Run training on your local machine.
You’ll be able to save and share your notebooks and your training data with other users.
1. Create a notebook
Follow the instructions to create a Kaggle Notebook and navigate to the Create Notebook page.
2. Select a Machine Learning Library
Go to the Choose a Machine Learning Library page. Here you can find a list of libraries that you can use in your notebooks. For this tutorial, select Linear Regression.
3. Choose a Kaggle Course
Next, you need to select a machine learning course. There are more than 20 courses available, and you can find the course with the most interesting exercises and that you find easiest to understand. For this tutorial, choose the Linear Regression with Supervised Learning.
4. Save the Notebook
Next, click the Save and Upload Notebook button to save the notebook locally on your machine.
You can open the notebook on any computer. All the data, code, and input you added to the notebook will be available to you.
Training on Kaggle Notebooks
Kaggle notebooks can be used to train machine learning models. This way, you can practice your machine learning skills by training on actual data.
To train your models, you need to upload your data to the dataset and specify the parameters of your models. You can either upload the data from scratch or load a dataset already created by another user.
1. Uploading data from scratch
If you want to create a new dataset from scratch, you can do that by uploading a new dataset. For this tutorial, you’ll use the Kaggle explorer to load the csv file from CSV imports. If you’re not familiar with the process, you can learn more on the Data Tutorials page.
2. Loading data from CSV imports
Open the Explorer page. Click the Load Data button to load the data. If the data is already in your dataset folder, you can click the Open button to use it.
3. Specify Parameters
Once the data is loaded, you’ll see the data in a table. Next, you can add parameters of your models. First, you need to use the Columns dropdown to select the columns that you want to predict. Then, you need to add the features and labels.
In this tutorial, you’
Related links:
Comments