Data Visualization

library(ggplot2)
diamonds

## # A tibble: 53,940 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  0.29   Premium     I     VS2  62.4    58   334  4.20  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  4.00  4.05  2.39
## # ... with 53,930 more rows

單變數：類別型

ggplot(data = diamonds, aes(x = cut)) +
geom_bar(fill = "lightblue", colour = "black")

單變數：連續型

ggplot(data = diamonds, aes(x = price)) +
geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

雙變數：連續 vs 連續

ggplot(data = diamonds, aes(x = table, y=depth)) +
geom_point()

雙變數：離散 vs 連續

ggplot(diamonds, aes(x=clarity, y=depth)) +
geom_boxplot()

多變量：鑽石銷售總體的關係

library(ggplot2)
library(GGally)
library(scales)
library(memisc)

## Loading required package: lattice

## Loading required package: MASS

## 
## Attaching package: 'memisc'

## The following object is masked from 'package:scales':
## 
##     percent

## The following objects are masked from 'package:stats':
## 
##     contr.sum, contr.treatment, contrasts

## The following object is masked from 'package:base':
## 
##     as.array

# 從數據集獲取10000個樣本數據進行分析
set.seed(20022012)
diamond_samp <- diamonds[sample(1:length(diamonds$price), 10000), ]
ggpairs(diamond_samp,lower= list(continuous = wrap("points", shape = I('.'))),
        upper = list(combo = wrap("box", outlier.shape = I('.'))))

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.