Python symfit.Fit类代码示例

    def test_known_solution(self):
        p, c1 = parameters('p, c1')
        y, t = variables('y, t')
        p.value = 3.0

        model_dict = {
            D(y, t): - p * y,
        }

        # Lets say we know the exact solution to this problem
        sol = Model({y: exp(- p * t)})

        # Generate some data
        tdata = np.linspace(0, 3, 10001)
        ydata = sol(t=tdata, p=3.22)[0]
        ydata += np.random.normal(0, 0.005, ydata.shape)

        ode_model = ODEModel(model_dict, initial={t: 0.0, y: ydata[0]})
        fit = Fit(ode_model, t=tdata, y=ydata)
        ode_result = fit.execute()

        c1.value = ydata[0]
        fit = Fit(sol, t=tdata, y=ydata)
        fit_result = fit.execute()

        self.assertAlmostEqual(ode_result.value(p) / fit_result.value(p), 1, 2)
        self.assertAlmostEqual(ode_result.r_squared / fit_result.r_squared, 1, 4)
        self.assertAlmostEqual(ode_result.stdev(p) / fit_result.stdev(p), 1, 3)

    def test_full_eval_range(self):
        """
        Test if ODEModels can be evaluated at t < t_initial.

        A bit of a no news is good news test.
        """
        tdata = np.array([0, 10, 26, 44, 70, 120])
        adata = 10e-4 * np.array([54, 44, 34, 27, 20, 14])
        a, b, t = variables('a, b, t')
        k, a0 = parameters('k, a0')
        k.value = 0.01
        t0 = tdata[2]
        a0 = adata[2]
        b0 = 0.02729855 # Obtained from evaluating from t=0.

        model_dict = {
            D(a, t): - k * a**2,
            D(b, t): k * a**2,
        }

        ode_model = ODEModel(model_dict, initial={t: t0, a: a0, b: b0})

        fit = Fit(ode_model, t=tdata, a=adata, b=None)
        ode_result = fit.execute()
        self.assertGreater(ode_result.r_squared, 0.95, 4)

        # Now start from a timepoint that is not in the t-array such that it
        # triggers another pathway to be taken in integrating it.
        # Again, no news is good news.
        ode_model = ODEModel(model_dict, initial={t: t0 + 1e-5, a: a0, b: b0})

        fit = Fit(ode_model, t=tdata, a=adata, b=None)
        ode_result = fit.execute()
        self.assertGreater(ode_result.r_squared, 0.95, 4)

    def test_likelihood_fitting_exponential(self):
        """
        Fit using the likelihood method.
        """
        b = Parameter(value=4, min=3.0)
        x, y = variables('x, y')
        pdf = {y: Exp(x, 1/b)}

        # Draw points from an Exp(5) exponential distribution.
        np.random.seed(100)
        xdata = np.random.exponential(5, 1000000)

        # Expected parameter values
        mean = np.mean(xdata)
        stdev = np.std(xdata)
        mean_stdev = stdev / np.sqrt(len(xdata))

        with self.assertRaises(NotImplementedError):
            fit = Fit(pdf, x=xdata, sigma_y=2.0, objective=LogLikelihood)
        fit = Fit(pdf, xdata, objective=LogLikelihood)
        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(b) / mean, 1, 3)
        self.assertAlmostEqual(fit_result.value(b) / stdev, 1, 3)
        self.assertAlmostEqual(fit_result.stdev(b) / mean_stdev, 1, 3)

    def test_chained_min_signature(self):
        """
        Test the automatic generation of the signature for ChainedMinimizer
        """
        minimizers = [
            BFGS, DifferentialEvolution, BFGS, DifferentialEvolution, BFGS
        ]

        fit = Fit(self.model, self.xx, self.yy, self.ydata,
                  minimizer=minimizers)

        names = [
            'BFGS', 'DifferentialEvolution', 'BFGS_2',
            'DifferentialEvolution_2', 'BFGS_3'
        ]
        for name, param_name in zip(names, fit.minimizer.__signature__.parameters):
            self.assertEqual(name, param_name)
        # Check for equal lengths because zip is slippery that way
        self.assertEqual(len(names), len(fit.minimizer.__signature__.parameters))

