R Markdown
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)
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))
## `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, color = drv), show.legend = FALSE )
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy)) + geom_smooth(mapping = aes(x = displ, y = hwy))
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) + geom_point() + 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()
## `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=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=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
#Most used functions
#str()
str(diamonds) # Diamonds is a Dataset
## 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$carat)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2000 0.4000 0.7000 0.7979 1.0400 5.0100
#create a vector Val with the values (46,34,87,22,91 and find its average
Val <- c(46, 34, 87, 22, 91)
average <- mean(Val)
average
## [1] 56
#Mean price of Diamonds in the dataset
Cost <-mean(diamonds$price)
Cost
## [1] 3932.8
#Price summary of the diamonds
Cost1<-summary(diamonds$price)
Cost1
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 326 950 2401 3933 5324 18823
ggplot(data=diamonds) + geom_smooth(mapping=aes(x=carat,y=price))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data=diamonds) + geom_smooth(mapping=aes(x=carat,y=price, linetype=cut))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data=diamonds) + geom_point(mapping=aes(x=carat,y=price, linetype=cut))
## Warning in geom_point(mapping = aes(x = carat, y = price, linetype = cut)):
## Ignoring unknown aesthetics: linetype
ggplot(data=diamonds) + geom_point(mapping=aes(x=carat,y=price, linetype=cut))+geom_smooth(mapping=aes(x=carat,y=price))
## Warning in geom_point(mapping = aes(x = carat, y = price, linetype = cut)):
## Ignoring unknown aesthetics: linetype
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data=diamonds) + geom_point(mapping=aes(x=carat,y=price, color=cut)) +geom_smooth(mapping=aes(x=carat,y=price))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data=diamonds) + geom_point(mapping=aes(x=carat,y=price, color=cut))
ggplot(data=diamonds) + geom_smooth(mapping=aes(x=carat,y=price, color=cut))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data=diamonds) + geom_smooth(mapping=aes(x=carat,y=price, group=cut))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
ggplot(data = diamonds, mapping = aes(x = carat, y = price)) +geom_point(mapping = aes(color = cut)) + geom_smooth()
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
quantile(diamonds$carat)
## 0% 25% 50% 75% 100%
## 0.20 0.40 0.70 1.04 5.01
#Histogram of Diamonds Carat Weight
hist(diamonds$carat, main="Histogram of Diamonds carat weight",xlab="Carat")
hist(diamonds$price, main="Histogram of Diamonds Price",xlab="Price")
#var() returns variance
var(diamonds$carat)
## [1] 0.2246867
#sd() returns Standard Deviation
sd(diamonds$price)
## [1] 3989.44
var(diamonds$carat)
## [1] 0.2246867
sd(diamonds$price)
## [1] 3989.44
#
table(diamonds$cut)
##
## Fair Good Very Good Premium Ideal
## 1610 4906 12082 13791 21551
#BAR CHART
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut))
#Coloring the bar chart using fill
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut, fill=cut))
#Coloring the bar chart using color
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut,color=cut))
#stacking Variables
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut,fill=clarity))
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut,fill=clarity), position = "fill")
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut,fill=clarity), position = "dodge")
nz<- map_data("nz")
#MAP of NEW ZEALAND
ggplot(nz, aes(long,lat,group=group))+ geom_polygon(fill="white", colour="black")
ggplot(nz, aes(long,lat,group=group))+ geom_polygon(fill="white", colour="black")+coord_quickmap()
usa<- map_data("usa")
ggplot(usa, aes(long,lat,group=group))+ geom_polygon(fill="white", colour="black")
#can use stat_count instead of geom_bar
ggplot(data=diamonds) + stat_count(mapping=aes(x=cut))
#To display Proportions
ggplot(data=diamonds) + geom_bar(mapping=aes(x=cut, y=..prop.., group=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.
#Stat_Summary
ggplot(data=diamonds) + stat_summary(mapping=aes(x=cut, y=depth),fun.min = min, fun.max = max, fun= median)
