https://github.com/jimfleming/numerai

Code from my experiments on Numerai
https://github.com/jimfleming/numerai

Last synced: about 1 year ago
JSON representation

Code from my experiments on Numerai

• Host: GitHub
• URL: https://github.com/jimfleming/numerai
• Owner: jimfleming
• License: mit
• Created: 2016-09-16T19:09:27.000Z (almost 10 years ago)
• Default Branch: master
• Last Pushed: 2018-10-03T21:49:25.000Z (almost 8 years ago)
• Last Synced: 2024-08-08T23:20:03.059Z (almost 2 years ago)
• Language: Jupyter Notebook
• Homepage: https://medium.com/@jimfleming/notes-on-the-numerai-ml-competition-14e3d42c19f3#.p3swptim4
• Size: 8.03 MB
• Stars: 287
• Watchers: 33
• Forks: 84
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Numerai Experiments

Folder structure:

- ensemble.py - combines multiple predictions using geometric mean

- fit_tsne.py - uses [this t-SNE implementation](https://github.com/danielfrg/tsne) for 2D embedding (does not work in 3D)

- search_params.py - uses `RandomSearchCV` for hyperparameter search

- tpot_test.py - runs [tpot](https://github.com/rhiever/tpot) over the data

- tpot_pipeline.py - best tpot model

- notebooks/ - contains Jupyter notebooks

- bh_tsne/ - is the original C++ t-SNE implementation with scripts for converting the csvs to the format the binary expects

- models/ - various model implementations

  - adverarial/ - generative adversarial model that saves the learned features for each sample

  - autoencoder/ - simple autoencoder with regular and denoising variants (also saves learned features)

  - classifier/ - simple neural network classifier

  - pairwise/ - pairwise model implementation described in the blog post

  - pipeline/ - various scikit-learn models

    - estimators.py - custom wrappers around `KernelPCA` and `Isomap` that fit on a small portion of the training samples to avoid memory errors

    - transformers.py - contains `ItemSelector` which allows for selecting data by a key when building pipelines ([source](http://scikit-learn.org/stable/auto_examples/hetero_feature_union.html))

    - fm.py - factorization machines

    - lr.py - logistic regression with t-SNE features

    - pairwise.py - sklearn variant of the pairwise model

    - simple.py - simple logistic regression with polynomial features