Skip to main content

Transforms categorical features into embedded vectors

Project description

Package transforms your categorical variables into embedded vectors. You should have tensorflow, pandas, numpy, keras and sklearn installed.

Attributes: model = EntityEmbedding(dataframe, features from the copy of the df, target column, column you want a vector for)

Hyperparameters you can optimize: model.train_fit(activation1='relu', activation2='relu', activation3='relu', loss='mean_squared_error', metrics='mape', dense_size_num=128, dense_size_conc_1=300, dense_size_conc_2=300, alpha=1e-3, epochs=1000, batch_size=512, verbose=1, patience=5)

Inside model.transform(), always provide embedded vector you want to use: model.transform(model.ent_emb)

model.visualize() returns 2 d visualization of your column categories.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

ent_embedding-0.0.1-py3-none-any.whl (2.5 kB view details)

Uploaded Python 3

File details

Details for the file ent_embedding-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: ent_embedding-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/32.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.62.3 importlib-metadata/4.10.1 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.10.2

File hashes

Hashes for ent_embedding-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b6d2e40113bf1693f6a2239879b51b9ff1fa2b343f65678bb85abbef5105f9cf
MD5 211c0acdf97b32f9d34671df087ac176
BLAKE2b-256 c6421e23ee248235473ca8703588c5cb1a1d8d6d45bb13c9f060d9601273ec71

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page