ensembleset 1.0a11

Dataset generator utility for data science projects

Ensembleset

Ensemblesets generates dataset ensembles by applying a randomized sequence of feature engineering methods to a randomized subset of input features.

1. Installation

Install the pre-release alpha from PyPI with:

pip install ensembleset

2. Usage

See the example usage notebook.

Initialize an ensembleset class instance, passing in the label name a training DataFrame. Optionally, include a test DataFrame and/or list of any string features. Then call the make_datasets() to generate an ensembleset, specifying:

1. The number of individual datasets to generate.
2. The number of feature to randomly select for each feature engineering step.
3. The number of feature engineering steps to run.

import ensembleset.dataset as ds

data_ensemble=ds.DataSet(
    label='label_column_name',
    train_data=train_df,
    test_data=test_df
    string_features=['string_feature_column_names']
)

data_ensemble.make_datasets(
    n_datasets=10,
    n_features=7,
    n_steps=5
)

By default, generated datasets will be saved to HDF5 in data/dataset.h5 using the following structure:

dataset.h5
├──train
│   ├── labels
|   ├── 1
|   ├── .
|   ├── .
|   ├── .
|   └── n
│
└──test
    ├── labels
    ├── 1
    ├── .
    ├── .
    ├── .
    └── n