# xinychen/transdim

Machine learning for transportation data imputation and prediction.

Repository: https://github.com/xinychen/transdim
Canonical: https://ross.abutalabs.com/products/transdim
Homepage: https://transdim.github.io
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-02-20T14:45:16+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 68, release rhythm 35, longevity 100
- inputs: {"age_days": 2896, "days_push": 194, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1289, forks 305 (observed 2026-08-28T04:04:15.329517+00:00)

## What it is
transdim is a Python/Jupyter Notebook project providing machine learning models for transportation data imputation and spatiotemporal time series prediction. It implements tensor learning models (e.g., low-rank autoregressive tensor completion) to handle various missing data patterns in traffic sensor data.

## Use cases
- impute missing traffic sensor data
- forecast road network traffic states
- handle missing values in time series forecasting
- low-rank tensor completion for spatiotemporal data
- benchmark missing data patterns like random and blockout missing
- learn tensor decomposition models for urban mobility data

## When to choose
- you need to impute missing spatiotemporal traffic data with well-studied missing patterns
- you want research-grade Python implementations of tensor completion and forecasting models
- you are working on time series prediction in the presence of missing values
- you need open transportation datasets and reproducible notebooks

## When to avoid
- you need a production-ready, pip-installable library with stable APIs
- your data is not spatiotemporal or traffic-related
- you need real-time or streaming imputation at scale
- you want a general-purpose time series forecasting toolkit without a missing-data focus

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, nlp
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: tensor-completion, time-series-forecasting, missing-data-imputation, spatiotemporal, traffic-data, jupyter-notebooks, research-code, transportation

## Member repositories
- xinychen/transdim (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.329517+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:55:46.933451+00:00, confidence not recorded.
  - readme: https://github.com/xinychen/transdim (fetched 2026-08-28T04:04:15.329517+00:00, sha 64523db51925)
  - homepage: https://transdim.github.io (fetched 2026-08-29T12:11:47.037787+00:00, sha 77919ce5bfa8)
- Data as of 2026-08-30T08:39:29.467469+00:00.