Data Explorer is an R Package with commands to explore datasets efficiently.
By Boxuan Cui, Data Scientist at Smarter Traveler
This script uses 6 commands to explore the dataset
dataset: BostonHousing
variables: begining dataset has 14, ending dataset has 18 which includes 4 transformed variables
package mlbench, dataset BostonHousing from mlbench
library (mlbench)
## Warning: package 'mlbench' was built under R version 3.4.3
data ("BostonHousing", package = "mlbench")
summary (BostonHousing)
## crim zn indus chas
## Min. : 0.00632 Min. : 0.00 Min. : 0.46 0:471
## 1st Qu.: 0.08204 1st Qu.: 0.00 1st Qu.: 5.19 1: 35
## Median : 0.25651 Median : 0.00 Median : 9.69
## Mean : 3.61352 Mean : 11.36 Mean :11.14
## 3rd Qu.: 3.67708 3rd Qu.: 12.50 3rd Qu.:18.10
## Max. :88.97620 Max. :100.00 Max. :27.74
## nox rm age dis
## Min. :0.3850 Min. :3.561 Min. : 2.90 Min. : 1.130
## 1st Qu.:0.4490 1st Qu.:5.886 1st Qu.: 45.02 1st Qu.: 2.100
## Median :0.5380 Median :6.208 Median : 77.50 Median : 3.207
## Mean :0.5547 Mean :6.285 Mean : 68.57 Mean : 3.795
## 3rd Qu.:0.6240 3rd Qu.:6.623 3rd Qu.: 94.08 3rd Qu.: 5.188
## Max. :0.8710 Max. :8.780 Max. :100.00 Max. :12.127
## rad tax ptratio b
## Min. : 1.000 Min. :187.0 Min. :12.60 Min. : 0.32
## 1st Qu.: 4.000 1st Qu.:279.0 1st Qu.:17.40 1st Qu.:375.38
## Median : 5.000 Median :330.0 Median :19.05 Median :391.44
## Mean : 9.549 Mean :408.2 Mean :18.46 Mean :356.67
## 3rd Qu.:24.000 3rd Qu.:666.0 3rd Qu.:20.20 3rd Qu.:396.23
## Max. :24.000 Max. :711.0 Max. :22.00 Max. :396.90
## lstat medv
## Min. : 1.73 Min. : 5.00
## 1st Qu.: 6.95 1st Qu.:17.02
## Median :11.36 Median :21.20
## Mean :12.65 Mean :22.53
## 3rd Qu.:16.95 3rd Qu.:25.00
## Max. :37.97 Max. :50.00
#initial visualization. first 3 commands to explore the data
library (DataExplorer)
## Warning: package 'DataExplorer' was built under R version 3.4.3
plot_missing (BostonHousing) ##Are there missing values and what is the missing data profile?
plot_bar (BostonHousing) ##How does the categorical frequency for each discrete variable look like?
plot_histogram(BostonHousing) ##What is the distribution of each continous variable?
#transform variables based on results from histogram
##Set rad to factor
BostonHousing$rad <- as.factor (BostonHousing$rad)
##Creat new discrete variables, makes binary variables
for (col in c ("crim", "zn", "indus", "b"))
BostonHousing[[paste0(col, "_d")]] <- as.factor (ggplot2::cut_interval(BostonHousing[[col]], 2))
##Plot bar chart for all discrete variables
plot_bar (BostonHousing)
#Plot variable medv against all other variables
plot_boxplot(BostonHousing, by = "medv")
plot_scatterplot(
subset(BostonHousing, select = -c(crim, zn, indus, b)), by = "medv", size = 0.5)
#colorcoded correlation plot. Plot all variables against all other variables
plot_correlation(BostonHousing)
