/2020-spring-datascience

Primary LanguageJupyter Notebook

CUNY Tech Prep

Introduction to Data Science and Machine Learning Class Outline

The Introduction to Data Science and Machine Learning class has been developed to teach students the underlying Data Science principles to work with data and build machine learning algorithms. In this course we will be using Python and Anaconda. After the course students are expected to have familiarity with all the Python libraries that compose the Data Science toolbox such as: Numpy, Pandas, Sklearn, Scipy, Seaborn, and Matplotlib.

Office Hours:

Resources:

The following links are meant to be resources that can be used outside of the classroom, as well as instruments if you want to go deeper on the topics covered in class. The first link is for beginner to intermediate Python coders. There are two options to access the rest of the books. The first option is throu your campus wi-fi you get auto log into acm.org and will have access to all ACM features. The second option is to sign up to acm.org for a yearly membership which only costs $20 per year for students. Once you sign-up to acm.org, click Learning Center then click E-Learning and on the upper tab click O’Reilly. O’Reilly has anything and everything computer savys might need.

There is no grading for this class but we do want you to learn as much as you can. Throughout the course students will be exposed to solve data problems using data science principles. After the course the student is expected to know how to handle data. The student is also expected to understand the type of ML algorithm’s that suit a particular problem. At the end of the course students will have the opportunity to shine as a star by showing-off their software engineering and data science skills on Demo Night.

Tentative course schedule:

Data Handling

  1. (3/12) Introduction to Data Science and working with Data.

  • Numpy and Pandas libraries.

  • Using SQL with python.

  1. (3/19) Data Exploration and Visualizations.

  • Matplotlib and Seaborn Libraries.

  • Type of Data, Imputing values.

  • Descriptive and Inferential Statistics

Machine Learning

  1. (3/26) Introduction to Machine Learning (Supervised).

  • Sklearn library and its toolbox.

  • Regression, Classification and evaluation metrics

  1. (4/2) Introduction to Machine Learning Continued (Unsupervised).

  • Clustering, Data reduction.

  • Ensemble Methods

  1. (4/16) Real-World Examples, Feature Engineering and Model Tuning.

  • Creating a data product.

  • Feature Engineering, imputing values and transforming data.

  • Model optimization.

  • Cross validation

  • Cookiecutter templates

Advanced Machine Learning

  1. (4/23) Natural Language Processing

  • Tokenization

  • Sentiment Analysis

  • BERT

  • TF-IDF

  • word2vec

  1. (4/30) Deep Neural Network.

  • Keras library.

  • Regression and Classification using DNN.

  1. (5/7) Recommendation Systems

  • Approaches, item vs user based

  • Real Examples

or

  1. (5/7) Image Classification with CNNs

  • Image augmentation

  • Dealing with large image data sets, flow from directory

  • Transfer learning