b.e.exploratory.dim_vis: Exploratory - Dimension Visualization

In Vitlik/DA1-16: Analysis of a spambase dataset

Description

To get (back) to the overview of all steps and functions use this link: a.a.main

This function simply creates several plots to better understand the dimensions of the data.

First plot is a barplot of the class dimension to grasp the amount of non-spam and spam classifications. The plot can be find in "out/1. Exploratory - Barplot of email numbers.pdf"

The second plot creates Histograms for each dimension to show the distributions of observations. It is stored in: "out/1. Exploratory - Histograms.pdf"

The third plot contains the scatterplots of all pairs of dimensions which had a correlation of at least 0.2 in descending order which puts the plots of dimensions with the highest correlation to the top. The result is stored in: "out/1. Exploratory - Scatterplots of highly correlated dimensions.pdf"

Usage

b.e.exploratory.dim_vis()

Author(s)

Vitali Friesen

Vitlik/DA1-16 documentation built on May 9, 2019, 10:01 p.m.