Diamonds Dataset
library(readr)
seeds_dataset_2_ <- read_csv("C:/Users/lazarus/Downloads/seeds_dataset (2).txt")
## Rows: 209 Columns: 1
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): 15.26 14.84 0.871 5.763 3.312 2.221 5.22 1
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
View(seeds_dataset_2_)
library(ggplot2)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ stringr 1.5.1
## ✔ forcats 1.0.0 ✔ 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(dplyr)
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, size=class))
## Warning: Using size for a discrete variable is not advised.
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, alpha=class))
## Warning: Using alpha for a discrete variable is not advised.
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy), color="blue")
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")) #changes the name of the class to "blue" rather than the color of the points to blue
ggplot(data=mpg)+geom_point(mapping=aes(x=displ,y=hwy)) + facet_wrap(~class, nrow=2)#creates 2 rows of plots
#draws a unique linetype for each unique value of the variable that you map to the linetype
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() #makes mapping global so you dont have to retype it
## `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
?diamonds
## starting httpd help server ... done
view(diamonds) #shows table/dataset
str(diamonds) #str shows size & columns...first step to loading a dataset is to look at/analyze it
## 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$carat) #gives statistics/interquartile values on the specific attribute...second step
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2000 0.4000 0.7000 0.7979 1.0400 5.0100
mean(diamonds$price)
## [1] 3932.8
summary(diamonds$price)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 326 950 2401 3933 5324 18823
Val <- c(46,34,87,22,91)
mean(Val)
## [1] 56
ggplot(data=diamonds)+geom_point(mapping=aes(x=carat,y=price, color=cut))
ggplot(data=diamonds)+geom_smooth(mapping=aes(x=carat,y=price, color=cut))
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
hist(diamonds$carat, main="Histogram of diamonds carat weight", xlab="Carat")
sd(diamonds$carat)
## [1] 0.4740112
var(diamonds$carat)
## [1] 0.2246867
sd(diamonds$price)
## [1] 3989.44
var(diamonds$price)
## [1] 15915629
table(diamonds$cut)
##
## Fair Good Very Good Premium Ideal
## 1610 4906 12082 13791 21551
ggplot(data=diamonds)+geom_bar(mapping=aes(x=cut))
ggplot(data=diamonds)+stat_summary(mapping=aes(x=cut,y=depth), fun.max=max, fun=median)
## Warning: Removed 5 rows containing missing values (`geom_segment()`).
ggplot(data=diamonds)+geom_bar(mapping=aes(x=cut, fill=clarity))
ggplot(data=diamonds)+geom_bar(mapping=aes(x=cut, fill=clarity), position="dodge")
#coord_quickmap, sets aspect ratio
nz <- map_data("nz")
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()
library(maps)
##
## Attaching package: 'maps'
##
## The following object is masked from 'package:purrr':
##
## map
library(naijR)
## Warning: package 'naijR' was built under R version 4.3.3
map_ng()
