Skip to main content
HomePythonGive Life: Predict Blood Donations
project

Give Life: Predict Blood Donations

Build a binary classifier to predict if a blood donor is likely to donate again.

Start Project for Free
11 Tasks1,500 XP6,709

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.
GroupTraining 2 or more people?Try DataCamp For Business

Loved by learners at thousands of companies


Project Description

"Blood is the most precious gift that anyone can give to another person — the gift of life." ~ World Health Organization

Forecasting blood supply is a serious and recurrent problem for blood collection managers: in January 2019, "Nationwide, the Red Cross saw 27,000 fewer blood donations over the holidays than they see at other times of the year." Machine learning can be used to learn the patterns in the data to help to predict future blood donations and therefore save more lives.

In this Project, you will work with data collected from the donor database of Blood Transfusion Service Center in Hsin-Chu City in Taiwan. The center passes its blood transfusion service bus to one university in Hsin-Chu City to gather blood donated about every three months. The dataset, obtained from the UCI Machine Learning Repository, consists of a random sample of 748 donors. Your task will be to predict if a blood donor will donate within a given time window. You will look at the full model-building process: from inspecting the dataset to using the tpot library to automate your Machine Learning pipeline.

Project Tasks

  1. 1
    Inspecting transfusion.data file
  2. 2
    Loading the blood donations data
  3. 3
    Inspecting transfusion DataFrame
  4. 4
    Creating target column
  5. 5
    Checking target incidence
  6. 6
    Splitting transfusion into train and test datasets
  7. 7
    Selecting model using TPOT
  8. 8
    Checking the variance
  9. 9
    Log normalization
  10. 10
    Training the logistic regression model
  11. 11
    Conclusion

Technologies

Python Python

Topics

Data ManipulationMachine Learning
Dimitri Denisjonok HeadshotDimitri Denisjonok

Python Backend Developer at Futrli

After graduating with a degree in Mathematics from the University of Nottingham (UK), Dimitri decided to pursue software engineering in Python. He has worked on various data related projects: from data visualizations to building data pipelines and machine learning models. His main interest is in Applied Data Science and how businesses and individuals can become more data-driven in their decision making.
See More

FAQs

What do other learners have to say?