New method for predicting from coefficients

In some situations we might need to predict scores from coefficients stored in a data frame. This will be useful when we need to generate predictions for linear models where no .model file is available. For example, this is a legacy model, a model trained using different package etc. This will also be useful when we need to generate prediction using scaled coefficients (https://rsmtool.readthedocs.io/en/stable/usage_rsmtool.html#model-information).

We want to have a method in modeler that generates predictions from coefficients in a dataframe.

Start by locating the modeler entry point and reviewing the model-information documentation linked in the issue. Define how coefficient data frames represent linear models, including legacy and scaled coefficients, then verify that predictions match supported model-based predictions across representative cases.

Written by the indexing model from the issue text.