This contains my implementation of a logistic regression classifier using gradient descent. The classifier is tested using both the raw features of data and the quadratic features of the data. I also included a high level implementation from the NumPY library in Python of logistic regression in order to compare how well my classifier performed against an established implementation. This project contains the 6 files of data used to test the classifiers. It also contains 4 .py files containing the implementation and testing of the logistic regression classifiers. The two files named LogReg1... are my own implementation of a logistic regression classifier using gradient descent. The other two files are the high level implementations using the NumPY library. The files labeled ...QuadFeats convert the datasets into quadratic features {1,x,y,xyx^2,y^2} vs the ...RawFeats which use the raw features of the dataset for classification {x,y}. The classifier implementation are all separated into separate files per the request of my teacher for the assignment. Also contained in this project is the report I wrote up summarizing my results for each classifier along with explanations of my implementations of the classifiers. Graphs containing the results from the classifier being run are included for each of the 4 .py files being run with all 6 different datasets. The misclassification rates are also included.