What does EDA typically use to summarize data characteristics?

Exploratory Data Analysis (EDA) primarily employs visual methods and graphical representations to provide insight into data characteristics. These visual tools, such as histograms, box plots, scatter plots, and heatmaps, allow analysts to identify patterns, trends, and anomalies within the dataset. By visualizing data, EDA helps in understanding its distribution, the relationship between variables, and potential outliers, all of which are critical for informing subsequent modeling and analysis.

While statistical metrics and other techniques may support the analysis, the cornerstone of EDA is its focus on visualization, which enhances human interpretation and understanding of the data. This makes visual representations an integral part of the data exploration process, as they enable more intuitive insights compared to raw numerical data alone.