Python sklearn.gaussian_process.kernels.WhiteKernel() Examples

def test_learning(self):
        """General testing for catkit.learn"""
        with FingerprintDB(data_path) as fp:
            X = fp.get_fingerprints(params=np.arange(20) + 1)
            y = fp.get_fingerprints(params=['Ef']).T[0]

        X0, X1, y0, y1 = train_test_split(X, y, test_size=0.6, shuffle=True)

        kernel = DotProduct() + WhiteKernel()
        gp = GaussianProcessRegressor(
            kernel=kernel, optimizer=optimizer,
            n_restarts_optimizer=0, alpha=0)
        gp.fit(X0, y0)

        # This is an ugly way to define default properties
        # The 3rd argument is for a certain number of global
        # optimization steps using the basinhopping algorithm
        optimizer.__defaults__ = (True, 'L-BFGS-B', 3)

        gp = GaussianProcessRegressor(
            kernel=kernel, optimizer=optimizer,
            n_restarts_optimizer=0, alpha=0)
        gp.fit(X0, y0)

        samples = online_learning(
            X, y, [0, 1, 2], factors=[1, 1], nsteps=3, plot=True)

        test_array = np.array([0, 1, 2, 24, 15, 23])
        np.testing.assert_allclose(samples, test_array) 

def test_gp_regression_learner():
    df_train = pd.DataFrame({
        'id': ["id1", "id2", "id3", "id4"],
        'x1': [10.0, 13.0, 10.0, 13.0],
        "x2": [0, 1, 1, 0],
        'y': [2.3, 4.0, 100.0, -3.9]
    })

    df_test = pd.DataFrame({
        'id': ["id4", "id4", "id5", "id6"],
        'x1': [12.0, 1000.0, -4.0, 0.0],
        "x2": [1, 1, 0, 1],
        'y': [1.3, -4.0, 0.0, 49]
    })

    from sklearn.gaussian_process.kernels import RBF, WhiteKernel, DotProduct

    kernel = RBF() + WhiteKernel() + DotProduct()

    learner = gp_regression_learner(features=["x1", "x2"],
                                    target="y",
                                    kernel=kernel,
                                    alpha=0.1,
                                    extra_variance="fit",
                                    return_std=True,
                                    extra_params=None,
                                    prediction_column="prediction")

    predict_fn, pred_train, log = learner(df_train)

    pred_test = predict_fn(df_test)

    expected_col_train = df_train.columns.tolist() + ["prediction", "prediction_std"]
    expected_col_test = df_test.columns.tolist() + ["prediction", "prediction_std"]

    assert Counter(expected_col_train) == Counter(pred_train.columns.tolist())
    assert Counter(expected_col_test) == Counter(pred_test.columns.tolist())
    assert (pred_test.columns == pred_train.columns).all()
    assert "prediction" in pred_test.columns 

def create_gaussian_process(self):
        '''
        Create the initial Gaussian process.
        '''
        if self.cost_has_noise:
            gp_kernel = skk.RBF(length_scale=self.length_scale) + skk.WhiteKernel(noise_level=self.noise_level)
        else:
            gp_kernel = skk.RBF(length_scale=self.length_scale)
        if self.update_hyperparameters:
            self.gaussian_process = skg.GaussianProcessRegressor(kernel=gp_kernel,n_restarts_optimizer=self.hyperparameter_searches)
        else:
            self.gaussian_process = skg.GaussianProcessRegressor(kernel=gp_kernel,optimizer=None) 

def gaussian_emulator(locator, config):
    """
    Thi is a Gaussian process linear emulator. It is used to create a surrogate model of CEA whose
    output is either rmse or cvrmse

    for more details on the work behind this please check:
    Rysanek A., Fonseca A., Schlueter, A. Bayesian calibration of Dyanmic building Energy Models. Applied Energy 2017.

    :param locator: pointer to location of CEA files
    :param samples: matrix m x n with samples simulated from CEA. m are the number of input variables [0,1]
    :param cv_rmse: array with results of cv_rmse after running n samples.
    :param building_name: name of building whose calibration process is being acted upon
    :return:
           file with database of emulator stored in locator.get_calibration_cvrmse_file(building_name)

    """
    # INITIALIZE TIMER
    t0 = time.clock()

    # Local variables
    building_name = config.single_calibration.building
    building_load = config.single_calibration.load
    with open(locator.get_calibration_problem(building_name, building_load),'r') as input_file:
        problem = pickle.load(input_file)
    samples_norm = problem["samples_norm"]
    target = problem["cv_rmse"]

    # Kernel with parameters given in GPML book for the gaussian surrogate models. The hyperparameters are optimized so you can get anything here.
    k1 = 5**2 * RBF(length_scale=1e-5)  # long term smooth rising trend RBF: radio basis functions (you can have many, this is one).
    k2 = 5**2 * RBF(length_scale=0.000415) * ExpSineSquared(length_scale=3.51e-5, periodicity=0.000199)  # seasonal component
    # medium term irregularity
    k3 = 316**2 * RationalQuadratic(length_scale=3.54, alpha=1e+05)
    k4 = 316**2 * RBF(length_scale=4.82) + WhiteKernel(noise_level=0.43)  # noise terms
    kernel = k1 + k2 + k3 + k4

    # give the data to the regressor.
    gp = GaussianProcessRegressor(kernel=kernel, alpha=1e-7, normalize_y=True, n_restarts_optimizer=2)
    gp.fit(samples_norm, target) # then fit the gp to your observations and the minmax. It takes 30 min - 1 h.

    # this is the result
    joblib.dump(gp, locator.get_calibration_gaussian_emulator(building_name, building_load))

    time_elapsed = time.clock() - t0
    print('done - time elapsed: %d.2f seconds' % time_elapsed) 

def online_learning(X, y, samples, factors=[1.0, 1.0], nsteps=40, plot=False):
    """A simple utility for performing online learning. The main
    components required are a regression method and a scoring
    technique.

    Currently, the scoring methodology and regressor are baked in.
    These need to be made modular.

    Minimum 3 samples are required for 3 fold cross validation.
    """
    ids = np.arange(len(y))

    kernel = DotProduct() + WhiteKernel()
    regressor = GaussianProcessRegressor(
        kernel=kernel, n_restarts_optimizer=5, alpha=0)

    step = 0
    while step < nsteps:
        X0 = X[samples]
        y0 = y[samples]

        regressor.fit(X0, y0)
        yp, ys = regressor.predict(X, return_std=True)

        # Provides some form of normalization.
        # Multiples denote relative importance
        yp_scale = preprocessing.scale(yp) * factors[0]
        ys_scale = preprocessing.scale(ys) * factors[1]
        score = ys_scale - yp_scale
        srt = np.argsort(score)[::-1]

        for s in srt:
            if s not in samples:
                samples = np.concatenate([samples, [s]])
                break

        if plot:
            mae = np.round(mean_absolute_error(yp, y), 3)
            n = len(samples)

            fig, ax = plt.subplots(figsize=(6, 4))
            ax.plot(ids, y, 'o', zorder=0)
            ax.errorbar(ids, yp, yerr=ys, fmt='o', zorder=1)
            ax.plot(samples, y[samples], 'o', zorder=3)
            xlim = ax.get_xlim()
            ylim = ax.get_ylim()
            ax.text(xlim[0] / 9.0, ylim[0] / 9.0, mae)
            plt.tight_layout()
            plt.savefig('./online-learning-RBF-{}.png'.format(n))
            plt.close()

        step += 1

    return samples