Every data scientist will likely have to perform linear regression tasks and predictive modeling processes at some point in their studies or career. For those of you looking to learn more about the topic or complete some sample assignments, this article will introduce 10 open datasets for linear regression. Additionally, some of the datasets on this list include regression tasks for you to complete with the data.
Linear Regression Datasets for Machine Learning
This dataset includes data taken from cancer.gov about deaths due to cancer in the United States. Along with the dataset, the author includes a full walkthrough on how they sourced and prepared the data, their exploratory analysis, model selection, diagnostics, and interpretation.
From the Behavioral Risk Factor Surveillance System at the CDC, this dataset includes information about physical activity, weight, and average adult diet.
Built for multiple linear regression and multivariate analysis, the Fish Market Dataset contains information about common fish species in market sales. The dataset includes the fish species, weight, length, height, and width.
This dataset was inspired by the book Machine Learning with R by Brett Lantz. The data contains medical information and costs billed by health insurance companies. It contains 1338 rows of data and the following columns: age, gender, BMI, children, smoker, region, insurance charges.
Created as a resource for technical analysis, this dataset contains historical data from the New York stock market. The dataset comes in four CSV files: prices, prices-split-adjusted, securities, and fundamentals. Using this data, you can experiment with predictive modeling, rolling linear regression, and more.
The OLS regression challenge tasks you with predicting cancer mortality rates for US counties. The dataset contains data from cancer.gov, clinicaltrials.gov, and the American Community Survey. It is in CSV format and includes the following information about cancer in the US: death rates, reported cases, US county name, income per county, population, demographics, and more.
This real estate dataset was built for regression analysis, linear regression, multiple regression, and prediction models. It includes the date of purchase, house age, location, distance to nearest MRT station, and house price of unit area.
From the UCI Machine Learning Repository, this dataset can be used for regression modeling and classification tasks. The dataset includes info about the chemical properties of different types of wine and how they relate to overall quality.
A useful dataset for price prediction, this vehicle dataset includes information about cars and motorcycles listed on CarDekho.com. The data is in a CSV file which includes the following columns: model, year, selling price, showroom price, kilometers driven, fuel type, seller type, transmission, and number of previous owners.
This dataset contains information compiled by the World Health Organization and the United Nations to track factors that affect life expectancy. The data contains 2938 rows and 22 columns. The columns include: country, year, developing status, adult mortality, life expectancy, infant deaths, alcohol consumption per capita, country’s expenditure on health, immunization coverage, BMI, deaths under 5-years-old, deaths due to HIV/AIDS, GDP, population, body condition, income information, and education.
Using the datasets above, you should be able to practice various predictive modeling and linear regression tasks. If you’re looking for more open datasets for machine learning, be sure to check out these 10 MNIST datasets and our related resources below. Don’t forget to sign up for our newsletter to receive more open datasets straight to your inbox.