Generating the models template

In the case of a model with L2 regularization, the model template is as follows:

{   "MLModelId": "CH8_AH_L2_00{k}",   "MLModelName": "[MDL AH L2] 00{k}",   "MLModelType": "REGRESSION",   "Parameters": {       "sgd.shuffleType": "auto",       "sgd.l1RegularizationAmount": "0.0",       "sgd.l2RegularizationAmount": "1.0E-06",       "sgd.maxPasses": "100"   },   "TrainingDataSourceId": "CH8_AH_training_00{k}",   "RecipeUri": "s3://aml.packt/data/ch8/recipe_ames_housing_001.json"}

And for a model with L1 regularization, the model template is as follows:

{   "MLModelId": "CH8_AH_L1_00{k}",   "MLModelName": "[MDL AH L1] 00{k}",   "MLModelType": "REGRESSION",   "Parameters": {       "sgd.shuffleType": "auto",       "sgd.l1RegularizationAmount": "1.0E-04", "sgd.l2RegularizationAmount": ...

Get Effective Amazon Machine Learning now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial