Machine Learning Datasets Playground

The playground where data narrates intriguing tales and machines lend a listening ear.

height_weight.csv

• Description: A lovely couple - height and weight! They share a strong positive linear relationship.
• Usage: Makes for a delightful first date with linear regression, predicting weight based on height.

multipleFeatures.csv

• Description: An ensemble of features, each contributing to the story. Linear relationships all around.
• Usage: Perfect setting for diving into multiple feature linear regression. An orchestra of features, if you will.

polyRegression.csv

• Description: Life isn’t always linear, sometimes it’s polynomial.
• Usage: Set the stage for polynomial regression models to unfold their non-linear magic.

logisticRegression.csv

• Description: A binary logistic regression dataset that believes in simplicity, projecting a straight line decision boundary.
• Usage: An ideal scenario for logistic regression models to flaunt their classification prowess.

logisticRegressionCircular.csv

• Description: A binary logistic regression dataset that enjoys a bit of curve, revealing an almost circular decision boundary.
• Usage: A playfield for logistic regression models with higher-order equations to take a swing.

linearRegressionSimple.csv

• Description: A classic single feature and target dataset.
• Usage: The perfect playground for beginners in linear regression. As uncomplicated as it gets.

logisticRegressionTumorSingle.csv

• Description: A binary logistic regression dataset with a serious cause - classifying tumors as malignant or benign based on size.
• Usage: Ideal for logistic regression models looking to make a positive impact in the medical field.

multi_class_generated.csv

• Description:
  • Dataset generated using ‘make_classification’ function from sklearn.datasets.
  • Consists of two features, both informative, with no redundant or repetitive features present.
  • Comprises four classes, each represented by a single cluster.
• Usage: Suitable for practicing multi-class regression tasks.

multipleFeaturesExtended.csv

-

anomaly_detection_data.csv

-

Note: The fun descriptions are simply metaphoric. The data files are as serious as they sound, perfect for your machine learning models to practice their skills.