PS linear regression

Method 1: Visual interface

Add the PS Linear Regression component to your workflow in Designer, then configure its parameters in the right pane.

L1 regularization drives sparsity — useful when many features are irrelevant and you want a sparse model. L2 regularization shrinks all coefficients proportionally — useful when features are correlated. If you are unsure which to use, start with L2 (set L1 weight to 0) and tune from there.

Method 2: PAI command

Run PAI commands through the SQL Script component.

Training command:

PAI -name ps_linearregression
    -project algo_public
    -DinputTableName="lm_test_input"
    -DmodelName="linear_regression_model"
    -DlabelColName="label"
    -DfeatureColNames="features"
    -Dl1Weight=1.0
    -Dl2Weight=0.0
    -DmaxIter=100
    -Depsilon=1e-6
    -DenableSparse=true

Prediction command:

drop table if exists logistic_regression_predict;
PAI -name prediction
    -DmodelName="linear_regression_model"
    -DoutputTableName="linear_regression_predict"
    -DinputTableName="lm_test_input"
    -DappendColNames="label,features"
    -DfeatureColNames="features"
    -DenableSparse=true

Parameters:

Step 1: Create input data

Run the following SQL statement in the SQL Script component to generate the input table.

drop table if exists lm_test_input;
create table lm_test_input as
select
*
from
(
select cast(2 as BIGINT) as label, '1:0.55 2:-0.15 3:0.82 4:-0.99 5:0.17' as features
    union all
select cast(1 as BIGINT) as label, '1:-1.26 2:1.36 3:-0.13 4:-2.82 5:-0.41' as features
    union all
select cast(1 as BIGINT) as label, '1:-0.77 2:0.91 3:-0.23 4:-4.46 5:0.91' as features
    union all
select cast(2 as BIGINT) as label, '1:0.86 2:-0.22 3:-0.46 4:0.08 5:-0.60' as features
    union all
select cast(1 as BIGINT) as label, '1:-0.76 2:0.89 3:1.02 4:-0.78 5:-0.86' as features
    union all
select cast(1 as BIGINT) as label, '1:2.22 2:-0.46 3:0.49 4:0.31 5:-1.84' as features
    union all
select cast(0 as BIGINT) as label, '1:-1.21 2:0.09 3:0.23 4:2.04 5:0.30' as features
    union all
select cast(1 as BIGINT) as label, '1:2.17 2:-0.45 3:-1.22 4:-0.48 5:-1.41' as features
    union all
select cast(0 as BIGINT) as label, '1:-0.40 2:0.63 3:0.56 4:0.74 5:-1.44' as features
    union all
select cast(1 as BIGINT) as label, '1:0.17 2:0.49 3:-1.50 4:-2.20 5:-0.35' as features
) tmp;

The table has two columns: label (BIGINT) and features (STRING in KV format). Each features value encodes feature IDs and values separated by colons, with pairs separated by spaces — for example, 1:0.55 2:-0.15.

In KV format, feature IDs must be positive integers and feature values must be real numbers. If feature IDs are strings, serialize the data first. If feature values are categorical strings, apply feature discretization before training.

Step 2: Build the workflow

Build a workflow in Designer using the components shown below. For details on workflow creation, see Algorithm modeling.

Step 3: Configure the components

Read Table-1:

On the Select Table tab, set Table Name to lm_test_input.

PS Linear Regression:

Use the settings below. Leave all other parameters at their defaults.

Prediction:

Use the settings below. Leave all other parameters at their defaults.

Step 4: Run the workflow

Click the Run button on the canvas to start the workflow.

Step 5: View prediction results

After the workflow completes, right-click the Prediction-1 component and choose View Data > Prediction Result Output.

Run the same example with PAI commands

The following commands reproduce the workflow above using the PAI command interface. All commands use the same lm_test_input table.

Train:

PAI -name ps_linearregression
    -project algo_public
    -DinputTableName="lm_test_input"
    -DmodelName="linear_regression_model"
    -DlabelColName="label"
    -DfeatureColNames="features"
    -Dl1Weight=1.0
    -Dl2Weight=0.0
    -DmaxIter=100
    -Depsilon=1e-6
    -DenableSparse=true

Predict:

drop table if exists logistic_regression_predict;
PAI -name prediction
    -DmodelName="linear_regression_model"
    -DoutputTableName="linear_regression_predict"
    -DinputTableName="lm_test_input"
    -DappendColNames="label,features"
    -DfeatureColNames="features"
    -DenableSparse=true

The prediction output table (linear_regression_predict) contains the original label and features columns appended with the predicted scores.