Project Give Life: Predict Blood Donations
"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.
To complete this Project, you need to know some Python, pandas, and logistic regression. We recommend one is familiar with the content in DataCamp's Manipulating DataFrames with pandas, Preprocessing for Machine Learning in Python, and Foundations of Predictive Analytics in Python courses.
- Inspecting transfusion.data file
- Loading the blood donations data
- Inspecting transfusion DataFrame
- Creating target column
- Checking target incidence
- Splitting transfusion into train and test datasets
- Selecting model using TPOT
- Checking the variance
- Log normalization 10.Training the linear regression model 11.Conclusion