tgan.research.experiments module

Tune and evaluate TGAN models.

tgan.research.experiments.fit_score_model(name, model_kwargs, train_data, test_data, continuous_columns, sample_rows, store_samples)

Fit and score models using given params.

tgan.research.experiments.numpy_default(obj)

Change numpy objects into json-serializable ones.

tgan.research.experiments.prepare_hyperparameter_search(epoch, steps_per_epoch, num_random_search)

Prepare hyperparameters.

tgan.research.experiments.run_experiment(name, epoch, steps_per_epoch, sample_rows, train_csv, continuous_cols, num_random_search, store_samples=True, force=False)

Run experiment using the given params and collect the results.

The experiment run the following steps:

1. We fetch and split our data between test and train.

2. We first train a TGAN data synthesizer using the real training data T and generate a synthetic training dataset Tsynth.

3. We then train machine learning models on both the real and synthetic datasets.

4. We use these trained models on real test data and see how well they perform.

tgan.research.experiments.run_experiments(config_path, output_path)

Run experiments specified in JSON file.