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:

? `datasets-package`
## starting httpd help server ... done
library(help = "datasets")

data("iris")
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
years <- c(1980, 1980, 1985, 1990)
scores<- c( 34, 44, 56, 83)

df <- data.frame(years, scores)

df
##   years scores
## 1  1980     34
## 2  1980     44
## 3  1985     56
## 4  1990     83
df[,1]
## [1] 1980 1980 1985 1990
df[,2]
## [1] 34 44 56 83
df$years
## [1] 1980 1980 1985 1990
df$scores
## [1] 34 44 56 83
df[df$scores<50,]
##   years scores
## 1  1980     34
## 2  1980     44
df[df$year==1980, "scores"]
## [1] 34 44
library(help = "datasets")

data("iris")
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
years <- c(1980, 1980, 1985, 1990)
scores<- c( 34, 44, 56, 83)

df <- data.frame(years, scores)

df
##   years scores
## 1  1980     34
## 2  1980     44
## 3  1985     56
## 4  1990     83
df[,1]
## [1] 1980 1980 1985 1990
df[,2]
## [1] 34 44 56 83
df$years
## [1] 1980 1980 1985 1990
df$scores
## [1] 34 44 56 83
df[df$scores<50,]
##   years scores
## 1  1980     34
## 2  1980     44
df[df$year==1980, "scores"]
## [1] 34 44
#Add new column named "Initial"

df$initial = c('d', 'b', 's', 'u')

df
##   years scores initial
## 1  1980     34       d
## 2  1980     44       b
## 3  1985     56       s
## 4  1990     83       u
df[df$year==1980, "scores"]
## [1] 34 44
# Toy Medical Dataset

subject_name <- c("John Doe", " Jane Doe", "Steve Graves")
temperarture <- c(98.1, 98.6, 101.4)
flu_status <- c(FALSE, FALSE, TRUE)


temperarture[2]
## [1] 98.6
temperarture[2:3]
## [1]  98.6 101.4
#To exclude use the minus sign

temperarture[-2]
## [1]  98.1 101.4
#Usig Factor for Categorical Variables

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
## [1] SEVERE   MILD     MODERATE
## Levels: MILD < MODERATE < SEVERE
symptoms > "MODERATE"
## [1]  TRUE FALSE FALSE
pt_data <- data.frame(subject_name, temperarture, flu_status, gender, blood, symptoms, stringsAsFactors = FALSE)
pt_data
##   subject_name temperarture flu_status gender blood symptoms
## 1     John Doe         98.1      FALSE   MALE     O   SEVERE
## 2     Jane Doe         98.6      FALSE FEMALE    AB     MILD
## 3 Steve Graves        101.4       TRUE   MALE     A MODERATE
pt_data$temperarture
## [1]  98.1  98.6 101.4
pt_data[1,2]
## [1] 98.1
pt_data[c(1,3),c(2,4)]
##   temperarture gender
## 1         98.1   MALE
## 3        101.4   MALE
#TO EXTRACT EVERYTHIN
pt_data[,]
##   subject_name temperarture flu_status gender blood symptoms
## 1     John Doe         98.1      FALSE   MALE     O   SEVERE
## 2     Jane Doe         98.6      FALSE FEMALE    AB     MILD
## 3 Steve Graves        101.4       TRUE   MALE     A MODERATE
pt_data[c(1,3), c("temperarture", "gender")]
##   temperarture gender
## 1         98.1   MALE
## 3        101.4   MALE
pt_data$temp_c <- (pt_data$temperarture-32)*(5/9)

pt_data
##   subject_name temperarture flu_status gender blood symptoms   temp_c
## 1     John Doe         98.1      FALSE   MALE     O   SEVERE 36.72222
## 2     Jane Doe         98.6      FALSE FEMALE    AB     MILD 37.00000
## 3 Steve Graves        101.4       TRUE   MALE     A MODERATE 38.55556
#Graphics
x <- rnorm(100)
y <- rnorm(100)

plot(x,y, xlab="X Label", ylab = "Y Label", main = "Main Title")

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
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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(ggplot2)
library(dplyr)

?mpg

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
data(mpg)
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_smooth(mapping=aes(x=displ,y=cyl))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

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

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

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()`).

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

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

#Using Facet and subplot

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy))+facet_wrap(~class,nrow=2)

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

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

ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy))+facet_grid(drv~cyl)

#Geo_Smooth
ggplot(data=mpg)+geom_smooth(mapping=aes(x=displ,y=cyl))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

ggplot(data=mpg)+geom_smooth(mapping=aes(x=displ,y=hwy, linetype=drv))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

ggplot(data=mpg)+geom_smooth(mapping=aes(x=displ,y=hwy, group=drv))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

ggplot(data=mpg)+geom_smooth(mapping=aes(x=displ,y=hwy)) + geom_smooth(mapping=aes(x=displ, y=hwy))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

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