Correlogram

Definition

A correlogram or correlation matrix allows to analyse the relationship between each pair of numeric variables of a dataset. The relationship between each pair of variable is visualised through a scatterplot, or a symbol that represents the correlation (bubble, line, number..).

The diagonal often represents the distribution of each variable, using an histogram or a density plot.

# library & dataset
import seaborn as sns
df = sns.load_dataset('iris')
import matplotlib.pyplot as plt
 
# Basic correlogram
sns_plot = sns.pairplot(df)
sns_plot.savefig("IMG/correlogram1.png")

Note: exceptionally, graphic provided in this page are made with Python, since I really like the pairplot function of the seaborn library.

What for

Correlogram are really handy for exploratory analysis. It allows to visualize the relationships of the whole dataset in a glimpse. For instance, the linear relationship between petal length and petal width is obvious here, as the one concerning sepal.

When you get a multivariate dataset, building a correlogram is one of the first step you should follow.

Variation

All the variations described in the scatterplot section are also available for correlogram. For example, why not applying a linear regression to each pair of variable:

# with regression
sns_plot = sns.pairplot(df, kind="reg")
sns_plot.savefig("IMG/correlogram2.png")

As described in the scatterplot section, it is a good practice to display subgroups if a categoric variable is available as well:

# with regression
sns_plot = sns.pairplot(df, kind="scatter", hue="species", markers=["o", "s", "D"], palette="Set2")
sns_plot.savefig("IMG/correlogram3.png")

Common mistakes

• Displaying the relationship between more than ~10 variables makes the plot very hard to read
• All the common caveats of scatterplot and histogram apply

Related

Bubble plotAdd a third dimension to your scatter: the circle sizeScatter plotDisplay the relationship between 2 numeric variablesConnected ScatterplotVery close from a scatterplot, but link data points with segmentsDensity 2dOne of the best way to avoid overplotting for big sample size

Build your own

The R, Python, React and D3 graph galleries are 4 websites providing hundreds of chart example, always providing the reproducible code. Click the button below to see how to build the chart you need with your favorite programing language.

R graph gallery Python gallery React gallery D3 gallery