# {py:mod}`airsspy.volume_minsep_model`

```{py:module} airsspy.volume_minsep_model
```

```{autodoc2-docstring} airsspy.volume_minsep_model
:allowtitles:
```

## Module Contents

### Classes

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`FeatureBuilder <airsspy.volume_minsep_model.FeatureBuilder>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder
    :summary:
    ```
* - {py:obj}`BaselineRegressor <airsspy.volume_minsep_model.BaselineRegressor>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor
    :summary:
    ```
* - {py:obj}`BaselineFormulaPredictor <airsspy.volume_minsep_model.BaselineFormulaPredictor>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor
    :summary:
    ```
````

### Functions

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`split_name_for_formula <airsspy.volume_minsep_model.split_name_for_formula>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.split_name_for_formula
    :summary:
    ```
* - {py:obj}`fit_ridge_regressor <airsspy.volume_minsep_model.fit_ridge_regressor>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.fit_ridge_regressor
    :summary:
    ```
* - {py:obj}`evaluate_regressor <airsspy.volume_minsep_model.evaluate_regressor>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.evaluate_regressor
    :summary:
    ```
* - {py:obj}`train_baseline_regressor <airsspy.volume_minsep_model.train_baseline_regressor>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.train_baseline_regressor
    :summary:
    ```
* - {py:obj}`save_baseline_bundle <airsspy.volume_minsep_model.save_baseline_bundle>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.save_baseline_bundle
    :summary:
    ```
* - {py:obj}`load_baseline_bundle <airsspy.volume_minsep_model.load_baseline_bundle>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.load_baseline_bundle
    :summary:
    ```
* - {py:obj}`train_baseline_models <airsspy.volume_minsep_model.train_baseline_models>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.train_baseline_models
    :summary:
    ```
````

### Data

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`PROPERTY_NAMES <airsspy.volume_minsep_model.PROPERTY_NAMES>`
  - ```{autodoc2-docstring} airsspy.volume_minsep_model.PROPERTY_NAMES
    :summary:
    ```
````

### API

````{py:data} PROPERTY_NAMES
:canonical: airsspy.volume_minsep_model.PROPERTY_NAMES
:value: >
   ('Z', 'X', 'atomic_mass', 'atomic_radius', 'atomic_radius_calculated', 'metallic_radius', 'average_i...

```{autodoc2-docstring} airsspy.volume_minsep_model.PROPERTY_NAMES
```

````

`````{py:class} FeatureBuilder
:canonical: airsspy.volume_minsep_model.FeatureBuilder

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder
```

````{py:attribute} element_list
:canonical: airsspy.volume_minsep_model.FeatureBuilder.element_list
:type: tuple[str, ...]
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.element_list
```

````

````{py:method} __post_init__() -> None
:canonical: airsspy.volume_minsep_model.FeatureBuilder.__post_init__

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.__post_init__
```

````

````{py:method} from_formulas(formulas: collections.abc.Iterable[str]) -> airsspy.volume_minsep_model.FeatureBuilder
:canonical: airsspy.volume_minsep_model.FeatureBuilder.from_formulas
:classmethod:

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.from_formulas
```

````

````{py:property} formula_feature_names
:canonical: airsspy.volume_minsep_model.FeatureBuilder.formula_feature_names
:type: list[str]

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.formula_feature_names
```

````

````{py:property} pair_feature_names
:canonical: airsspy.volume_minsep_model.FeatureBuilder.pair_feature_names
:type: list[str]

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.pair_feature_names
```

````

````{py:method} formula_features(formula: str) -> numpy.ndarray
:canonical: airsspy.volume_minsep_model.FeatureBuilder.formula_features

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.formula_features
```

````

````{py:method} pair_features(formula: str, pair_key: str) -> numpy.ndarray
:canonical: airsspy.volume_minsep_model.FeatureBuilder.pair_features

```{autodoc2-docstring} airsspy.volume_minsep_model.FeatureBuilder.pair_features
```

````

`````

````{py:function} split_name_for_formula(formula: str, *, seed: int, train_ratio: float = 0.8, val_ratio: float = 0.1) -> str
:canonical: airsspy.volume_minsep_model.split_name_for_formula

```{autodoc2-docstring} airsspy.volume_minsep_model.split_name_for_formula
```
````

`````{py:class} BaselineRegressor
:canonical: airsspy.volume_minsep_model.BaselineRegressor

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor
```

````{py:attribute} alpha
:canonical: airsspy.volume_minsep_model.BaselineRegressor.alpha
:type: float
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.alpha
```

````

````{py:attribute} transform
:canonical: airsspy.volume_minsep_model.BaselineRegressor.transform
:type: str
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.transform
```

````

````{py:attribute} feature_mean
:canonical: airsspy.volume_minsep_model.BaselineRegressor.feature_mean
:type: numpy.ndarray
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.feature_mean
```

````

````{py:attribute} feature_scale
:canonical: airsspy.volume_minsep_model.BaselineRegressor.feature_scale
:type: numpy.ndarray
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.feature_scale
```

````

````{py:attribute} target_mean
:canonical: airsspy.volume_minsep_model.BaselineRegressor.target_mean
:type: float
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.target_mean
```

````

````{py:attribute} coefficients
:canonical: airsspy.volume_minsep_model.BaselineRegressor.coefficients
:type: numpy.ndarray
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.coefficients
```

````

