# `Dsxir.EvaluationResult`

Result of a single `Dsxir.Evaluate.run/2` invocation.

  * `:score` — `avg(metric_value) * 100`, rounded to 1 decimal place.
  * `:results` — one row per devset entry, in input order. Successful rows
    carry `metric: float()`; errored rows carry `metric: nil, error: %Exception{}`.
  * `:errors` — `%{count: non_neg_integer(), by_class: %{atom() => non_neg_integer()}}`.
    `:by_class` keys are the splode error class atoms (`:adapter`, `:lm`,
    `:invalid`, `:halted`, `:framework`, `:unknown`).

Subscribers branch on `nil` vs. populated; the `:errors` map is always
present, even when zero errors occurred (then `count: 0, by_class: %{}`).

# `row`

```elixir
@type row() :: %{
  example: Dsxir.Example.t(),
  prediction: nil | Dsxir.Prediction.t(),
  metric: nil | float(),
  error: nil | Exception.t()
}
```

# `t`

```elixir
@type t() :: %Dsxir.EvaluationResult{
  errors: %{
    count: non_neg_integer(),
    by_class: %{required(atom()) => non_neg_integer()}
  },
  results: [row()],
  score: float()
}
```

# `error_row`

```elixir
@spec error_row(Dsxir.Example.t(), Exception.t()) :: row()
```

Build an errored row, attaching the caught exception in place of a prediction.

# `ok_row`

```elixir
@spec ok_row(Dsxir.Example.t(), Dsxir.Prediction.t(), float()) :: row()
```

Build a successful row with its example, prediction, and numeric metric.

# `score_from`

```elixir
@spec score_from([float()]) :: float()
```

Aggregate `values` into a 0..100 score by averaging and scaling, rounded to
one decimal place. An empty list returns `0.0`.

---

*Consult [api-reference.md](api-reference.md) for complete listing*