LinearLagModel#

Linear-with-softplus lag-phase growth fitter (no saturation).

Parameters and usage: LinearLagModel.

  • One row per: fitted group (the groupby columns)

  • Written to: the frame analyze() returns; when it is the pipeline’s model, a CLI run writes deliverables/LinearLagModel.csv and .parquet

  • Columns: 11, each a pattern (see Placeholders)

Placeholders

Some column names depend on how you run the operation. They are shown as patterns, with these placeholders:

<metric>

The fitted column without its metric-family prefix: fitting Size_Area writes LinearLagModel_Area_v.

LINEAR_LAG_MODEL#

Metric family: LinearLagModel#

Column

Description

Type

Biology

LinearLagModel_<metric>_v

The post-lag phase growth rate.

Tier 1 · Direct phenotype

The post-lag phase growth rate using the target metric (usually radius)

LinearLagModel_<metric>_s0

The initial value of the target metric

Tier 1 · Direct phenotype

The initial size

LinearLagModel_<metric>_lambda

The duration of the lag phase

Tier 1 · Direct phenotype

LinearLagModel_<metric>_alpha

lag phase transition sharpness

Tier 2 · Descriptive trait

MODEL_METRICS#

Every growth model writes these columns; see Shared columns.

Metric family: ModelMetrics#

Column

Description

Type

ModelMetrics_<metric>_MAE

The mean absolute error

Quality

ModelMetrics_<metric>_MSE

The mean squared error

Quality

ModelMetrics_<metric>_RMSE

The root mean squared error

Quality

ModelMetrics_<metric>_R2

The coefficient of determination

Quality

ModelMetrics_<metric>_NumSamples

The number of samples used for model fitting

Quality

ModelMetrics_<metric>_OptimizerLoss

The loss of model fitting

Quality

ModelMetrics_<metric>_OptimizerStatus

The output of the optimizer status

Quality