Here you'll find my data science and machine learning projects:
(Statistical and ML implementations)
autoregressive_model Autoregressive (AR) models with advanced techniques: model selection, diagnostics, structural breaks, rolling forecasts, Fourier seasonality, exogenous variables, business cycle analysis, and benchmarking for economic time series.
autoregressive_moving_average_ARMA A practical ARMA modeling implementation in Python. Explores theory, data analysis, model fitting, diagnostics, forecasting, and advanced extensions, utilizing statsmodels, pandas, and matplotlib.
data_augmentation_for_CNN This project demonstrates image data augmentation techniques using TensorFlow/Keras to enhance CNN training on a car classification dataset. It applies random flips, contrast adjustments, and explores pipeline optimizations to reduce overfitting and improve model generalization.
deterministic_process_for_ts Exploration of deterministic processes in time series forecasting using statsmodels, featuring trend modeling, seasonality, Fourier terms, custom components, and integration with AutoReg and SARIMAX models.
discrete_choice_models Extended discrete choice modeling notebook with Fair's affair data & STAR98 education analysis. Covers Logit, Probit, GLM, diagnostics, model comparison, marginal effects, and advanced topics like censored regression and count models. Complete with visualizations and validation techniques.
generalized_linear_models Generalized Linear Models (GLMs) with Python examples, covering Binomial, Gamma, and Gaussian families, model diagnostics, formula interface, and alternative estimation approaches using statsmodels.
kernel_density_estimation_kde Kernel Density Estimation (KDE) in Python. Explore theory, implementation, bandwidth optimization, kernel functions, and practical applications with statsmodels and scipy.
LOWESS-Smoother-Implementation Implementation of LOWESS (Locally Weighted Scatterplot Smoothing) algorithm with bootstrap confidence intervals for nonparametric regression and data smoothing in Python.
ordinary_least_squares Ordinary Least Squares regression with comprehensive diagnostics, robust alternatives, and best practices.
quantile_regression Quantile regression implementation with statsmodels using Engel dataset. Analyzes conditional distributions, compares with OLS, visualizes results, and demonstrates inventory optimization applications. Includes diagnostics and alternative approaches.
recursive_least_squares_rls Recursive Least Squares: theoretical foundations, practical applications with copper and monetary datasets, structural break analysis, and comparisons with alternative time-varying parameter methodologies.
regression_diagnostic Regression diagnostic tests using statsmodels for model validation and assumption checking in real-world data analysis.
rolling_regression A comprehensive rolling regression analysis notebook using Fama-French factors and industry portfolios. Demonstrates dynamic CAPM estimation, time-varying parameter analysis, structural break detection, and practical applications in finance with Python.
seasonal_trend_decomposition_using_LOESS_STL STL decomposition notebook with parameter analysis, diagnostics, seasonal strength metrics, forecasting, and alternative methods. Complete time series decomposition workflow with visualizations and statistical tests.
survival_and_duration_analysis A comprehensive Python survival analysis workflow using statsmodels. Covers Kaplan-Meier estimation, log-rank tests, Cox proportional hazards regression, and alternative approaches like Nelson-Aalen and Accelerated Failure Time models with practical code examples.
the_theta_model A comprehensive implementation of the Theta Model for time series forecasting. Includes model estimation, sensitivity analysis, diagnostics, and extensions. Uses statsmodels, pandas, and matplotlib.
weighted_least_squares_wls Analysis and comparison of Weighted Least Squares (WLS) and Ordinary Least Squares (OLS). Covers heteroscedasticity, Feasible WLS, Huber robust regression, and validates methods with a Monte Carlo simulation.
🔒 private / ⏳ in progress
Focus: Statistical algorithms and ML applications in particle physics
Status: 🔒 private / ⏳ active development
TSU-wb_pc_hard Final project for the professional development program "Introduction to Data Science" at Tomsk State University in 2025.
linux-env-backup Automated backup and restore solution for Linux development environments. Backs up packages, development environments, IDE (VS Code) settings, and configurations.
restic-backup-automation-tool Automated backup system with Restic. Supports USB drives and HDDs. Features smart scheduling, auto-mounting, snapshot cleanup.