        for param in fit.minimizer.__signature__.parameters.values():
            self.assertEqual(param.kind, inspect_sig.Parameter.KEYWORD_ONLY)
        # Make sure keywords end up at the right minimizer.
        with self.assertRaises(TypeError):
            # This is not a valid kwarg to DiffEvo, but it is to BFGS. Check if
            # we really go by name of the Minimizer, not by order.
            fit.execute(DifferentialEvolution={'return_all': False})

    def test_vector_fitting(self):
        """
        Tests fitting to a 3 component vector valued function, without bounds
        or guesses.
        """
        a, b, c = parameters('a, b, c')
        a_i, b_i, c_i = variables('a_i, b_i, c_i')

        model = {a_i: a, b_i: b, c_i: c}

        xdata = np.array([
            [10.1, 9., 10.5, 11.2, 9.5, 9.6, 10.],
            [102.1, 101., 100.4, 100.8, 99.2, 100., 100.8],
            [71.6, 73.2, 69.5, 70.2, 70.8, 70.6, 70.1],
        ])

        fit = Fit(
            model=model,
            a_i=xdata[0],
            b_i=xdata[1],
            c_i=xdata[2],
            minimizer = MINPACK
        )
        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(a) / 9.985691, 1.0, 5)
        self.assertAlmostEqual(fit_result.value(b) / 1.006143e+02, 1.0, 4)
        self.assertAlmostEqual(fit_result.value(c) / 7.085713e+01, 1.0, 5)

    def test_vector_fitting_bounds(self):
        """
        Tests fitting to a 3 component vector valued function, with bounds.
        """
        a, b, c = parameters('a, b, c')
        a.min = 0
        a.max = 25
        b.min = 0
        b.max = 500
        a_i, b_i, c_i = variables('a_i, b_i, c_i')

        model = {a_i: a, b_i: b, c_i: c}

        xdata = np.array([
            [10.1, 9., 10.5, 11.2, 9.5, 9.6, 10.],
            [102.1, 101., 100.4, 100.8, 99.2, 100., 100.8],
            [71.6, 73.2, 69.5, 70.2, 70.8, 70.6, 70.1],
        ])

        fit = Fit(
            model=model,
            a_i=xdata[0],
            b_i=xdata[1],
            c_i=xdata[2],
        )
        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(a), np.mean(xdata[0]), 4)
        self.assertAlmostEqual(fit_result.value(b), np.mean(xdata[1]), 4)
        self.assertAlmostEqual(fit_result.value(c), np.mean(xdata[2]), 4)

    def test_fitting(self):
        """
        Tests fitting with NumericalLeastSquares. Makes sure that the resulting
        objects and values are of the right type, and that the fit_result does
        not have unexpected members.
        """
        xdata = np.linspace(1, 10, 10)
        ydata = 3*xdata**2

        a = Parameter()  # 3.1, min=2.5, max=3.5
        b = Parameter()
        x = Variable()
        new = a*x**b

        fit = Fit(new, xdata, ydata, minimizer=MINPACK)

        fit_result = fit.execute()
        self.assertIsInstance(fit_result, FitResults)
        self.assertAlmostEqual(fit_result.value(a), 3.0)
        self.assertAlmostEqual(fit_result.value(b), 2.0)

        self.assertIsInstance(fit_result.stdev(a), float)
        self.assertIsInstance(fit_result.stdev(b), float)

        self.assertIsInstance(fit_result.r_squared, float)
        self.assertEqual(fit_result.r_squared, 1.0)  # by definition since there's no fuzzyness

    def test_likelihood_fitting_gaussian(self):
        """
        Fit using the likelihood method.
        """
        mu, sig = parameters('mu, sig')
        sig.min = 0.01
        sig.value = 3.0
        mu.value = 50.
        x = Variable()
        pdf = Gaussian(x, mu, sig)

        np.random.seed(10)
        xdata = np.random.normal(51., 3.5, 10000)

