From b8519f00d9c30a7726435aac6989455a7ba91afe Mon Sep 17 00:00:00 2001 From: Birte Kristina Friesel Date: Mon, 21 Oct 2024 08:06:02 +0200 Subject: README: document CSV loader variables --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 59bf214..248f9e9 100644 --- a/README.md +++ b/README.md @@ -155,6 +155,8 @@ The following variables may be set to alter the behaviour of dfatool components. | `DFATOOL_RMT_LOSS_IGNORE_SCALAR` | **0**, 1 | Ignore scalar parameters when computing the loss for split node candidates. Instead of computing the loss of a single partition for each `x_i == j`, compute the loss of partitions for `x_i == j` in which non-scalar parameters vary and scalar parameters are constant. This way, scalar parameters do not affect the decision about which non-scalar parameter to use for splitting. | | `DFATOOL_PARAM_CATEGORICAL_TO_SCALAR` | **0**, 1 | Some models (e.g. FOL, sklearn CART, XGBoost) do not support categorical parameters. Ignore them (0) or convert them to scalar indexes (1). Conversion uses lexical order. | | `DFATOOL_FOL_SECOND_ORDER` | **0**, 1 | Add second-order components (interaction of feature pairs) to first-order linear function. | +| `DFATOOL_CSV_IGNORE` | *str1,str2,...* | Ignore the listed fields when loading CSV log files. | +| `DFATOOL_CSV_OBSERVATIONS` | *str1,str2,...* | Treat the listed fields as observations rather than features. | ## Examples -- cgit v1.2.3