language	tags	pretty_name	size_categories	task_categories	configs	license
[en]	[student performance tabular_classification multiclass_classification UCI]	Diamond	[10K<n<100K]	[tabular-classification]	[encoding cut cut_binary]	cc

Diamonds

The Diamonds dataset from Kaggle. Dataset collecting properties of cut diamonds to determine the cut quality.

Configurations and tasks

Configuration	Task	Description
encoding		Encoding dictionary showing original values of encoded features.
cut	Multiclass classification	Predict the cut quality of the diamond.
cut_binary	Binary classification	Is the cut quality at least very good?

Usage

from datasets import load_dataset

dataset = load_dataset("mstz/diamonds", "cut")["train"]

Features

Feature	Description
carat	float32
color	string
clarity	float32
depth	float32
table	float32
price	float32
observation_point_on_axis_x	float32
observation_point_on_axis_y	float32
observation_point_on_axis_z	float32
cut	int8