News for hackers. Stuff that matters.

__blacksite__

Re:Ludwig, a code-free deep learning toolbox on Tuesday February 12, 2019 @01:14PM (#19145960)
I've never seen TOML, but I really like it. In my pretty simple pipeline, I've just been using a JSON-like structure that I can easily import into Python:

  strategies = [
  {
      'name': 'column1',
      'kind': 'categorical',
      'strategy': 'ohe'
  },
  {
      'name': 'column2',
      'kind': 'continuous',
      'strategy': 'center'
  }
  ...
  ]

It has worked very well thus far. I received a request from a stakeholder a few weeks back about building a new model using a slightly different target. I told him it'd take a couple of days at least (it was a very similar target), but I had it completed (at least from a re-engineering perspective) in about 5 minutes. I simply changed the target variable config and removed any leaky features after changing the target.

I'm convinced that this approach, coupled with configurations for tree-based models like minimum samples per leaf and max depth, is the most efficient way of building predictive models. Those configurations specific to tree-based model software help to skirt things like the rule of five, etc., IMO.

Re:Ludwig, a code-free deep learning toolbox on Tuesday February 12, 2019 @10:15AM (#19144092)
Personally I've been working on the same declarative approach over the past couple of years at my company. This year I changed things to make heavy use of scikit-learn's `make_column_transformer` and `ColumnTransformer` capabilities.

It's nice to see other, (much more) reputable engineering organizations taking a similar approach and treating the construction of different predictive models as an exercise in configuration.

Although in my solution I haven't looked at any DL models, and typically default to feeding everything through XGBoost and performing a grid search for the best hyperparameter config there. My product is basically focused entirely around taking a raw dataset and a configuration file and producing an analytic dataset off of which algorithms can be tested.

I'd be really interested in hearing others' experiences with this type of stuff.