Multimodal item feature extraction for K-12 math assessment. Reads item text and images through one entry point, with math-aware normalization via textstat and NLTK. Measure readability, Common Core State Standards for Mathematics domain, cognitive load, and the relations carried by wording or by notation. Classify item images into visual types with an instructional role, read shape subtypes with OpenCV and Pillow, and extract text through Gemini and OpenAI vision APIs.
Installation
pip install mathipy
With optional dependencies:
pip install "mathipy[nlp]" # readability (textstat, nltk)
pip install "mathipy[vision]" # visual analysis (opencv, pillow)
pip install "mathipy[ocr]" # OCR via vision LLMs (httpx)
pip install "mathipy[documents]" # document parsing (python-docx, pdfplumber)
pip install "mathipy[all]" # all features
From GitHub:
pip install "mathipy[all] @ git+https://github.com/mshin77/mathipy.git"
Getting Started
See Quick Start and Analyzing Math Items for tutorials.
Citation
- Shin, M. (2026). mathipy: Multimodal item feature extraction for K-12 math assessment (Python package version 0.4.16) [Computer software]. https://github.com/mshin77/mathipy
1 maintainer
Metadata
1 maintainer
Release files for mathipy 0.4.16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mathipy-0.4.16.tar.gz | 75.6 kB | Without provenance | Details for mathipy-0.4.16.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mathipy-0.4.16-py3-none-any.whl | Python 3 | none | any | Details for mathipy-0.4.16-py3-none-any.whl |
Total release size: 157.4 kB
Release files / mathipy-0.4.16.tar.gz
| Download URL | mathipy-0.4.16.tar.gz |
|---|---|
| Size | 75.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bd58188d94501c83c16aaa58571093f588bf061ead54ea2c5eb66394d44dbd86
|
|
BLAKE2b-256 checksum How to use checksums |
3804caea1ca9822211725272038c0c02b34eb305a5a9017d7c968c96a202da78
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.6
|
Release files / mathipy-0.4.16-py3-none-any.whl
| Download URL | mathipy-0.4.16-py3-none-any.whl |
|---|---|
| Size | 81.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1521e53165d3fbd1b84a94a7b2a56ad96f40110cab171f94cb4d7c95b62d0bae
|
|
BLAKE2b-256 checksum How to use checksums |
3a37dc105a39b9533d1158e5b955f88a4b5a6de2a80445f5ab58834a6189b1a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.6
|
Security for mathipy 0.4.16
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
