- The first script,I have developed 2 deep learning models to predict the rating of a coffee shop. One, is a baseline model using all default parameters and the other is a tune model that I've made by tweaking the parameters.
- In the second script,above used Random Forest and GBM for developing models. In this script, I have created a random data set on my own and made two models. One that is a good model and the other model which has overfitted.
- The third script involved not only involved model development but data engineering as well. Before making the models I had to extract the day, year and month from a erroneous string containing all the details. The based on various parameters, I was able to make a Stacked Ensemble that was able to predict the price of a house. This Stack Ensemble was made of a GBM, Random Forest, Deep Learning and GLM models. The aim of the project was to create a model to predict the prices of house with RMSE < 123000 dollars. I was able to create a model that predicted the price of house with RMSE = 113561 dollars.
neilbhutada/Machine-Learning-with-h2o
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|