Welcome to machine learning course

Hope you enjoy this course

If you have any question, please email me at: [email protected]

The course will meet two sessions per week, each session lasts two hours. There will be forty five minutes lecture following an hour and fifteen minutes lab time, students will work on real-world projects under guidance of instructor (students supposed to work on the projects at home, during the lab time, instructor will help students to troubleshoot errors as well as perfect the projects).

Week 1 (Unit 1 – Basics):

• Session 1: Introduction, Anaconda setup, Jupyter notebook, getting familiar with Pandas, numpy, scipy, SQLite database
• Session 2: Statistics, probability, hypothesis testing, t-test, p-value
  Project: database, statistics, probability

Week 2:

• Session 1: Probability distributions, chi squared, Bernoulli, Normal, Central Limit Theorem
• Session 2: Visualizations (matplotlib, seaborn), testing loans data, A/B test, RFC experiment
  Project: probability plotting, analysis report (using statistic models)

Week 3 (Unit 2 – Analysis):

• Session 1: Acquiring data in Json format, download and clean Citi Bike data
  Project: citibike
• Session 2: work on project, store and analyze an hour Citi Bike data

Week 4:

• Session 1: Acquiring weather data from an API, store and profile data
  Project: Temperature
• Session 2: work on project, analyze temperature data

Week 5:

• Session 1: HTML and CSS for web scraping, scape data from United Nations
  Project: education
• Session 2: work on project, store and profile scraped UN data, compare GDP to educational attainment

Week 6 (Unit 3 - Regression)

• Session 1: Overview Linear Regression, clean and plot data
  Project: Linear Regression
• Session 2: work on project, Linear Regression Analysis

Week 7:

• Session 1: Overview Logistic Regression, data cleaning
  Project: Logistic Regression
• Session 2: work on project, Logistic Regression Analysis

Week 8:

• Session 1: Overview Multivariate and Time Series
  Project: Multivariate Analysis, Time Series
• Session 2: work on project, Multivariate Analysis and Time Series

Week 9 (Unit 4 – Prediction)

• Session 1: Over fitting and Cross Validation, Decision Tree and Random Forest
  Project: Random Forest
• Session 2: work on project, data cleaning, Random Forest Analysis

Week 10:

• Session 1: Bayes, data cleaning, Bayes Analysis
  Project: Bayes
• Session 2: K-Nearest Neighbors, Clustering, data cleaning
  Project: knn, kmeans

Week 11:

• Session 1: Support Vector Machine
  Project: SVM
• Session 2: Principal Component Analysis, Linear Discriminant Analysis
  Project: PCA, LDA

Week 12 & 13 (Unit 5 – Capstone project)

These two weeks will dedicate to Capstone project. Each student will propose his/her own project to work on independently under instructor’s guidance.