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:

library(ggplot2)
ggplot(data=mpg, mapping=aes(x=displ,y=hwy)) + geom_point(mapping=aes(color=class)) + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

ggplot(data=mpg, mapping=aes(x=displ,y=hwy)) + geom_point(mapping=aes(color=class)) + geom_smooth(data=dplyr::filter(mpg, class=="subcompact"), se=FALSE) 
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

ggplot(data=mpg, mapping=aes(x=displ,y=hwy)) + geom_point(mapping=aes(color=class)) + geom_smooth(data=dplyr::filter(mpg, class=="minivan"), se=FALSE) 
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,
## : pseudoinverse used at 4.008
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,
## : neighborhood radius 0.708
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,
## : reciprocal condition number 0
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,
## : There are other near singularities as well. 0.25

?diamonds
## starting httpd help server ... done
head(diamonds)
## # A tibble: 6 × 10
##   carat cut       color clarity depth table price     x     y     z
##   <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1  0.23 Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
## 2  0.21 Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
## 3  0.23 Good      E     VS1      56.9    65   327  4.05  4.07  2.31
## 4  0.29 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
## 5  0.31 Good      J     SI2      63.3    58   335  4.34  4.35  2.75
## 6  0.24 Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48
# str(diamonds)  shows all the structure of the individual attributes

str(diamonds)
## tibble [53,940 × 10] (S3: tbl_df/tbl/data.frame)
##  $ carat  : num [1:53940] 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
##  $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
##  $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
##  $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
##  $ depth  : num [1:53940] 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
##  $ table  : num [1:53940] 55 61 65 58 58 57 57 55 61 61 ...
##  $ price  : int [1:53940] 326 326 327 334 335 336 336 337 337 338 ...
##  $ x      : num [1:53940] 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
##  $ y      : num [1:53940] 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
##  $ z      : num [1:53940] 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...
summary(diamonds)
##      carat               cut        color        clarity          depth      
##  Min.   :0.2000   Fair     : 1610   D: 6775   SI1    :13065   Min.   :43.00  
##  1st Qu.:0.4000   Good     : 4906   E: 9797   VS2    :12258   1st Qu.:61.00  
##  Median :0.7000   Very Good:12082   F: 9542   SI2    : 9194   Median :61.80  
##  Mean   :0.7979   Premium  :13791   G:11292   VS1    : 8171   Mean   :61.75  
##  3rd Qu.:1.0400   Ideal    :21551   H: 8304   VVS2   : 5066   3rd Qu.:62.50  
##  Max.   :5.0100                     I: 5422   VVS1   : 3655   Max.   :79.00  
##                                     J: 2808   (Other): 2531                  
##      table           price             x                y         
##  Min.   :43.00   Min.   :  326   Min.   : 0.000   Min.   : 0.000  
##  1st Qu.:56.00   1st Qu.:  950   1st Qu.: 4.710   1st Qu.: 4.720  
##  Median :57.00   Median : 2401   Median : 5.700   Median : 5.710  
##  Mean   :57.46   Mean   : 3933   Mean   : 5.731   Mean   : 5.735  
##  3rd Qu.:59.00   3rd Qu.: 5324   3rd Qu.: 6.540   3rd Qu.: 6.540  
##  Max.   :95.00   Max.   :18823   Max.   :10.740   Max.   :58.900  
##                                                                   
##        z         
##  Min.   : 0.000  
##  1st Qu.: 2.910  
##  Median : 3.530  
##  Mean   : 3.539  
##  3rd Qu.: 4.040  
##  Max.   :31.800  
## 
summary(diamonds$cut)
##      Fair      Good Very Good   Premium     Ideal 
##      1610      4906     12082     13791     21551
summary(diamonds$carat)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.2000  0.4000  0.7000  0.7979  1.0400  5.0100
#to view it in a table form
View(diamonds)

val <- c(46,34,87,22,91)
mean(val)
## [1] 56
mean(diamonds$price)
## [1] 3932.8
max(diamonds$price)
## [1] 18823
median(diamonds$price)
## [1] 2401
min(diamonds$price)
## [1] 326
summary(diamonds$price)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     326     950    2401    3933    5324   18823
#x=carrat vs y=price
ggplot(data=diamonds)+geom_point(mapping=aes(x=carat,y=price))

ggplot(data=diamonds, mapping=aes(x=carat,y=price)) + geom_point(mapping = aes(color=cut)) 

# Histogram

?hist

hist(diamonds$carat, main="Histogram of Diamond Carat Weight", xlab = "Carat")

hist(diamonds$price, main="Histogram of Diamond Price", xlab = "Price")

sd(diamonds$carat)
## [1] 0.4740112
sd(diamonds$price)
## [1] 3989.44
var(diamonds$carat)
## [1] 0.2246867
var(diamonds$price)
## [1] 15915629
ggplot(data=diamonds) + stat_count(mapping = aes(x=cut))

#Introduce proportion to make all sum to 1

ggplot(data=diamonds) + stat_count(mapping = aes(x=cut, y=..prop.., group=0.1))
## Warning: The dot-dot notation (`..prop..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(prop)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

ggplot(data=diamonds) + stat_summary(mapping = aes(x=cut, y=depth),
                                     fun.min=min,
                                     fun.max=max,
                                     fun=median
                                     )

# Colour border alone

ggplot(data=diamonds) + stat_count(mapping = aes(x=cut, color=cut))

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, color=cut))

# Color all fill

ggplot(data=diamonds) + stat_count(mapping = aes(x=cut, fill=cut))

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, fill=cut))

ggplot(data=diamonds) + stat_count(mapping = aes(x=cut, fill=clarity))

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, fill=clarity))

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, fill=color))

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, fill=clarity), position = "dodge")

ggplot(data=diamonds) + geom_bar(mapping = aes(x=cut, fill=color), position = "dodge")

nz <- map_data("nz")
ggplot(nz, aes(long, lat, group=group)) + geom_polygon(fill="white", color="black")

usa <- map_data("usa")
ggplot(usa, aes(long, lat, group=group)) + geom_polygon(fill="white", color="black")

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