Machine Learning Engineer Nanodegree

Model Evaluation and Validation

Project: Using Machine Learning to classify if a patient has diabetes

Install

This project requires Python and the following Python libraries installed:

• NumPy
• Pandas
• matplotlib
• scikit-learn
• tensorflow
• keras

You will also need to have software installed to run and execute a Jupyter Notebook.

If you do not have Python installed yet, it is highly recommended that you install the Anaconda distribution of Python, which already has the above packages and more included.

Code

Template code is provided in the Capstone_Final_Project.ipynb notebook file. You will also be required to use the diabetes.csv dataset file to complete your work.

Run

Use jupyter notebook kernel conda_tensorflow2_p36

In a terminal or command window, in the root project run:

ipython notebook Capstone_Final_Project.ipynb

or

jupyter notebook Capstone_Final_Project.ipynb

or open with Jupyter Lab

jupyter lab

This will open the Jupyter Notebook software and project file in your browser.

Data

The diabetes dataset consists of 768 data points, with each datapoint having 9 features. You can get this dataset from kaggle.

Features

1. Pregnancies: Number of times pregnant
2. Glucose: Plasma glucose concentration 2 hours in anoral glucose tolerance test.
3. BloodPressure: Diastolic blood pressure (mm Hg)
4. SkinThickness: Triceps skin fold thickness (mm)
5. Insulin: 2-Hour serum insulin (mu U/ml)
6. BMI: Body mass index (weight in kg/(height in m)^2)
7. DiabetesPedigreeFunction: Diabetes pedigree function
8. Age: years old

Target Variable

9. Outcome: Is diabetic person or not