````{py:attribute} intercept
:canonical: airsspy.volume_minsep_model.BaselineRegressor.intercept
:type: float
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.intercept
```

````

````{py:attribute} feature_names
:canonical: airsspy.volume_minsep_model.BaselineRegressor.feature_names
:type: list[str]
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.feature_names
```

````

````{py:method} predict_raw(features: numpy.ndarray) -> numpy.ndarray
:canonical: airsspy.volume_minsep_model.BaselineRegressor.predict_raw

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.predict_raw
```

````

````{py:method} predict(features: numpy.ndarray) -> numpy.ndarray
:canonical: airsspy.volume_minsep_model.BaselineRegressor.predict

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.predict
```

````

````{py:method} to_payload() -> dict
:canonical: airsspy.volume_minsep_model.BaselineRegressor.to_payload

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.to_payload
```

````

````{py:method} from_payload(payload: dict) -> airsspy.volume_minsep_model.BaselineRegressor
:canonical: airsspy.volume_minsep_model.BaselineRegressor.from_payload
:classmethod:

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineRegressor.from_payload
```

````

`````

````{py:function} fit_ridge_regressor(features: numpy.ndarray, targets: numpy.ndarray, *, alpha: float, feature_names: list[str], sample_weight: numpy.ndarray | None = None, transform: str = 'log') -> airsspy.volume_minsep_model.BaselineRegressor
:canonical: airsspy.volume_minsep_model.fit_ridge_regressor

```{autodoc2-docstring} airsspy.volume_minsep_model.fit_ridge_regressor
```
````

````{py:function} evaluate_regressor(model: airsspy.volume_minsep_model.BaselineRegressor, features: numpy.ndarray, targets: numpy.ndarray) -> dict[str, float]
:canonical: airsspy.volume_minsep_model.evaluate_regressor

```{autodoc2-docstring} airsspy.volume_minsep_model.evaluate_regressor
```
````

````{py:function} train_baseline_regressor(items: collections.abc.Sequence[airsspy.volume_minsep_data.VolumeAggregate] | collections.abc.Sequence[airsspy.volume_minsep_data.PairAggregate], *, feature_fn: collections.abc.Callable[[object], numpy.ndarray], target_fn: collections.abc.Callable[[object], float], weight_fn: collections.abc.Callable[[object], float], feature_names: list[str], seed: int, alpha_grid: collections.abc.Sequence[float], max_rows: int | None = None) -> tuple[airsspy.volume_minsep_model.BaselineRegressor, dict]
:canonical: airsspy.volume_minsep_model.train_baseline_regressor

```{autodoc2-docstring} airsspy.volume_minsep_model.train_baseline_regressor
```
````

````{py:function} save_baseline_bundle(output_dir: str | pathlib.Path, *, builder: airsspy.volume_minsep_model.FeatureBuilder, volume_model: airsspy.volume_minsep_model.BaselineRegressor, minsep_model: airsspy.volume_minsep_model.BaselineRegressor, metrics: dict, dataset_summary: dict) -> None
:canonical: airsspy.volume_minsep_model.save_baseline_bundle

```{autodoc2-docstring} airsspy.volume_minsep_model.save_baseline_bundle
```
````

````{py:function} load_baseline_bundle(path: str | pathlib.Path) -> tuple[airsspy.volume_minsep_model.FeatureBuilder, airsspy.volume_minsep_model.BaselineRegressor, airsspy.volume_minsep_model.BaselineRegressor, dict]
:canonical: airsspy.volume_minsep_model.load_baseline_bundle

```{autodoc2-docstring} airsspy.volume_minsep_model.load_baseline_bundle
```
````

````{py:function} train_baseline_models(*, dataset_path: str | pathlib.Path, output_dir: str | pathlib.Path, seed: int = 17, pair_min_count: int = 1, volume_alpha_grid: collections.abc.Sequence[float] = (1e-06, 0.0001, 0.01, 1.0, 100.0), minsep_alpha_grid: collections.abc.Sequence[float] = (1e-06, 0.0001, 0.01, 1.0, 100.0), max_volume_rows: int | None = None, max_pair_rows: int | None = None) -> dict
:canonical: airsspy.volume_minsep_model.train_baseline_models

```{autodoc2-docstring} airsspy.volume_minsep_model.train_baseline_models
```
````

`````{py:class} BaselineFormulaPredictor
:canonical: airsspy.volume_minsep_model.BaselineFormulaPredictor

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor
```

````{py:attribute} bundle_path
:canonical: airsspy.volume_minsep_model.BaselineFormulaPredictor.bundle_path
:type: str | pathlib.Path
:value: >
   None

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor.bundle_path
```

````

````{py:method} __post_init__() -> None
:canonical: airsspy.volume_minsep_model.BaselineFormulaPredictor.__post_init__

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor.__post_init__
```

````

````{py:method} predict(formula: str) -> dict
:canonical: airsspy.volume_minsep_model.BaselineFormulaPredictor.predict

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor.predict
```

````

````{py:method} predict_many(formulas: collections.abc.Sequence[str]) -> list[dict]
:canonical: airsspy.volume_minsep_model.BaselineFormulaPredictor.predict_many

```{autodoc2-docstring} airsspy.volume_minsep_model.BaselineFormulaPredictor.predict_many
```

````

`````