Chapter 4 Understand Data

Understand your building raw materials can help you choose correct tools and make the most use of them to construct your ideal buildings.

                                    -- Gangmin Li

Understand data is a foundation of solving analytical problems. The two major purposes of understand data are:

  1. Access data quantity and quality
  2. Set up objectives for Data preprocess

In practice the initial data assessments can be done together or separately. The purpose of them is to setup objectives for Data preprocess to accomplish. The methods used to understand data are usually both Descriptive analysis and Exploratory analysis. We will use Titanic problem as an example to understand its data.