All you need is AutoML … and love! — Prevision.io
Organized by Kaggle Days, last week’s hackathon Now You Are Playing With Power concluded. Here is a recap of the project and a bit on how using Prevision.io’s AutoML capability performed. The hackathon:
How much electricity can a steam turbine generate? In this competition, your aim is to predict the unit load power generation based on the given factors of a steam turbine in specific working environments.
Steam turbines are still used continuously today due to their successful stability in electric power generation. Other important factors are that the steam conditions have been improving and that steam turbines have been evolving and responding to electric power energy demand by rapidly adopting the latest analysis technologies for their design and applying up-to-date technologies for higher efficiency and reliability to actual products.
The steam power plant consists of a boiler, steam turbine and generator and other fillers. The boiler produces high-pressure vapor and high temperature. Steam turbine converts heat energy steam to mechanical energy. The generator then converts mechanical energy to electrical energy.
At normal atmospheric pressure [0.10 MPa] water increases at 100 ° C when the pressure increases, the boiling point of the water increases. When the pressure is increased to 22.12 MPa, and at a temperature of 374ºC, water does not boil but is directly converted into steam. This is called the critical point, and the pressure above this critical point is called supercritical pressure. Supercritical pressure with a temperature equal to or more than 593ºC is called ultra-supercritical pressure.
Some parts of turbines working in a high-pressure environment face specific challenges over other turbines. The reason why is simple: these parts are exposed to higher pressures and higher temperatures, particularly in the high-pressure (HP) section.
Coordinated control system (CCS) coordinates boiler and turbine systems to track load demand and ensure safe and economical operation simultaneously.
The evaluation metric for this competition is Root Mean Squared Error (RMSE). Click here if you want to know more about regression metrics.
🚀 Only using Prevision.io AutoML capabilities, you would have completed 16th out of 130 submissions !
Simple Steps To Reproduce:
- Start the competition here
- Sign up / Login to https://cloud.prevision.io
- Upload train.csv and test.csv. You can find data here.
- Run experiment using full models + blend
- 40 minutes later the experiment is done, make predictions on test.csv file
- Submit to Kaggle. Your score is 1.94 on Kaggle Public Leaderboard (top 17%)
- Add predictions to test file and merge together train & test
- Upload traintest.csv
- Run experiment using full models + blend on this new dataset
- Wait 1h, make predictions on test.csv file
- Submit to Kaggle. Your score is 1.55 on Kaggle Public Leaderboard (top 12%)
Why use Prevision.io ?
✔️ In first 2 minutes, with a fast and easy Decision Tree, your score is 2.0 on Kaggle Public Leaderboard (top 19%)
✔️ No data preparation needed, Prevision.io manages missing values, target encoding, creation of statistics by row and normalization of continuous variables.
✔️ Prevision.io manages the search for hyper parameters
✔️ Prevision.io uses Linear Regression, Random Forest, Gradient Boosting (XGB, LGB, CAT), neural network (tensorflow/keras)
✔️ Prevision.io makes up to 3 levels of stacking!
Results
I launched a second experiment with additional feature engineering to obtain the final score / ranking. Prevision.io allows you to compare versions of experiments, keeping track of results in a simple UI. What did it take to make this happen:
🔥 Less than 30 minutes of effort on my side to achieve a top 12% finish.
👉 Try It Now, it’s FREE ! https://cloud.prevision.io