tensorflow / tensorflow/probability

tfp.sts.forcast only applies to future data. Is it possible to "predict" training data?

Open
#1,846 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

I am using the Structural Time Series of TensorFlow Probability.
I separated my data(1 year) into training data (10 months) and test data (2 months).

After building the model and forecasting, I wondered whether it is possible to "predict" the training data so that I can compare the performance of the model in the training data interval.
Since the arguments of "tfp.sts.forcast" can only specify "num_steps_forecast" which does not include that option, I would ask here.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with tfp.sts.forcast and the Structural Time Series forecasting material; determine whether its inputs support predictions over observed training timesteps rather than only future steps. Define the expected in-sample behavior and comparison output before deciding whether an API change or documentation is needed.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.