Applied Data Science

Overview

Being able to extract knowledge from large, complex data sets is one of the most critical skills in today’s data-driven world. This course provides an introduction to fundamental concepts and techniques of Data Science. Learners will learn to combine tools and methods from computer science, statistics, data visualization, and the social sciences to extract knowledge from data. Concepts taught in the course will be illustrated with case studies drawn from fields such as business, public health, and the social sciences. This class focuses on teaching library (e.g, Pandas) based data analysis and model development.

Syllabus

Module 1: Data, Statistics, and Visualization

Module 1 begins with an introduction to Applied Data Science, and Introduction Discussion, and an Introduction Quiz. This module also includes lectures on data, statistics, and visualization. There is one Coursera Lab assignment to create your environmental setup and familiarize yourself with Python. There is also a Module Quiz at the end of this module.

Module 2: Introduction to Regressions

Module 2 includes lectures on regression, error evaluation, and model fitness. There is one Coursera Lab assignment on EDA and Visualization. There is also a Module Quiz at the end of this module.

Module 3: Linear Regressions

Module 3 includes lectures on linear models, bootstrapping, predictors, and Model F. There is one Coursera Lab assignment on k-NN Regression. There is also a Module Quiz at the end of this module.

Module 4: Model Selection

Module 4 includes lectures on overfitting, model selection, cross validation, and bias vs. variance. There is one Coursera Lab assignment on Linear Regression. There is also a Module Quiz at the end of this module.

Module 5: Clustering & Community Detection

Module 5 includes lectures on unsupervised learning, inter-observational distances, partition-based clustering, hierarchical clustering, diagnostics, optimization, and density-based clustering. There is one Coursera Lab assignment on Dimensionality Reduction. There is also a Module Quiz at the end of this module.

Module 6: Outlier Detection

Module 6 includes lectures on outliers, statistical-based detection, deviation-based detection, and distance-based detection. There is one Coursera Lab assignment on Outlier Detection, Model Selection, and Cross Validation. There is also a Module Quiz at the end of this module.