Exploratory Data Analysis
In your typical data science project, the majority of your time will be spent investigating the data to find hidden patterns and outliers, often by plotting them in a visualization. This process is called Exploratory Data Analysis (EDA) and, through summary statistics, allows you to uncover underlying data structures and test your hypotheses.
We can split exploratory data analytics into three parts:
- Univariate analysis
- Bivariate analysis
- Linear relationships
Let's look at each of these analysis techniques in detail.
Univariate Analysis
Univariate analysis is the simplest form of analysis and is where we analyze each feature (column of a DataFrame) and try to uncover the pattern or distribution of the data. In this section, we will be looking at the following features:
- Revenue column
- Visitor type
- Traffic type
- Region
- Weekend-wise distribution
- Browser and operating system
- Administrative page...
