Versions Compared

Old Version 2

changes.mady.by.user Mohammed Iqbal

Saved on

compared with

New Version Current

changes.mady.by.user Amritesh Singh

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

On this Page

Table of Contents

Info

This document is under development. The final version will be made available by November 10, 2018.

Overview

Expected Input and Output

Prerequisites

Configuring Accounts

Accounts are not used with this Snap.

OR

This Snap uses account references created on the Accounts page of SnapLogic Manager to handle access to this endpoint. See <link to Snap Pack's account page> for information on setting up this type of account

maxLevel2
excludeOlder Versions|Additional Resources|Related Links|Related Information

Overview

This is a Transform type Snap that enables you to predict the target field for an unlabeled document. An unlabeled document is one that does not have a label field. So, the Snap reads this unlabeled document and predicts the target field. Predictions are made based on the regression model built by the Trainer (Regression) Snap.

Image Added

Input and Output

Expected input: An unlabeled document and the regression model. 

Expected output: Predictions from the regression model based on the input document. 

Expected upstream Snaps:

  • First input view: Any Snap that generates an unlabeled document document. For example, JSON Parser, JSON Generator, CSV Parser, CSV Generator, Mapper, and so on.
  • Second input view: Any Snap that reads and outputs the regression model. For example, a combination of File Reader, and JSON Parser.

Expected downstream Snaps: Any Snap that uses the predicted result. For example, Aggregate, or a combination of File Writer and JSON Formatter.

Prerequisites

The input document must be in tabular format (no nested structure). 

Configuring Accounts

Accounts are not used with this Snap.

Configuring Views

Input

This Snap has exactly one document input view.two document input views. The first input view is for the unlabeled document that requires prediction. The second input view is for the regression model.
OutputThis Snap has exactly one document output view.
ErrorThis Snap has at most one document error view.

Troubleshooting

None.

Limitations and Known Issues

None.

Modes


Snap Settings

Downloads
  • Drop-down lists: List out all the options present in the drop-down menu describing the options in terms of what they do and when they are to be used.
  • Conditional properties: If a property is not marked with a * but is required to be configured based on configuration of other properties then mark those as Conditional, explaining in the property, whose configuration warrants this property's configuration, that it is to be configured.
  • Read-only: If the property cannot be edited but displays some content based on the Snap's configuration

Check the Documenting Snap/Account settings page for a guideline on framing content for each type of property.

LabelRequired. The name for the Snap. Modify this to be more specific, especially if there are more than one of the same Snap in the pipeline.
Info
titleInstructions: Delete after reading
Execute during preview

Select this property to execute the Snap when the pipeline is validated.

Default value: Not selected

Examples

Snap Execution


Select one of the following three modes in which the Snap executes:

  • Validate & Execute: Performs limited execution of the Snap, and generates a data preview during Pipeline validation. Subsequently, performs full execution of the Snap (unlimited records) during Pipeline runtime.

  • Execute only: Performs full execution of the Snap during Pipeline execution without generating preview data.

  • Disabled: Disables the Snap and all Snaps that are downstream from it.

Default Value: Execute only

Example: Validate & Execute



Examples

Heating Load Prediction – Testing

The model trained in the Heating Load Prediction – Model Training example pipeline is tested against an unlabeled dataset. 

Image Added

Download this pipeline.


Note

To understand the dataset and the process prior to testing the model see the following examples:


Expand
titleUnderstanding the pipeline

In this example, the unlabeled dataset is created using the CSV Generator Snap. This dataset is used as the data input for the Predictor (Regression) Snap. The target field (heating load) is to be predicted for this dataset. 

Image Added

The model trained in the Heating Load Prediction – Model Training example is used as the model input. The File Reader Snap is configured to read this model from the SLDB. The JSON Parser Snap is used to parse the output from the File Reader Snap. Below is a preview of the output from the JSON Parser Snap (the model):

Image Added

Model Testing

To test a model trained on a classification dataset, the Predictor (Regression) Snap must be used. 

The Predictor (Regression) Snap requires two inputs:

  • An unlabeled dataset for the data input
  • The ML model trained on the labeled dataset for the model input

The Predictor Snap is configured as shown below:

Image Added

Based on its configuration, the output from the Snap includes one class prediction per document. This output is as shown below:

Image Added


Download this pipeline.

Additional Example

The following use case demonstrates a real-world scenario for using this Snap:


Downloads

Multiexcerpt include macro
namedownload_instructions
pageOpenAPI

Attachments
patterns*.slp,*.zip

Additional Resources

  • Glossary

  • Getting started with SnapLogic

    • Snap History

    PaneltitleSnap History

    Insert excerpt
    ML Core Snap Pack
    ML Core Snap Pack
    nopaneltrue