Practice-oriented advanced training program "Programming in Python. Modeling​"

SECTION I. Python Language Basics (14 hours)
1.1. Development environment Jupiter notebook. Data Types
1.2. Branch Operators
1.3. The concept of a cycle. Working with Loops
1.4. Functions
1.5. One-dimensional and multidimensional lists..
1.6. Strings, Sets and Dictionaries
1.7. Working with files

SECTION II. Special Python libraries (14 hours)
2.1. Data processing libraries: numpy, pandas
2.2. Data visualization libraries: matplotlib, plotly
2.3. Machine learning libraries: statsmodels, sklearn
2.4. Deep learning libraries: pytorch, keras

III SECTION. Simulation (32 hours)
3.1. Model verification
3.2. Feature engineering: categorical features, text features, derived features, feature pipelines
3.3. Naive Bayes classification: Bayesian classification, Gaussian Naive Bayes classifier, polynomial Naive Bayes classifier
3.4. Linear regression: simple linear regression, regression by combination of basis functions, regularization
3.5. Support Vector Machine:
3.6. Example: Face Recognition
3.7. Principal component method
3.8. Example: handwritten digit recognition
3.9. Clustering k-means methods
3.10. Example of color compression
3.11. Mixtures of Gaussian distributions
3.12. Kernel density estimation
3.13. Time series

Preliminary schedule of classes (webinars):