part of the factors yet but can be in future
blood<-factor(c("O","AB","A"),levels=c("A","B","AB","O"))
blood
## [1] O AB A
## Levels: A B AB O
#adding order into our factors
symptoms<-factor(c("SEVERE","MILD","MODERATE"), levels= c("MILD","MODERATE","SEVERE"), ordered=TRUE)
symptoms
## [1] SEVERE MILD MODERATE
## Levels: MILD < MODERATE < SEVERE
symptoms>"MODERATE"
## [1] TRUE FALSE FALSE
#stringAsFactors=FALSE; do it for the data sets downloaded from internet even
pt_data<- data.frame(subject_name,temperature,flu_status,gender,blood,symptoms,stringsAsFactors = FALSE)
pt_data
## subject_name temperature flu_status gender blood symptoms
## 1 John Doe 98.1 FALSE MALE O SEVERE
## 2 Jahn Doe 98.6 FALSE FEMALE AB MILD
## 3 Steve Graves 101.4 TRUE MALE A MODERATE
pt_data$subject_name
## [1] "John Doe" "Jahn Doe" "Steve Graves"
pt_data[1,2] #show value of 1st row and 2nd column
## [1] 98.1
pt_data[,1] # all rows of the 1st column
## [1] "John Doe" "Jahn Doe" "Steve Graves"
pt_data[2,] # all the details of 2nd patient
## subject_name temperature flu_status gender blood symptoms
## 2 Jahn Doe 98.6 FALSE FEMALE AB MILD
pt_data[c(1,3),c(2,4)]
## temperature gender
## 1 98.1 MALE
## 3 101.4 MALE
pt_data[,] # extract all data
## subject_name temperature flu_status gender blood symptoms
## 1 John Doe 98.1 FALSE MALE O SEVERE
## 2 Jahn Doe 98.6 FALSE FEMALE AB MILD
## 3 Steve Graves 101.4 TRUE MALE A MODERATE
pt_data [c(1,3), c("temperature","gender")]
## temperature gender
## 1 98.1 MALE
## 3 101.4 MALE
pt_data$temp_c<-((pt_data$temperature-32)*(5/9))
pt_data
## subject_name temperature flu_status gender blood symptoms temp_c
## 1 John Doe 98.1 FALSE MALE O SEVERE 36.72222
## 2 Jahn Doe 98.6 FALSE FEMALE AB MILD 37.00000
## 3 Steve Graves 101.4 TRUE MALE A MODERATE 38.55556
pt_data[c("temperature","temp_c")]
## temperature temp_c
## 1 98.1 36.72222
## 2 98.6 37.00000
## 3 101.4 38.55556
library(ggplot2)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)
#statement to display the displacement and highway mileage
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy))
#statement to display the displacement and city mileage
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=cty))
#statement to display the displacement and number of cylinders
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=cyl))
#statement to display the displacement and highway mileage, same graph with color
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy, color=class))
#statement to display the displacement and highway mileage, same graph with size
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy, size=class))
## Warning: Using size for a discrete variable is not advised.
#statement to display the displacement and highway mileage, same graph with shape
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy, shape=class))
## Warning: The shape palette can deal with a maximum of 6 discrete values because more
## than 6 becomes difficult to discriminate
## ℹ you have requested 7 values. Consider specifying shapes manually if you need
## that many have them.
## Warning: Removed 62 rows containing missing values (`geom_point()`).
#statement to display the displacement and highway mileage, same graph with blue color
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy), color="blue")
#statement to display the displacement and highway mileage with facet wrap
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy)) + facet_wrap(~ class,nrow=2)
#statement to display the displacement and highway mileage with facet wrap
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy)) + facet_grid(drv~ cyl)