Giter Club home page Giter Club logo

herbarium_phenology's People

Contributors

rafelafrance avatar

Stargazers

 avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

herbarium_phenology's Issues

Image utilities are too slow

At the very least I can use multiprocessing. It is very likely that I can speed up other parts of the program.

Revisit using a multi-headed model or another multi-label technique

We have a multi-label problem with missing labels. I don't need the latest & greatest solution to the issue but I do want to create a single model for all of the traits. We want to gracefully handle missing labels in the data. If possible it would also be nice to add labels to an existing model.

Create a runs table

Track what, how, and when jobs are run.

See the example in the digi_leap repository.

Move splits into the images table

Splits need to follow the image so that a test image should always be a test image. The same logic for splitting the record applies, it just hitting a different table.

Try oversampling

Classes (positive/negative) are heavily imbalanced. I am currently using weighted classes. See if oversampling works better for our case.

Extract angiosperm order and family names from web pages

We need to filter the iDigBio information to only include angiosperm data (among other things). Two web pages have a fairly exhaustive list of this information along with some alternate names. Alternate names will be very helpful for older data because the names will change over time.

We need to write a script that will download the pages and then extract the data from them and write them to a text file that can be read programmatically. I'm OK with either CSV or JSON-lines output. Links to the pages:

We need to be able to run this script (or jupyter notebook) repeatedly... Or more accurately all of us need to be able to run this script to gather the information ourselves.

Note that I have had success using the BeautifulSoup4 python library. I just used it to parse a checklist for lice hosts.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.