I found myself in the Data Science working on engineering projects
and predicting the likelihood of equipment failure.
This area has been incredibly inspiring to me.
My contacts:
- 📞 +7-983-238-55-06
- 📲 Telegram
- ✉ patrakeevvalentin@gmail.com
- ML skills:
Python,SQL,Git,SQLALchemy,PostreSQL,Redash,FastAPI,Airflow,PyTorch,PyCharm,Jupyter Notebook,Command-line - Technologies:
Pandas,Numpy,Scipy,Sklearn,Matplotlib,Seaborn,KNN,Linear/Logistic Regression,SVM,Decision trees,Random Forest,XGBoost,LightGBM,CatBoost,GridSearchCV,Optuna
| Project name | Description | Presented in the project |
|---|---|---|
| Recommendation-system-social-network | The project currently provides a social media post recommendation system. Inside the repository there is a diagram of the project |
EDA, Data Preprocessing, Feature Engineering (Juputer Notebooks), PostgreSQL, LogReg, Catboost, FastAPI, Test Postman |
| Equipments-Failures | Prediction of equipment breakdown/failure | EDA, Data Preprocessing, Feature Engineering (Juputer Notebooks), LogReg, CatBoost, XGBC, LGBMC, RandomForest, HistGradient, Optuna |
| KickStarter | Predicting the success of a crowdfunding platform | EDA, Data Preprocessing, Feature Engineering, LogReg, Catboost, GridSearchCV Comparison of several models |
| Regression with a Mohs Hardness | Using regression to predict the hardness of minerals based on their physicochemical properties | EDA -->> Feature Engineering, LGBMRegressor, CatBoostRegressor, KNeighborsRegressorr, SVR, RandomForestRegressor, Optuna |
