Steel Strength Dataset


This is a small example that demonstrates some material datasets, how to retrieve these datasets and some functions for getting a better inside on the parameters of the datasets.

Datasets available on Matminer

First lets have a look on the datasets that are available on matminer:


Importing and exploring the steel_strength dataset

In this example we are going to import the steel_strength dataset. This dataset consists of 312 steels with experimental yield strength and ultimate tensile strength from Citrine.

With head() function we view the first 5 rows of the dataset.


Let’s plot now the histograms of every parameter involved in this dataset:


With describe() we can have some statistics for the various columns in the data:


Below is a simple plot tensile strength vs yield strength:

Below we compute the correlation matrix:


Another way to illustrate the correlation by plotting selected variables against each other


Correlation matrix can also be plotted as below: