EDA

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.2     v purrr   0.3.4
## v tibble  3.0.4     v dplyr   1.0.2
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.0

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

view(diamonds)

#Discrete Variables
ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut))

Continuous Variables

ggplot(data = diamonds)+
  geom_histogram(mapping = aes(x = carat ), binwidth = 0.5)

Changing bin sizes

(Smaller<-diamonds %>%
  filter( carat <3))

## # A tibble: 53,900 x 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 0.290 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
##  7 0.24  Very Good I     VVS1     62.3    57   336  3.95  3.98  2.47
##  8 0.26  Very Good H     SI1      61.9    55   337  4.07  4.11  2.53
##  9 0.22  Fair      E     VS2      65.1    61   337  3.87  3.78  2.49
## 10 0.23  Very Good H     VS1      59.4    61   338  4     4.05  2.39
## # ... with 53,890 more rows

ggplot( data = Smaller, mapping =aes (x= carat))+
  geom_histogram(binwidth = 0.1)

Overlaying different histograms

ggplot(data = Smaller, mapping = aes(x= carat, colour = cut))+
  geom_freqpoly(binwidth = 0.1)

Questions after seeing a graph

ggplot(data = Smaller, mapping = aes(x = carat))+
  geom_histogram(binwidth = 0.01)

Covariation

Continuous Variables

ggplot(data= diamonds , mapping= aes(x= price))+
  geom_freqpoly(mapping = aes(colour= cut ), binwidth=500)

Adding density of count

ggplot(data= diamonds , mapping= aes(x= price , y= ..density..))+
  geom_freqpoly(mapping = aes(colour= cut ), binwidth=500)

box plots

categorical values

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

diamonds%>% 
  count(color, cut)%>%
  ggplot(mapping = aes(x= color , y =cut))+
  geom_tile(mapping = aes(fill=n))

2 Continuous Variables

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

Tile

ggplot( data = Smaller)+
  geom_bin2d(mapping= aes(x= carat , y= price))

ggplot( data = Smaller ,mapping= aes(x= carat , y= price))+
  geom_boxplot(mapping = aes(group= cut_width(carat, 0.1)))