Learn Python programming for data science. Part 2 describes how to use machine learning to generate predictions and recommendations and automate routine tasks.
Overview
Syllabus
Introduction
- Machine learning rocks
- What you should know
- Defining data science
- Why use Python for data science?
- Where does AI fit in?
- Machine learning 101
- Grouping machine learning algorithms
- Linear regression
- Multiple linear regression
- Logistic regression: Concepts
- Logistic regression: Data preparation
- Logistic regression: Treat missing values
- Logistic regression: Re-encode variables
- Logistic regression: Validating data set
- Logistic regression: Model deployment
- Logistic regression: Model evaluation
- Logistic regression: Test prediction
- K-means method
- Hierarchical methods
- DBSCAN for outlier detection
- Explanatory factor analysis
- Principal component analysis (PCA)
- Association rules models with Apriori
- Neural networks with a perceptron
- Instance-based learning with KNN
- Decision tree models with CART
- Bayesian models with Naive Bayes
- Ensemble models with random forests
- Next steps
Taught by
Lillian Pierson, P.E.