Train AutoML in Python
Train a full machine learning pipeline on tabular data. You don't have to apply any preprocessing on data, the AutoML will fill missing values and convert categorical, text and dates into numeric format if needed. The AutoML will perform algorithm search and tunning. Please select training mode that you would like to use and set the training time budget.
Available modes:
- Explain - it is perfect for initial data analysis, very fast,
- Perform - good for bulding production-level pipelines, considers prediction time during optimization,
- Compete - the best model performance, it is using feature generation techniques and Stacked Ensemble.
Required packages
You need below packages to use the code generated by recipe. All packages are automatically installed in MLJAR Studio.
mljar-supervised>=1.1.7
Interactive recipe
You can use below interactive recipe to generate code. This recipe is available in MLJAR Studio.
In the below recipe, we assume that you have following variables available in your notebook:
- X (type DataFrame)
- y (type Series)
Python code
# Python code will be here
Code explanation
- Create AutoML object. AutoML configuration is setup in the constructor.
- Train AutoML object.
Example Python notebooks
Please find inspiration in example notebooks
MLJAR AutoML cookbook
Code recipes from MLJAR AutoML cookbook.
- « Previous
- MLJAR AutoML
- Next »
- Predict with AutoML