LoginSign Up
← Back to all sparks
H

hardhat

ANALYTICS
Velocity0.0

Developer toolkit for building consistent modeling packages in R

github.com/tidymodels/hardhat ↗

hardhat keeps adding the contracts tidymodels needs next

tidymodelsr-statsmachine-learninginfrastructureapi-contracts
◆Current state
hardhat is the infrastructure layer under tidymodels, defining the preprocessing and extraction contracts other packages implement. Its releases read as a list of new generics and vector classes: extract_postprocessor(), extract_fit_time(), extract_tailor(), and a quantile_pred() class for quantile-regression output. The newest release is narrow warning and missing-value handling in mold().
◆Where it's heading
Each addition here lands ahead of a user-facing feature elsewhere in tidymodels — the postprocessor and tailor generics precede the postprocessing workflow, quantile_pred() precedes quantile prediction in parsnip. The package's own surface stays deliberately small and its cadence follows what the rest of the stack is about to need.
◆Prediction
Expect further extraction generics and prediction-type classes as tidymodels builds out postprocessing, with hardhat's own API remaining thin.

◆Recent moves

  1. 4mo ago

    mold() warning and quantile missing-value fixes

    Silences a spurious strings_as_factors warning on recipe objects and improves missing handling in quantile predictions. Cleanup on the quantile work introduced in 1.4.1.

    View source ↗
  2. 11mo ago

    extract_tailor() generic added

    Another extraction contract for the rest of tidymodels to implement, this time for tailor objects. Small in isolation, but it is how postprocessing becomes reachable from a fitted workflow.

    View source ↗
  3. 1y ago

    quantile_pred() class for quantile regression output

    Adds the vector class that quantile predictions travel in, and moves errors onto cli. This is the contract parsnip's quantile-regression support is built on — the capability shows up downstream, not here.

    View source ↗
  4. 2y ago

    extract_postprocessor() and extract_fit_time() generics

    Two more generics defined ahead of their consumers, including the first postprocessing hook. Consistent with hardhat's pattern of landing the contract before the feature.

    View source ↗
  5. 2y ago

    Documentation topic renamed at CRAN's request

    A documentation rename with no code change.

    View source ↗
  6. 3y ago

    Multi-outcome prediction helpers and one-hot factor encoding

    Adds the spruce_*_multiple() family for standardising multi-outcome predictions and fct_encode_one_hot(), plus strings_as_factors control on the recipe blueprint. Broadens what preprocessing blueprints can express.

    View source ↗