/Machinehack-Renew-Power-Hiring-Hackathon

Create a model to get an ideally functioning turbine’s expected rotor bearing temperature.

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Machinehack-Renew-Power-Hiring-Hackathon

Competition hosted on Machinehack.com

About

Create a model to get an ideally functioning turbine’s expected rotor bearing temperature.

Final Score is 0.01852

Evaluation Metric is MAPE.

File information

  • machinehack-renew-power-hiring-hackathon_eda.ipynb

    Basic Exploratory Data Analysis

    Packages Used,

     * seaborn
     * Pandas
     * Numpy
     * Matplotlib
    
  • machinehack-renew-power-hiring-hackathon-model.ipynb

    Data Pre-processing and model.

    Packages Used,

      * Sklearn
      * Pandas
      * Numpy
      * Matplotlib
      * pycaret    
    

    Compared multiple regression models using pycaret’s compare_models function. Then took the top 3 models based on the MAPE then blend the model by using pycaret blend_models function.

Xgboost Regressor Residual Plot

Alt text

Xgboost Prediction Error Plot

Alt text

Top 3 Models

Alt text

Xgboost Feature Importance Plot

Alt text

SHAP - Xgboost Feature Importance Plot

Alt text

Rotor bearing temperature distribution - train and test data

Alt text