Machine Learning with Python

Module 1: Overview of Data Science

• Data Science as a Quantitative Discipline
• Overview of a Data Mining Process Cycle

Module 2: The Data Foundation

• Data Sources
• Types of Data
• Working with Missing Values
• Working with Outliers
• Working with Duplicate Records

Module 3: Sampling and Hypothesis Testing

• Why Sampling May be Important for Machine Learning
• Sampling Techniques and Sample Bias
• Statistical Hypothesis
• Z-score, T-score and F statistic
• P-values
• Implementation of Hypothesis Testing for Model Evaluation Analysis

Module 4: Machine Learning Fundamentals

• What is Machine Learning?
• Supervised vs. Unsupervised Learning
• Overview of Supervised Machine Learning
• Overview of Unsupervised Machine Learning
• Overview of Major Steps in Building and Testing Quantitative Models

Module 5: Building a Linear Regression Model with Python

• Univariate Regression vs. Multiple Regression
• Mathematical Foundation of Linear Regression Overview: least square method vs. maximum likelihood method
• Model Assumptions
• Working with Continuous Attributes
• Dealing with Collinear Variable
• Model Subset Selection:
• Automating Model Selection Procedure
• Model Parameter Evaluation, R squared vs. adjusted R squared
• Validating the Model
• Working with Categorical Variables
• Considering Input Variable Interactions

Module 6: Example of building a Classification Model with Python

• Dealing with Imbalanced Training Sets
• Understanding Confusion Matrix
• Evaluating Binary Classifiers using ROC / AUC

Module 7: Example of Cluster Analysis with Python

• Overview of Cluster Analysis Mathematical Foundation
• K-means Clustering Method

Module 8: Dimension Reduction techniques with Python

• What is Dimension Reduction?
• The Practical Goals of Dimension Reduction Implementation
• Principal Component Analysis vs. Singular Value Decomposition
• How Many Components to Choose

Module 9: Class Conclusion

• What was Not Covered in the Class
• Big Data Analytics – the Future of Machine Learning: Main Tools and Concept