How to use Sklearn Datasets For Machine Learning

In this post, you wil learn about how to use Sklearn datasets for training machine learning models. Here is a list of different types of datasets which are available as part of sklearn.datasets

• Iris (Iris plant datasets used – Classification)
• Boston (Boston house prices – Regression)
• Wine (Wine recognition set – Classification)
• Breast Cancer (Breast cancer wisconsin diagnostic – Classification)
• Digits (Optical recognition of handwritten digits dataset – Classification)
• Linnerud (Linnerrud dataset – Classification)
• Diabetes (Diabetes – Regression)

The following command could help you load any of the datasets:

from sklearn import datasets
iris = datasets.load_iris()
boston = datasets.load_boston()
breast_cancer = datasets.load_breast_cancer()
diabetes = datasets.load_diabetes()
wine = datasets.load_wine()
datasets.load_linnerud()
digits = datasets.load_digits()

All of the datasets come with the following and are intended for use with supervised learning:

• Data (to be used for training)
• Labels (Target)
• Labels attriibute
• Description of the dataset

The following command can be used for accessing the value of above:

# Let's use IRIS as an example for reading different aspects of data
iris.data
iris.target
iris.target_names
print(iris.DESCR)