Predict on independent unlabeled observations

// Development runtime: explicit independent unlabeled inference.
// Synthetic rule y = 2*x + 3; x is measured in m, target y in J.
import aner.data
import aner.ml
import aner.tensor
import aner.units

var schema = data.schema().column("row_id", "Int64", false)
schema = schema.column("group", "String", false)
schema = schema.unit_column("x", "m", false)
schema = schema.unit_column("y", "J", false)
let observed = data.scan_csv("examples/fixtures/contextual/inference_training.csv", schema, "NA")
    .collect(0, 1048576, 2)
let populations = data.frame(observed, "row_id", "group", "y")
    .partition_groups(List("A", "B"), List(), List("C", "D"))
let scaler = ml.fit_standardizer(populations.train())
let training = scaler.transform(populations.train()).batch(1048576)
let model = ml.fit_linear(training)
let held_out = model.predict(scaler.transform(populations.test()).batch(1048576))

// These new observations have independent IDs and no target column.
// Physical columns carry their explicit source units; metadata stays outside
// the mapped model inputs. Mapping lists source names in fitted feature order.
var external_schema = data.schema().column("note", "String", false)
external_schema = external_schema.unit_column("distance_cm", "cm", false)
external_schema = external_schema.column("observation_id", "Int64", false)
let external_table = data.scan_csv("examples/fixtures/contextual/inference_observations.csv", external_schema, "NA")
    .collect(0, 1048576, 2)
let observations = data.frame(external_table, "observation_id", "", "")
let aligned = scaler.align_inputs(observations, List("distance_cm"))
let inputs = scaler.transform(aligned).batch(1048576)
let prediction = model.predict(inputs)

print(prediction.row_id(0))
print(prediction.row_id(1))
print(prediction.unit())
print(prediction.values().value(0, 0) > 6.999999999 &&
    prediction.values().value(0, 0) < 7.000000001)
print(prediction.values().value(1, 0) > 10.999999999 &&
    prediction.values().value(1, 0) < 11.000000001)
print((prediction.values().value(0, 0) - held_out.values().value(0, 0)) < 0.000000001 &&
    (prediction.values().value(0, 0) - held_out.values().value(0, 0)) > -0.000000001)
print(aligned.role())
print(prediction.explain().contains("fit_authorized=false"))
// inputs.targets(), ml.fit_linear(inputs) and fitting on aligned are errors.
// A raw-input model can be the alignment reference directly. A preprocessed
// model requires alignment against the first ledger and its exact fitted chain.