Create ML Pipeline

In this section, we will be building a prediction ML model using the preprocessed datasets in the previous section. The datasets will be the input to the ML Pipeline Builder which enables you to define the model’s architecture and select a target column for prediction.

To create a ML pipeline:

1. Navigate to the Pipelines component in the left menu and click Create Pipeline.

   

2. In the Create Pipeline pop-up, choose the desired Pipeline Type. Here, select Prediction as your pipeline type.

   

3. Enter Pipeline_B as the pipeline name, Choose Dataset as Cancer_detection_A, and Choose Target Column should be diagnosis. Note, the model name will be auto-populated based on the pipeline name.

4. Choose the Retrain model when the dataset is updated checkbox to retrain the pipeline whenever the dataset is updated with new data.

   Note: checkout this document on periodic-sync, and to create an auto-generated pipeline using AutoML refer to the document on AutoML pipeline.

   

5. Click Create. The pipeline details page will be displayed.

   

Next, configure the pipeline by defining the nodes in the ML Pipeline Builder interface.

Data Type Conversion

Because the target column “diagnosis” contains categorical data of type String, we will encode it for further ML training standards.

1. In the Operations menu, navigate to ML operations->Encoding->Label Encoder.

2. Drag and drop the Label Encoder node to the ML Pipeline Builder Interface. Connect the Label Encoder node to the Source node.

   

This operation will convert the column values of type String to Integer while maintaining the order and preserving data accuracy.

Hyperparameter Tuning

For any ML model, it’s mandatory to implement an ML algorithm based on which the model will be trained. In this tutorial, we will be implementing the logistic classification algorithm to configure the tuning parameters for the ML model to ensure it is optimized for our preprocessed dataset.

1. In the Operations menu, navigate to ML operations->Algorithm->Classification->Logistic Regression.

2. Drag and drop the Logistic Regression node in the Pipeline Builder. The node will be connected to the Destination node automatically.

3. Connect the Label Encoder and the Logistic Regression nodes. For the Logistic Regression node, we will go with the default configuration. Click Save.

   

Proceed with executing the pipeline by clicking on Execute for further evaluation and deployment.

Click Execution Stats to view more details about each stage of the execution in detail.

Upon successful execution of the ML Pipeline, the prediction model is created and will be displayed under the Models section.

You can view the details of the model on the Models details page by clicking on the model name.

Additionally, the accuracy of the generated model can be evaluated and viewed in the Metrics section of the Models details page. This provides valuable insights on the performance and effectiveness of the model in making predictions on the data.