clarify grouping not part of arima currently in user docs
diff --git a/src/ports/postgres/modules/tsa/arima.sql_in b/src/ports/postgres/modules/tsa/arima.sql_in
index 48f0abd..12930a6 100644
--- a/src/ports/postgres/modules/tsa/arima.sql_in
+++ b/src/ports/postgres/modules/tsa/arima.sql_in
@@ -158,13 +158,17 @@
<DD>TEXT. The name of the column containing the time series data. This data is
currently restricted to DOUBLE PRECISION.</DD>
- <DT>grouping_columns (optional)</DT>
- <DD>TEXT, default: NULL. <em>Not currently implemented. Any non-NULL value is ignored.</em>
+ <DT>grouping_columns (not currently implemented)</DT>
+ <DD>TEXT, default: NULL.
A comma-separated list of column names used to group the input dataset
into discrete groups, training one ARIMA model per group. It is similar to
the SQL <tt>GROUP BY</tt> clause. When this value is null, no grouping is
- used and a single result model is generated.</DD>
+ used and a single result model is generated.
+
+ @note Grouping is not currently implemented for ARIMA, but
+ will be added in the future. Any non-NULL value for this parameter
+ is ignored.</em></DD>
<DT>include_mean (optional)</DT>
<DD>BOOLEAN, default: FALSE. Mean value of the data series is added in the ARIMA model