Transition Matrix and Prediction Scripts #3901
Open
ananyak534 wants to merge 3 commits into
Open
Conversation
mdietze
reviewed
Apr 3, 2026
| if (k == 0) { | ||
| p = rep(0, nrow(tmat)); names(p) = rownames(tmat); p[cur] = 1 | ||
| } else { | ||
| p = predict_k_steps(tmat, cur, k) |
Member
There was a problem hiding this comment.
I'd recommend that you rethink what you're doing here to make the predictions iteratively (use the last prediction as the input to the next prediction) rather than repeating the prediction from 0 to k each time k increases by 1
| start_info[, CLASS := trimws(as.character(CLASS))] | ||
| states = rownames(tmat_final) | ||
|
|
||
| ##all predictions |
Member
There was a problem hiding this comment.
What's the relationship between "predictions_with_tmatrix.R" and the code in this file? It doesn't look like you're using those functions here. I'd recommend either using those functions or converting the core of this code into a function, and then have the script here focus on reading specific data, calling the prediction function, and then performing the validation. Indeed, such a script might be better reformatted as a Rmd vignette.
dlebauer
pushed a commit
to ashiklom/pecan
that referenced
this pull request
Apr 22, 2026
Two bugs found in the PEcAn.uncertainty module: 1. run.sensitivity.analysis.R: if (!pfts %in% ...) uses a vector-valued condition, which triggers an error in R >= 4.x when more than one PFT name is supplied. Wrapping with �ny() makes the intent explicit and avoids the multi-element condition warning/error. 2. get.results.R: The logger.warn call for the sensitivity analysis loop appended a literal ')' to the variable name string, producing spurious output such as 'Currently performing sensitivity analysis on variable NPP)'. Removed the stray closing parenthesis. Refs: PecanProject#3901
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull request for my script that generates a transition matrix on crop classes for the 2018-2023 data. The second file, 'predict_and_store.R', uses the matrix to predict crop classes up until a given year for one of the four seasons.
What this does
Key parts
Outputs
Notes
Transition step is slow, so the results and files are saved and reused
this uses simplified Markov behavior where next state depends only on current
How to run
Run 'transition_matrix.R' once to generate CSVs (but it will take a bit of time ~20 minutes)
run 'predict_and_store.R' using saved files --> can update season_idx and end_year values to modify predictions