Scatter plot (relplot): allows you to visualize the relationship between two quantitative variables and identify potential trends, clusters, or outliers.
Line plot (relplot): allows you to represent the evolution of one or more variables, particularly over time or according to an ordered variable.
Regression plot (regplot and lmplot): allows you to simultaneously visualize observations and the estimated relationship between two variables, facilitating the interpretation of a potential correlation.
Bar plot (catplot): allows you to compare categories based on aggregated values, such as a mean, sum, or count.
Histogram, KDE curve, and ECDF (displot):
the histogram represents the distribution of observations for a quantitative variable;
the KDE curve provides a smoothed estimate of this distribution;
the ECDF curve allows you to visualize the cumulative distribution and easily estimate percentiles or the proportion of observations below a given value.
Box plot (boxplot): summarizes the distribution of a variable using the median, quartiles, range, and outliers.
Letter-value plot (boxenplot): is an extension of the box plot designed for large datasets. It displays a greater number of quantiles to describe the distribution more precisely, particularly in the tails.
Violin plot (violinplot): combines information from a box plot with a density estimate, providing a better visualization of the shape of the distribution.
Heatmap (heatmap): represents the values of a matrix using color coding, making it easier to identify patterns, concentrations, or variations in the data.
Clustered heatmap (clustermap): combines a heatmap with hierarchical clustering of rows and columns based on their similarity, in order to highlight structures or groups within quantitative data.