learn-co-curriculum / curriculum-overview Goto Github PK

Tips for Getting Started

While the program is designed for beginners, there are a few sets of skills that will help you prepare in order to get the most out of the course:

Familiarity with computers: You don’t need to be a technical expert, but you should know the difference between files and folders/directories and be able to navigate the file system on your computer. You should be comfortable connecting to the internet and have a working video camera and microphone for joining study groups, conversations with fellow students, and discussions with your support team, like instructors and coaches.

Computational Thinking: You don’t need to be able to program, but you’re going to have an easier time if you have some experience with basic programming concepts like variables, data types, conditionals and loops. If you have never written any code in any language, consider familiarizing yourself with these concepts ahead of the first day of school.. If you previously spent at least a few hours programming in any language and are comfortable with the basic principles mentioned above, you’re in good shape - we’ll be covering how they all work in Python during this course.

Pre-Calc: The course material assumes that you have experience with high school algebra. If you’re not sure whether you fit that description, consider reviewing the basic concepts required to graph a linear equation ahead of the first day of school.

If you have any questions or concerns about these three skills, please drop us a line at [email protected] so we can make sure to work with you when the course starts to share additional resources that will help you to fill any gaps.

The Data Science Curriculum V2.1

Module 1: Introduction to Data with Python and SQL
Our first module introduces the fundamentals of Python for data science. You’ll learn basic Python programming, how to use Jupyter Notebooks, and will be familiarized with popular Python libraries that are used in data science, such as Pandas and NumPy. Additionally, you’ll learn how to use Git and Github as a collaborative version control tool. To organize your data, you’ll learn about data structures, relational databases, ways to retrieve data, and the fundamentals of SQL for data querying for structured databases. Furthermore, you’ll learn how to access data from various sources using APls, as well as perform Web Scraping.

Finally, we’ll conclude with a heavy focus on visualizations as a way to go from data to insights.

At the end of this module, students will use their newly learned skills to collect, organize and visualize data, with the goal to provide actionable insights!

Module 2: Statistics, AB testing, and Linear Regression
Having learned how to gather and explore data with Python and SQL you can now go deeper into analyzing that information with statistics. In this module, you’ll learn about the fundamentals of probability theory, where you will learn about probability principles such as combinations and permutations. You will go on and learn about statistical distributions and how to create samples when distributions are known. By the end of this module, you will be able to apply this knowledge by running A/B tests. Additionally, you’ll learn how to build your first (and important) data science model: a linear regression model.

Module 3: Machine Learning techniques
This module is all about machine learning, with a heavy focus on supervised learning. To start, you will go a little deeper into regression analysis, learning about extensions to linear regression, and a new form of regression: logistic regression. In building regression models, students will learn about penalization terms, preventing overfitting through regularization and using cross validation to validate regression models.

Next, you’ll learn how to build and implement the most important machine learning techniques. You’ll learn about classification algorithms such as Support Vector Machines and Decision Trees. Additionally, you’ll learn how to build even more robust classifiers using ensemble methods such as Bagged and Boosted Trees, and Random Forests.

Module 4: Big Data, Deep Learning and Natural Language Processing
After a full module on supervised learning, this module focuses on a variety of advanced Data Science techniques. You will start with learning about unsupervised learning techniques such as clustering techniques and dimensionality reduction techniques. Next, you will be introduced to threading and multiprocessing to be able to work with big data. In doing so, you’ll learn about PySpark and AWS, and how to use those tools to build a recommendation system. Next, you will get an in-depth overview of deep learning techniques, learning about densely connected neural networks, enabling high-performing classification performance. Next, students will learn how to use regular expressions in Python, and how to manage string values, analyze text and perform sentiment analysis.

Module 5: Data Science Advanced Project
In our final project, you’ll work individually to create a large-scale data science and machine learning project. This final project provides an in-depth opportunity for you to demonstrate your learning accomplishments and get a feel for what working on a large-scale data science project is really like.

You and your fellow students will each pitch three different ideas and then decide on your final project with your instructors. Instructors advise on projects based on difficulty and feasibility given the course’s time constraints. At the end of the project, you’ll receive a grade based on various factors.

Upon project completion, you’ll know how to construct a project that gathers and builds statistical or machine learning models to deliver insights and communicate findings through data visualization and storytelling techniques.

Feedback and Raising Issues

In addition to embracing an open-source curriculum – to reflect industry trends and feedback – Flatiron has a dedicated Curriculum team who is consistently revisiting content to make sure we are sharing up-to-date information.

Our Curriculum team asks for your input on each lesson or lab in two ways:

1. On the right panel of each lesson, we ask “How do you feel about this lesson?” Help us improve the curriculum by sharing a quick “thumbs up” or “thumbs down” about the given lesson or lab.

2. If you see a curricular error, please report it by clicking on the “Flag” icon at the top of the lesson. This is where you’d report something like “When I type the command that’s listed, the Terminal reports: ‘Not Found’.”

Differentiated from a lesson feedback or curricular errors, there may inevitably be “bugs” that exist in the Learn environment. If you’ve completed a quiz or a lab, and for some reason you can’t move on to the next lab, please submit a bug report to [email protected]. This is another key skill of a data scientist - being able to articulate and document your findings.

Help.learn.co

A collection of help articles, with advice and answers to frequently asked questions from the Flatiron School Team: help.learn.co