Skip to content
View am-tropin's full-sized avatar
Block or Report

Block or report am-tropin

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
am-tropin/README.md

Hi there πŸ‘‹ I'm Aleksandr

πŸ“ˆ A Data Scientist, 2 years in applying Machine Learning to real-world problems (and 5 years of commercial experience as a Data Analyst and a BI Engineer).

πŸ‘¨β€πŸŽ“ My Degrees:

  • πŸ€– Mathematics and Mechanics Researcher, Discrete Mathematics and Mathematical Cybernetics
  • πŸ“ Mathematics Bachelor & Master, Geometry and Topology

πŸ“² Contact:

Pinned Loading

  1. poland-apartment-prices poland-apartment-prices Public

    πŸ‡΅πŸ‡±πŸ  The project predicts an apartment price for Warsaw, Krakow and Poznan. Distributed apartments by districts using geopandas; built XGBoost model with MAPE = 9% (the best of others).

    Jupyter Notebook

  2. english-song-lyrics english-song-lyrics Public

    πŸ‡¬πŸ‡§πŸŽ§ The project clusters English lyrics using NLTK and gives text-based recommendations (both with Tf-idf from scikit-learn). Also there are the listening and grammar trainers.

    Jupyter Notebook 1

  3. rain-maps-api rain-maps-api Public

    πŸ—ΊπŸŒ§ The project creates a gif of rain dynamics near Berlin using data from RainViewer API, with downloading a geomap using Plotly and building a CI/CD pipeline using GitHub Actions.

    Jupyter Notebook 2 1

  4. georgian-letters georgian-letters Public

    πŸ‡¬πŸ‡ͺ✍️ The project collects the image dataset of Georgian printed letters and recognizes them using CV and CNN from Keras and TensorFlow. Also there are trainers for learning letters and numerals.

    Jupyter Notebook

  5. restaurant-europe restaurant-europe Public

    πŸ‡ͺπŸ‡ΊπŸ½ The project classifies restaurants by various features using XGBoost and scikit-learn models and gives content-based recommendations of European restaurants using Jaccard metric from SciPy.

    Jupyter Notebook

  6. renewable-energy-europe renewable-energy-europe Public

    πŸ‡©πŸ‡ͺπŸ”‹ The project predicts weekly solar energy generation in Germany using seasonal ARIMA model with accuracy of 82% and Time Series Analysis from statsmodels.

    Jupyter Notebook