Data science is an exciting discipline, which leverages Machine Learning and Artificial Intelligence to enable decision makers to turn raw data into understanding, insight, and actionable options. With the enormous volume and variety of data being created and collected daily, Data Science is one of today’s fastest growing and critically important fields for businesses, organizations, and government. Data Scientists are in demand by both industry and the public sector with robust job growth expected well into the next decade.

Target Audience:

Information Architects, Data Analysts, Statisticians, Developers, Business Intelligence professionals, Business Analysts, Big Data specialists, Coders, Web Developers, learners interested in Predictive Analytics and anyone looking to expand their skills and / or advance their career by learning these valuable and in demand knowledge areas.

This hands-on, project-based course serves as a foundation for building real-world applications with Machine Learning capabilities and as a starting point for a career as a well-rounded data practitioner. In addition to guided projects and practical exercises, students will complete a final capstone project that integrates key concepts from the course. Each student will present their capstone to the class, demonstrating their ability to design, implement, and communicate a machine learning solution to a real-world problem.  Students who successfully complete will receive a Certificate of Completion from SUNY Westchester and a shareable digital badge in recognition of their achievement. 

The course focuses on key foundational concepts related to Data Science and Machine Learning using the Python programming language. Students will learn the foundations of problem solving, statistical algorithms, and machine learning models using Jupyter Notebooks within the Anaconda, Visual Studio Code, and Google Colab programming environments.  Students will also learn the basics of SQL databases as data sources, as well as the Docker containerization platform for model deployment.  

Students will implement experiments to solve various business problems using the Python programming language and machine learning algorithms included in the scikit-learn and Tensorflow libraries.  These experiments are designed to satisfy predictive analytics requirements related to regression, classification, image recognition and natural language processing. 

Objective:

After taking this class, students are expected to:

• Understand fundamentals of the Python programming language and create scripts that interact with data sets and machine learning models, 
• Interact with data sets in various formats (including flat files and SQL databases) and create meaningful visualizations based on business requirements, 
• Understand the basics of Python-based machine learning models and when to select the appropriate algorithms based on business requirements, 
• Gain proficiency with the Jupyter Notebook, Visual Studio Code and the Google Colab programming environments 
• Understand the foundations of Deep Learning and implement models using Deep Learning algorithms 
• Illustrate the data science lifecycle 
• Collect, clean, prepare and explore data 
• Navigate the model selection process 
• Evaluate and refine data models 
• Deploy data models using techniques including Docker containers

Course Outline:

• Class Introduction and Course Topics Review 
• Overview with Data Sets, Python and Jupyter Notebooks 
• Transform and Visualize Datasets (Including CSV, JSON and SQL queries) 
• Implement Data Wrangling Techniques 
• Introduction to Statistical Analysis 
• Implement Regression, Classification and Clustering Models 
• Understand Deep Learning Neural Networks 
• Understand Model Loss, Optimizers and Learning Rates 
• Understand the NLTK Libraries 
• Implement Deep Learning Models for Regression, Image Recognition and Natural Language Processing 
• Recognize Lifecycle Frameworks 
• Identify Tools and Best Practices 
• Demonstrate Exploratory Data Analysis 
• Explore Mathematical Areas Including Linear Algebra and Calculus 
• Tune Hyperparameters 
• Prepare Data for Stakeholders 
• Describe Deployment Methodologies