Presentation of Data Analysis

Descriptive Analysis

Santanu Dutta
ACME

Data

We will select the happy dataset available in package 'GGally'. Lets look at the data.

suppressPackageStartupMessages(library("googleVis"))
library(ggplot2)
head(diamonds)

##   carat       cut color clarity depth table price    x    y    z
## 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

Summary Of Data

Lets view the summary of data

library(ggplot2)
summary(diamonds)

##      carat               cut        color        clarity     
##  Min.   :0.2000   Fair     : 1610   D: 6775   SI1    :13065  
##  1st Qu.:0.4000   Good     : 4906   E: 9797   VS2    :12258  
##  Median :0.7000   Very Good:12082   F: 9542   SI2    : 9194  
##  Mean   :0.7979   Premium  :13791   G:11292   VS1    : 8171  
##  3rd Qu.:1.0400   Ideal    :21551   H: 8304   VVS2   : 5066  
##  Max.   :5.0100                     I: 5422   VVS1   : 3655  
##                                     J: 2808   (Other): 2531  
##      depth           table           price             x         
##  Min.   :43.00   Min.   :43.00   Min.   :  326   Min.   : 0.000  
##  1st Qu.:61.00   1st Qu.:56.00   1st Qu.:  950   1st Qu.: 4.710  
##  Median :61.80   Median :57.00   Median : 2401   Median : 5.700  
##  Mean   :61.75   Mean   :57.46   Mean   : 3933   Mean   : 5.731  
##  3rd Qu.:62.50   3rd Qu.:59.00   3rd Qu.: 5324   3rd Qu.: 6.540  
##  Max.   :79.00   Max.   :95.00   Max.   :18823   Max.   :10.740  
##                                                                  
##        y                z         
##  Min.   : 0.000   Min.   : 0.000  
##  1st Qu.: 4.720   1st Qu.: 2.910  
##  Median : 5.710   Median : 3.530  
##  Mean   : 5.735   Mean   : 3.539  
##  3rd Qu.: 6.540   3rd Qu.: 4.040  
##  Max.   :58.900   Max.   :31.800  
##

Charts

Lets display some charts.

library(rCharts)
library(ggplot2)

n1 <- nPlot(carat ~ cut , group = "color", data = diamonds[1:40,], type = "multiBarChart")
n1$show("iframesrc", cdn = TRUE)

Plotting Chart from economics dataset

library(rCharts)
data(economics, package = 'ggplot2')
econ <- transform(economics, date = as.character(date))
m1 <- mPlot(x = 'date', y = c('psavert', 'uempmed'), type = 'Line',
  data = econ)
m1$set(pointSize = 0, lineWidth = 1)
m1$print('chart2', include_assets = TRUE)

Loading required package: reshape2

Plot

Lets plot some descriptive analysis of data.

library(googleVis)
library(GGally)
g <-gvisMotionChart(diamonds, "carat", "price", options = list(width = 800, height = 600))

## Warning in if (class(x[[.x]]) == "Date") as.character(x[[.x]]) else
## x[[.x]]: the condition has length > 1 and only the first element will be
## used

## Warning in if (class(x[[.x]]) == "Date") as.character(x[[.x]]) else
## x[[.x]]: the condition has length > 1 and only the first element will be
## used

## Warning in if (class(x[[.x]]) == "Date") as.character(x[[.x]]) else
## x[[.x]]: the condition has length > 1 and only the first element will be
## used

## Error in gvisCheckMotionChartData(data, my.options): The data must have rows with unique combinations of idvar and timevar.
## Your data has 53940 rows, but idvar and timevar only define 28988 unique rows.

plot(g, options=list(width=600, height=400), tag="chart")

## Error in plot(g, options = list(width = 600, height = 400), tag = "chart"): object 'g' not found