Hackerearth_get-a-room-ml-hackathon

Competition hosted on hackerearth.com

About

Build a Machine Learning model to identify the habitability score of the property based on the property's basic information and location-based information.

Competition LB Rank: 121/2803

Final Score 83.13212

Evaluation Metric 100*R2 score.

File information

• get_a_room_ml_hackathon_EDA.ipynb

  Packages Used,

   * seaborn
   * Pandas
   * Numpy
   * Matplotlib
  

  Basic Exploratory Data Analysis

• get-a-room-ml-hackathon-model.ipynb

  Packages Used,

    * Sklearn
    * Pandas
    * Numpy
    * Matplotlib
    * pycaret
  

  Data Pre-processing

  Compared multiple regression models using pycaret’s compare_models function. Then took the top 3 models based on the r2 score then blend the model by using pycaret blend_models function.

  For more detailed information about the model.

Random Forest Regressor Residual Plot

Random Forest Regressor Prediction Error Plot

Top 3 Models

Random Forest Model Feature Importance Plot