[FEAT] / [MORE PRIMITIVES] Geo Imputers from the literature / ML-powered ones are needed!

[simonprovost]

💡 Feature Request

Welcome to the OSMNxMapping feature request hub! 🎉

Hey there, before you jump in, take a quick sec to check out the
important stuff below—it’ll help us keep the magic flowing smoothly.

Important

Before you proceed, please confirm the following:

• I’ve checked the API docs and confirmed this feature doesn’t already exist (no duplicates, please!).
• I’ve scoured the existing issues to make sure this hasn’t been requested before.
• I get that feature requests are reviewed periodically and might take a little time—patience is key!

---

Describe the Feature Request

Currently, the preprocessing module's imputer submodule, consists of a default imputer that naively drops records of a dataset with missing longitude or latitude information, and a second that, based on a given passed column name of the data pertaining to something similar to "address" of the given record in the dataset, can geocode this using open street map, in order to impute a bit less naively the latitude and/or longitude columns with missing coordinate(s).

More are required; two are insufficient, especially because one is simply the default.

Describe Preferred Solution

1. From popular techniques in the literature. GIS-related.
2. Machine-learning-powered ones.
3. Let's innovate new techniques.

A new imputer simply needs to be inherited from https://github.com/VIDA-NYU/OSMNXMapping/blob/main/src/osmnx_mapping/modules/preprocessing/imputer/abc_imputer.py to be integrated within the OSMNxMapping workflow.

Describe Alternatives

N/A

Related Code

N/A

Additional Context

N/A

If the feature request is approved, would you be willing to submit a PR?

• Yes
• No

(No worries if you’re new to this—we’ll guide you every step of the way! 🤝)