This course will teach you how to leverage the power of Python and artificial intelligence to create and test hypothesis. We'll start for the ground up, learning some basic Python for data science before diving into some of its richer applications to test our created hypothesis. We'll learn some of the most important libraries for exploratory data analysis (EDA) and machine learning such as Numpy, Pandas, and Sci-kit learn. After learning some of the theory (and math) behind linear regression, we'll go through and full pipeline of reading data, cleaning it, and applying a regression model to estimate the progression of diabetes. By the end of the course, you'll apply a classification model to predict the presence/absence of heart disease from a patient's health data.
Introduction to Python Programming for Hypothesis Testing
In this module, we'll get ourselves started with Programming in Python. After becoming familiar with Python and the Jupyter Notebook interface, we'll dive into some basic coding paradigms such as variables, loops, and functions. We'll also cover data structures in the form of lists and dictionaries. We'll go through one of the most useful things in your Python arsenal - importing and using modules effectively. Finally, we'll introduce scikit-learn and walk through a classification problem to predict the presence/absence of cancer from health data.
Creating a Hypothesis: Numpy, Pandas, and Scikit-Learn
In this module, we'll become familiar with the two most important packages for data science: Numpy and Pandas. We'll begin by learning the differences between the two packages. Then, we'll get ourselves familiar with np arrays and their functionalities. Adding text turns our arrays into tables, and gives rise to the Pandas module. After a basic introduction, we'll end with a series of important data manipulation tools such as indexing, merging/combining datasets, and reshaping data.
Scikit-Learn Revisited: ML for Hypothesis Testing
In this module, we'll work from the ground up to build and test our hypothesis. Learning both the theory and the code, we'll learn to test our predictions with different types of machine learning algorithms. We'll start by going through some of the necessary data preprocessing steps to orient ourselves. Getting familiar with using the Scikit-Learn library starts with the documentation. From there, we'll load in a dataset and analyze some of its most basic properties. Finally, we'll import and use models to make a prediction.
Using Classification to Predict the Presence of Heart Disease
In the final project, we'll try and predict the presence of heart disease using patient data. We'll load in data, create new features, and apply a machine learning algorithm using scikit-learn.
Sabrina Moore, Rajvir Dua and Neelesh Tiruviluamala