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.

#create a new data frame
years<- c(1980,1980,1985,1990)
scores<- c(34,44,56,83)
df<-data.frame(years,scores)
#this creates a data frame df with 2 columns years and scores
df[,1] #will access the values for scores
## [1] 1980 1980 1985 1990
#[,x]:means return all values in column x
df[df$year==1980] # to access the values for years
##   years scores
## 1  1980     34
## 2  1980     44
## 3  1985     56
## 4  1990     83
#creating toy dataset

subject_name<-c("John Doe", "Jane Doe", "Steve Graves")
temperature<-c(98.1, 98.6, 101.4)
flu_status<-c(FALSE, FALSE, TRUE)
temperature[2:1]
## [1] 98.6 98.1
temperature[-2]
## [1]  98.1 101.4
gender<-factor(c("MALE","FEMALE","MALE"))
gender
## [1] MALE   FEMALE MALE  
## Levels: FEMALE MALE
blood<-factor(c("O","AB","A"),
               levels=c("A","B","AB","O"))
blood
## [1] O  AB A 
## Levels: A B AB O
symptoms<- factor(c("SEVERE","MILD","MODERATE"),
                 levels = c("MILD","MODERATE","SEVERE"), ordered = TRUE)
symptoms>"MODERATE"
## [1]  TRUE FALSE FALSE
pt_data<-data.frame(subject_name,temperature,flu_status,gender,blood,symptoms,
                    stringAsFactors =FALSE)

pt_data[1,2]
## [1] 98.1
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$temp_C
## [1] 36.72222 37.00000 38.55556
pt_data
##   subject_name temperature flu_status gender blood symptoms stringAsFactors
## 1     John Doe        98.1      FALSE   MALE     O   SEVERE           FALSE
## 2     Jane Doe        98.6      FALSE FEMALE    AB     MILD           FALSE
## 3 Steve Graves       101.4       TRUE   MALE     A MODERATE           FALSE
##     temp_C
## 1 36.72222
## 2 37.00000
## 3 38.55556
?mpg
## No documentation for 'mpg' in specified packages and libraries:
## you could try '??mpg'
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.2
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.3.2
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.2
## Warning: package 'tibble' was built under R version 4.3.2
## Warning: package 'tidyr' was built under R version 4.3.2
## Warning: package 'readr' was built under R version 4.3.2
## Warning: package 'purrr' was built under R version 4.3.2
## Warning: package 'stringr' was built under R version 4.3.2
## Warning: package 'forcats' was built under R version 4.3.2
## Warning: package 'lubridate' was built under R version 4.3.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ✔ readr     2.1.5
## ── 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
mpg
## # A tibble: 234 × 11
##    manufacturer model      displ  year   cyl trans drv     cty   hwy fl    class
##    <chr>        <chr>      <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
##  1 audi         a4           1.8  1999     4 auto… f        18    29 p     comp…
##  2 audi         a4           1.8  1999     4 manu… f        21    29 p     comp…
##  3 audi         a4           2    2008     4 manu… f        20    31 p     comp…
##  4 audi         a4           2    2008     4 auto… f        21    30 p     comp…
##  5 audi         a4           2.8  1999     6 auto… f        16    26 p     comp…
##  6 audi         a4           2.8  1999     6 manu… f        18    26 p     comp…
##  7 audi         a4           3.1  2008     6 auto… f        18    27 p     comp…
##  8 audi         a4 quattro   1.8  1999     4 manu… 4        18    26 p     comp…
##  9 audi         a4 quattro   1.8  1999     4 auto… 4        16    25 p     comp…
## 10 audi         a4 quattro   2    2008     4 manu… 4        20    28 p     comp…
## # ℹ 224 more rows
head(mpg)
## # A tibble: 6 × 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…
ggplot(data=mpg)+
  geom_point(mapping=aes(x=displ,y=hwy))

ggplot(data=mpg)+
  geom_point(mapping=aes(x=displ,y=cty))

ggplot(data=mpg)+
  geom_point(mapping=aes(x=displ,y=cyl))

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy,color=class))

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy,alpha=class))
## Warning: Using alpha for a discrete variable is not advised.

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy),color="royalblue")

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy))+
  facet_wrap(~ class,nrow=3)