Course materials for General Assembly's Data Science course in New York (8/23/15 - 11/12/15).
Course Producer: Daniel Demoray (email: ddemoray@generalassemb.ly)
Instructor: Amy Roberts
EiRs: Tom Hunter & Corey Maher
###Exit Ticket Fill me out at the end of each class!
###Course Description
Foundational course in data science, including machine learning theory, case studies and real-world examples, introduction to various modeling techniques, and other tools to make predictions and decisions about data. Students will gain practical computational experience by running machine learning algorithms and learning how to choose the best and most representative data models to make predictions. Students will be using Python throughout this course.
You can always reach out to Daniel by phone or email if you have any inquiries about enrollment, payments, graduation requirements or questions about how to get to know other students.
General Assembly's Part-time courses are pass/fail programs. We have certain requirements in order to be considered a graduate of our programs:
- Missing no more than 2 class sessions over the duration the course.
- Completing 80% of assigned homework
- Completing the final project
(Advanced topics will be finalized after student goals are defined)
| Week | Tuesday | Thursday |
|---|---|---|
| 1 | 8/25: Introduction to Data Science | 8/27: Introduction to Python for Data Science |
| 2 | 9/1: Intro to Machine Learning with KNN | 9/3: Regression & Regularization Part 1 HW1 Due |
| 3 | 9/8: Web APIs & Regression Part 2 | 9/10: Decision Trees for Classification & Regression HW2 Due |
| 4 | 9/15: Decision Trees Lab & Random Forests | 9/17: Clustering with K-Means Project Milestone: [Elevator Pitch] |
| 5 | 9/22: No Class | 9/24: Logistic Regression HW3 Due |
| 6 | 9/29: ROC Curves, AUC, & Imbalanced Classes | 10/1: Databases Technologies |
| 7 | 10/6: Recommender Systems HW4 Due |
10/8: Naive Bayes |
| 8 | 10/13: Natural Language Processing Project Milestone: [First Draft Due] |
10/15: Dimensionality Reduction |
| 9 | 10/20: Time Series Analysis | 10/22: Final Project Work Session and/or Advanced topic (TBD) |
| 10 | 10/27: Final Project Work Session and/or Advanced topic (TBD) | 10/29: Final Project Work Session & Peer Feedback Project Milestone: [Peer Feedback Due] |
| 11 | 11/2: Final Project Work Session and/or Advanced topic (TBD) | 11/5: Advanced topic (TBD) |
| 12 | 11/10: Project Presentations Day 1 Project Milestone: Presentation |
11/12: Project Presentations Day 2 Project Milestone: Presentation & Paper |
syllabus last updated: 8/24/2015
Please submit completed homework assignments to the appropriate Google Drive folder.
| HW | Topics | Dataset | Assigned | Due | Feedback |
|---|---|---|---|---|---|
| 1 | Data Exploration | titanic | 8/27 | 9/1 | 9/3 |
| 2 | KNN & Cross Validation | iris | 9/3 | 9/10 | 9/15 |
| FP1 | Elevator Pitch | N/A | 9/8 | 9/17 | 9/24 |
| 3 | Decision Trees | bank | 9/15 | 9/24 | 10/1 |
| 4 | Logistic Regression, ROC/AUC, & Imbalanced Classes | spam | 9/29 | 10/6 | 10/13 |
| FP2 | [First Draft] of Final Project | yours | 9/29 | 10/13 | 10/20 |
| FP3 | [Peer Feedback] on Final Project First Draft | yours | 10/13 | 10/20 | n/a |
| FP4 | [Final Project] | yours | 9/8 | 11/10 | 11/13 |
| instructor | times available | method |
|---|---|---|
| Amy | TBD | slack and hangouts by appointment |
| Corey | TBD | in person at GA or by slack |
| Tom | TBD | in person at GA or by slack |
Please use email or Slack to schedule office hours. Use [office hours] in the subject line as it can help us find the emails easier and reply more quickly.
You've all been invited to use Slack for chat during class and the day. Please consider this the primary way to contact other students. The TAs will be in Slack during class to handle questions. All instructors will be available on Slack during office hours (listed above).