Skip to content

Used SciPyWrapper for AreWeThereYet notebook#1

Merged
fjhickernell merged 8 commits into
mainfrom
ishaan-are-we-there-yet
Jul 22, 2026
Merged

Used SciPyWrapper for AreWeThereYet notebook#1
fjhickernell merged 8 commits into
mainfrom
ishaan-are-we-there-yet

Conversation

@ishn29

@ishn29 ishn29 commented May 11, 2026

Copy link
Copy Markdown
Collaborator

Changed the notebook to route both IID and LD sampling through SciPyWrapper. The notebook now declares the wait time marginals once and lets SciPyWrapper handle the unit square to distribution transform instead of manually calling each marginal's ppf on Sobol coordinates.

Had to use a PPF only adapter for W2 because the taxi wait time has a zero inflated distribution. There is a chance the wait is exactly zero, and otherwise the wait follows an exponential distribution. For this notebook, we only need the PPF to turn uniform samples into taxi wait times. The PDF method is not needed and caused problems because W2 is not a regular continuous distribution.

Kept make_zie for W2 instead of QMCPy ZeroInflatedExpUniform because the notebook model needs two separate independent waiting times: W1 for the train wait and W2 for the taxi wait. make_zie gives only the taxi wait distribution, while ZeroInflatedExpUniform is already a full 2D joint true measure. That joint model does not match this notebook's setup as directly.

Changed the notebook to route both IID and LD sampling through SciPyWrapper. The notebook now
declares the wait time marginals once and lets SciPyWrapper handle the unit square to distribution transform instead of manually calling each
marginal's ppf on Sobol coordinates.

Had to use a PPF only adapter for W2 because the taxi wait time has a zero inflated distribution. There is a chance the wait is exactly zero, and otherwise the wait follows an exponential distribution. For this notebook, we only need the PPF to turn uniform samples into taxi wait times. The PDF method is not needed and caused problems because W2 is not a regular continuous distribution.

Kept make_zie for W2 instead of QMCPy ZeroInflatedExpUniform because the notebook model needs two separate independent waiting times: W1 for the train wait and W2 for the taxi wait. make_zie gives only the taxi wait distribution, while ZeroInflatedExpUniform is already a full 2D joint true measure. That joint model does not match this notebook's setup as directly.
@ishn29
ishn29 requested a review from fjhickernell May 11, 2026 00:31
@ishn29 ishn29 closed this Jun 24, 2026
@ishn29 ishn29 reopened this Jun 24, 2026
@fjhickernell

Copy link
Copy Markdown
Member

@copilot resolve the merge conflicts in this pull request

A student submitted a pull request to MATH565Fall2025 that changes a notebook. The PR cannot be merged because the qmcsoftware submodule pointer conflicts with the current base branch.

Please resolve this locally and update the student's PR branch.

Requirements:

  1. Inspect the repository status, remotes, current base branch, PR branch, and PR file changes before modifying anything.
  2. Confirm that the student's intended work is in the notebook and that the qmcsoftware change is only an outdated or accidental submodule pointer.
  3. Fetch the latest remote branches.
  4. Check out the student's PR branch locally.
  5. Merge the current remote base branch into the student's branch.
  6. Resolve the qmcsoftware conflict by retaining the exact submodule pointer recorded by the current remote base branch. Do not merge or modify files inside the QMCSoftware repository, and do not advance QMCSoftware to its latest develop commit.
  7. Preserve all of the student's legitimate notebook changes.
  8. Initialize/update submodules to the resolved recorded commits.
  9. Show me:
    • the conflicting commits before resolution,
    • the resolved qmcsoftware gitlink SHA,
    • git status,
    • the final diff against the base branch,
    • and a concise explanation of what will be committed.
  10. Check that the final PR diff contains the intended notebook changes and no unintended submodule-pointer change.
  11. Do not commit or push until I review the proposed resolution.

@fjhickernell

Copy link
Copy Markdown
Member

@copilot resolve the merge conflicts in this pull request

Copilot AI commented Jul 22, 2026

Copy link
Copy Markdown
Contributor

@copilot resolve the merge conflicts in this pull request

A student submitted a pull request to MATH565Fall2025 that changes a notebook. The PR cannot be merged because the qmcsoftware submodule ...

Here is the full proposed resolution — nothing has been committed or pushed yet.


1. Conflicting commits before resolution

Side Commit qmcsoftware pointer
Our branch (ishaan-are-we-there-yet) HEAD d818f3a — "Update submodule pointers (classlib 060d78b63164, qmcsoftware 13c665c40deb, tests na)" 13c665c40deb37465899d49587db32b646be40aa
origin/main HEAD f8fdc19 — "Add course problem reporting workflow" 9eb475177d114bf94a6c15b70bd01d186df641b5

The branch's earlier merge (c33f43b) brought in main up to 6afc240, but main then moved forward through a5dc851 → a942012 → a842f5a → f8fdc19, each updating submodule pointers. Our branch also received an extra "Update submodule pointers" commit (d818f3a) that advanced qmcsoftware to 13c665c — a newer, unintended commit.


2. Resolved qmcsoftware gitlink SHA

9eb475177d114bf94a6c15b70bd01d186df641b5   ← taken from origin/main

The staged index already records this SHA. The conflicting 13c665c40deb from our branch is discarded entirely. No files inside the QMCSoftware repo were touched.


3. git status (merge in progress, all conflicts resolved)

On branch ishaan-are-we-there-yet
All conflicts fixed but you are still merging.
  (use "git commit" to conclude merge)

Changes to be committed:
    new file:   .github/ISSUE_TEMPLATE/course-material-problem.yml
    modified:   README.md
    modified:   _data/navigation.yaml
    modified:   index.md
    new file:   pages/report-a-problem.md
    modified:   qmcsoftware

(The five non-submodule files above come entirely from origin/main's "Add course problem reporting workflow" commit and are simply being merged in — the student did not touch them.)


4. Final diff of this PR branch against origin/main

After the merge commit, git diff --cached origin/main --name-status shows:

A    notebooks/AreWeThereYetSciPyWrapper.ipynb

That is the only change. The qmcsoftware line produces an empty diff — the resolved pointer matches origin/main exactly.


5. What will be committed

A single merge commit that:

  • Brings in origin/main's "Add course problem reporting workflow" changes (new issue template, README/nav/index updates).
  • Sets qmcsoftware to 9eb475177d11 — exactly what origin/main records.
  • Retains the student's notebooks/AreWeThereYetSciPyWrapper.ipynb unchanged.

The notebook is confirmed to contain the intended SciPyWrapper work: it imports SciPyWrapper from qmcpy.true_measure and uses it consistently for IID sampling, replicated IID sampling, sigma estimation, and LD sampling — all the notebook content from the original PR.


Awaiting your approval to commit and push.

@fjhickernell
fjhickernell merged commit d3c42b4 into main Jul 22, 2026
1 check failed
@fjhickernell
fjhickernell deleted the ishaan-are-we-there-yet branch July 22, 2026 13:39
Copilot stopped work on behalf of fjhickernell due to an error July 22, 2026 13:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants