models.linear
Linear regression by least squares on a table of any size: one streaming pass accumulates the QR factor of the weighted design, a second computes the residual statistics, so memory does not depend on the number of rows (20 million rows fit in about 50 MB). It fits the model stats.lm fits -- the same design columns, coefficients, covariance and statistics, tested to agree to 1e-9 -- and writes the same linear model for models.predict.
Formulas follow R's rules for expansion, ordering and coding of categoricals. Nesting (/, %in%) and cross-validation are not offered; use stats.lm for tables that fit in memory and need them. A collinear design fails, naming the column, rather than dropping it.
- Kind:
standard - Network: no
Inputs🔗
| Name | Type | Description |
|---|---|---|
data | file (Parquet or CSV) | Training table: one row per observation, with the target, the predictor columns, and any weights or id columns. |
formula | string | Model formula, e.g. ESTIMATE ~ B5 + log(B25) + FORTYPE + 0. Use instead of target and features. Default empty. |
target | string | The response column (when no formula is given). Default empty. |
features | string | Column selector for the predictors (when no formula is given): names, globs and exclusions, e.g. B*,MB*,-B0. Default empty. |
intercept | boolean | Include an intercept when building the model from target and features. With a formula, write + 0 in the formula instead. Default true. |
id_columns | string | Column selector for identifier columns, never used as predictors; kept as text when reading CSV. Default empty. |
weights | string | Column of non-negative observation weights. Empty fits unweighted. |
categorical | string | Column selector for predictors to treat as categorical even though they are stored as numbers. Default empty. |
na_action | string | fail (default, naming the columns) or drop: what to do with a row that has a missing value in a model column. |
Outputs🔗
| Name | Type | Description |
|---|---|---|
model | file (SpadeModel) | The fitted model (family linear), for models.predict. |
coefficients | file (CSV) | One row per design column: term, estimate, std_error, statistic, p_value. |
fit | json | Rows used and dropped, the arguments that shaped the fit, and metrics: rmse, mae, r_squared, adj_r_squared, aic, bic, sigma, df_residual. |
Example🔗
- id: "@fit"
name: models.linear
inputs:
- "@pixels"
args:
target: "biomass"
features: "B*,MB*"