gistfile1.py

def pick_h(protein, fingerprint, loader, model=TWELM, full_param_grid = {'C': list(np.logspace(0, 5, 6)),
                               'h': [100, 200, 500, 1000]}):
    comps = [[protein, fingerprint]]

    loader = copy.deepcopy(loader)

    preprocess_fncs = []

    data = get_data(comps, loader, preprocess_fncs).values()[0][0][0]
    
    X = data['X_train']['data']
    y = data['Y_train']['data']

    X_test = data['X_valid']['data']
    y_test = data['Y_valid']['data']


    projector = RandomProjector()
    model = partial(model, projector=projector, random_state=666)

    grid = GridSearch(base_model_cls=model,
                      param_grid=full_param_grid,
                      seed=666,
                      score=wac_score)

    grid.fit(X, y)

    best_params = grid.best_params

    return best_params['h']