Get a well's stored predictions beside its actuals
The build's stored prediction for an existing well beside its actuals, per stream: predicted (the pre-refit train fit's cumulative at each ip_day), actual and ape, |predicted − actual| / actual (null without an actual above 0).
Get a well's stored predictions beside its actuals
/wells/{key}/predictionsThe build's stored prediction for an existing well beside its actuals, per stream: predicted (the pre-refit train fit's cumulative at each ip_day), actual and ape, |predicted − actual| / actual (null without an actual above 0).
Split
holdout: the train fit never saw the well. train: in-sample (in_sample: true), so its error reads about twice as good; hide these by default. A stream without a stored prediction has split: null and a reason saying whether the build stored none for it or the dataset lacks that split's predictions.
Caching
Dataset-derived: cached, with an ETag.
Parameters
Path parameters
keystringRequiredWellbore key, as SB329-01414. GET /wells/facets, /wells/search, /wells/typecurve and /wells/production are paths, not wells: keys are API numbers or SBnnn-nnnnn, so no well is shadowed.
Query parameters
model_setstringOptionalpattern ^[a-z0-9][a-z0-9-]{0,62}$
The model set to answer from, an
idfrom GET /model-sets. Absent: the set GET /model-sets names asdefault, the base dataset unless the server answers from a published set.model_set=defaultreaches the base dataset; once the server retires it, a 400 naming the set answering instead.- An unknown id, or a set scoped to other tenants, is a 400 listing the ids the caller may use in
details.allowed(published sets only oncedefaultis retired); a set that can't load, a 503 with the reason. - Plans and exports stay in their set: a call naming them (by path,
plan,ids,source.plan, a scenario'splan.id, or a comparison'sa.planandb.plan, also undersource.comparison) reaches it withoutmodel_set. - An explicit
model_setwins; naming resources of two sets in one request is a 400.
Responses
200 OK
The well's predictions per stream.
wellbore_keystringRequiredWellbore key.
sample_databooleanRequiredTrue when the figures come from synthetic sample data.
streamsobjectRequiredPer stream. Only the streams the model set serves (GET /model-sets
streams): a set serving gas alone answers gas alone.ShowHide 3 child fields
oilobjectOptionalOne stream's stored predictions for the well, or why there are none.
ShowHide 2 variants
One of
Predictions object
Predictions.
model_numstringRequiredModel number.
fitstringRequiredThe fit predicted with.
"train"splitstringRequiredholdout: the train fit never saw the well; train: it trained on it.
"holdout""train"in_samplebooleanRequiredTrue for a training well: its error reads better than held-out.
unitstringRequiredVolume unit.
"bbl""mcf"ip_daysarray of integersRequiredip_days, ascending.
predictedarray of numbersRequiredOne per ip_day.
actualarray of numbersRequiredOne per ip_day.
apearray of numbersRequiredOne per ip_day.
No predictions object
No predictions.
model_numstringRequiredModel number.
fitstringRequiredThe fit.
"train"splitanyRequiredNone.
reasonstringRequiredWhy there are none.
gasobjectOptionalOne stream's stored predictions for the well, or why there are none.
Same fields as WellStreamPredictions.
waterobjectOptionalOne stream's stored predictions for the well, or why there are none.
Same fields as WellStreamPredictions.
304 Unchanged since the ETag in If-None-Match.Errors
| Status | When |
|---|---|
| 404 | No such well, grid, plan or route. |
Shared errors400401403500503What they mean