Sklearn Logistic RegressionInstall

Summary

Predict class labels or probabilities for incoming data using a previously trained logistic regression model.

Inputs

• modelData (required) — JSON string containing the trained model (from train operation)
• predictFeatureColumns (required) — Comma-separated list of feature column names (must match training features)
• pythonPath — Path to Python executable with scikit-learn installed

Output shape

a list of prediction records

Each record adds prediction (and optionally probabilities) to the original input; may be omitted on failure if continueOnFail is not set

Examples

Example 1: Apply a trained model to new data to obtain predictions

modelData = '{...}', predictFeatureColumns = 'feature1,feature2'

Example 2: Obtain class probabilities for predictions

operation = predictProba, modelData = '{...}', predictFeatureColumns = 'feature1,feature2'