Graham McIntire
e7a7ae073d
Task 9.3 - Weight recalibration via gradient descent:
- Recalibrator module fits logistic regression weights using Nx
- Trains on QSO positives vs random baseline negatives
- Cross-validates by month, normalizes weights to sum to 1.0
- Mix task: mix recalibrate_scorer --sample 5000 --epochs 2000
Task 9.4 - Side-by-side scorer comparison:
- ScorerDiff.compare/3 re-scores grid with old vs new weights
- Reports mean diff, regressions, improvements, per-band breakdown
- Mix task: mix scorer_diff --new-weights '{...}'
Phase 3 - NEXRAD ingestion pipeline:
- NexradClient fetches IEM n0q composite PNGs, extracts per-point
box statistics (mean/max dBZ, texture variance)
- NexradObservation schema with unique (lat, lon, observed_at)
- NexradWorker on :nexrad queue for background processing
- nexrad_texture backtest feature in Features module
- mix nexrad_backfill --limit 200
All tasks added to AdminTaskWorker and Release for production use.
1116 tests, 0 failures.
31 lines
872 B
Elixir
31 lines
872 B
Elixir
defmodule Microwaveprop.Weather.NexradObservation do
|
|
@moduledoc false
|
|
use Ecto.Schema
|
|
|
|
import Ecto.Changeset
|
|
|
|
@primary_key {:id, :binary_id, autogenerate: true}
|
|
@foreign_key_type :binary_id
|
|
|
|
schema "nexrad_observations" do
|
|
field :observed_at, :utc_datetime
|
|
field :lat, :float
|
|
field :lon, :float
|
|
field :mean_reflectivity_dbz, :float
|
|
field :max_reflectivity_dbz, :float
|
|
field :texture_variance, :float
|
|
field :pixel_count, :integer
|
|
|
|
timestamps(type: :utc_datetime)
|
|
end
|
|
|
|
@required_fields ~w(observed_at lat lon)a
|
|
@optional_fields ~w(mean_reflectivity_dbz max_reflectivity_dbz texture_variance pixel_count)a
|
|
|
|
def changeset(observation, attrs) do
|
|
observation
|
|
|> cast(attrs, @required_fields ++ @optional_fields)
|
|
|> validate_required(@required_fields)
|
|
|> unique_constraint([:lat, :lon, :observed_at])
|
|
end
|
|
end
|