Executing the machine learning model will get to know which model is good for evaluation. Based on training data, it will allow you to check which model will perform better against data that is not yet seen.
Execute Machine Learning Model
Perform the ML model analysis
- To create and execute a ML analysis click on AnalysisML Analysis .
- All ML analysis, those created by you or shared with you will be displayed.
- To formulate a fresh analysis click on New. The ML analysis dialog box will display that contain three tabs:
- Analysis Builder which will help you to configure model, query, and filters.
- Columns Mapper will assist to map train and test columns of the dataset.
- Form Data will let you configure the columns
- In Analysis Builder tab, assign analysis name and ML model from the drop-down list. These models were created by you previously in ML Modeler. To learn about creating an ML model click here .
- Select the ML model from the drop down.
- The drop-down list will get the list of all the ML models you have in Infoveave.
- To make a prediction, from the Using Prediction tab, select between query or data.
- If you select the option Query, from the drop-down list select the query.
- when you select Form Data to make the prediction, then configure the column details under the tab Form Data.
- You can apply filters based on dimensions (if applicable).
- Click on Continue to proceed to Columns Mapper.
- You have an option to map each column available in a dataset under Columns Mapper tab.
- Assume that in a dataset, if a column has a different name in the train & test dataset. Then, you can map source column to destination column by selecting a column from the drop-down list.
- Check Same as Source checkbox, if you want to map all columns as same as datasource columns. In this case, the drop-down list of destination columns will get disabled.
- Click on Save to save ML Analysis.
Execute and Manage ML Analysis
You can find the created ML analysis under the tab My ML Analysis.
- Click on Execute to run the ML analysis.
- Click Edit if you want to make any changes in ML analysis. The edit dialog will display, where you can modify changes based on model, query and the filters.
- Click Delete , if you want to delete ML analysis.
- To share the model click on .
- You can also create folders to add the analysis, add descriptions to the ML analysis which will come handy when sharing the ML analysis.
Managing ML Analysis
ML analysis can be managed with the options to share, edit, move to a folder, add a description, and delete.
- Share the ML analysis with the team/role from the share option.
- Choose between the options
- Share with user
- Share with role
- To share with the users, select the “share with users” tab. Pick the user(s) with whom the ML analysis needs to be shared from the share dialogue box.
- Choose the “share with role” tab to make a ML analysis available to a certain work role. From the dialog box, choose a role.
- Select the users from the presented list of users.
- If you wish to share your ML analysis with all, then select Share With Everyone.
- Select the user from the available list and click to share the ML analysis.
- To remove a particular user/role from the shared list, select the user/role and click .
Click Save to share your ML analysis with the selected users.
- Shared personals receive a notification after the successful share.
- To unshare a ML analysis, just unselect users or uncheck the Share With Everyone.
- Edit any of your ML analysis with the Edit option.
- To move to a folder, create a folder by clicking the New Folder option, then drag the ML analysis into the desired folder using the drag-and-drop feature.
- You may also choose a folder from a drop-down menu by clicking the folder symbol on the ML analysis.
- Click “Add Description” and fill out the description details to add a description to the ML analysis.
- Select the Editor Type.
- Add necessary Tags (if required).
- Add Description and Content.
- Click Ok
- If you want to delete ML analysis, click on Delete .
- Type in “delete‘ in the text box.
- Click Yes.