        # Expected parameter values
        mean = np.mean(xdata)
        stdev = np.std(xdata)
        mean_stdev = stdev/np.sqrt(len(xdata))

        fit = Fit(pdf, xdata, objective=LogLikelihood)
        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(mu) / mean, 1, 6)
        self.assertAlmostEqual(fit_result.stdev(mu) / mean_stdev, 1, 3)
        self.assertAlmostEqual(fit_result.value(sig) / np.std(xdata), 1, 6)

    def test_gaussian_fitting(self):
        """
        Tests fitting to a gaussian function and fit_result.params unpacking.
        """
        xdata = 2*np.random.rand(10000) - 1  # random betwen [-1, 1]
        ydata = 5.0 * scipy.stats.norm.pdf(xdata, loc=0.0, scale=1.0)

        x0 = Parameter()
        sig = Parameter()
        A = Parameter()
        x = Variable()
        g = A * Gaussian(x, x0, sig)

        fit = Fit(g, xdata, ydata)
        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(A), 5.0)
        self.assertAlmostEqual(np.abs(fit_result.value(sig)), 1.0)
        self.assertAlmostEqual(fit_result.value(x0), 0.0)
        # raise Exception([i for i in fit_result.params])
        sexy = g(x=2.0, **fit_result.params)
        ugly = g(
            x=2.0,
            x0=fit_result.value(x0),
            A=fit_result.value(A),
            sig=fit_result.value(sig),
        )
        self.assertEqual(sexy, ugly)

    def test_fitting(self):
        xdata = np.linspace(1,10,10)
        ydata = 3*xdata**2

        a = Parameter() #3.1, min=2.5, max=3.5
        b = Parameter()
        x = Variable()
        new = a*x**b

        fit = Fit(new, xdata, ydata, minimizer=MINPACK)
        fit_result = fit.execute()
        self.assertIsInstance(fit_result, FitResults)
        self.assertAlmostEqual(fit_result.value(a), 3.0)
        self.assertAlmostEqual(fit_result.value(b), 2.0)

        self.assertIsInstance(fit_result.stdev(a), float)
        self.assertIsInstance(fit_result.stdev(b), float)

        self.assertIsInstance(fit_result.r_squared, float)
        self.assertEqual(fit_result.r_squared, 1.0)  # by definition since there's no fuzzyness

        # Test several illegal ways to access the data.
        self.assertRaises(AttributeError, getattr, *[fit_result.params, 'a_fdska'])
        self.assertRaises(AttributeError, getattr, *[fit_result.params, 'c'])
        self.assertRaises(AttributeError, getattr, *[fit_result.params, 'a_stdev_stdev'])
        self.assertRaises(AttributeError, getattr, *[fit_result.params, 'a_stdev_'])
        self.assertRaises(AttributeError, getattr, *[fit_result.params, 'a__stdev'])

    def test_minimize(self):
        """
        Tests maximizing a function with and without constraints, taken from the
        scipy `minimize` tutorial. Compare the symfit result with the scipy
        result.
        https://docs.scipy.org/doc/scipy-0.18.1/reference/tutorial/optimize.html#constrained-minimization-of-multivariate-scalar-functions-minimize
        """
        x = Parameter(value=-1.0)
        y = Parameter(value=1.0)
        # Use an  unnamed Variable on purpose to test the auto-generation of names.
        model = Model(2 * x * y + 2 * x - x ** 2 - 2 * y ** 2)

        constraints = [
            Ge(y - 1, 0),  # y - 1 >= 0,
            Eq(x**3 - y, 0),  # x**3 - y == 0,
        ]

        def func(x, sign=1.0):
            """ Objective function """
            return sign*(2*x[0]*x[1] + 2*x[0] - x[0]**2 - 2*x[1]**2)

        def func_deriv(x, sign=1.0):
            """ Derivative of objective function """
            dfdx0 = sign*(-2*x[0] + 2*x[1] + 2)
            dfdx1 = sign*(2*x[0] - 4*x[1])
            return np.array([ dfdx0, dfdx1 ])

        cons = (
            {'type': 'eq',
             'fun' : lambda x: np.array([x[0]**3 - x[1]]),
             'jac' : lambda x: np.array([3.0*(x[0]**2.0), -1.0])},
            {'type': 'ineq',
             'fun' : lambda x: np.array([x[1] - 1]),
             'jac' : lambda x: np.array([0.0, 1.0])})

        # Unconstrained fit
        res = minimize(func, [-1.0,1.0], args=(-1.0,), jac=func_deriv,
               method='BFGS', options={'disp': False})
        fit = Fit(model=- model)
        self.assertIsInstance(fit.objective, MinimizeModel)
        self.assertIsInstance(fit.minimizer, BFGS)

        fit_result = fit.execute()

        self.assertAlmostEqual(fit_result.value(x) / res.x[0], 1.0, 6)
        self.assertAlmostEqual(fit_result.value(y) / res.x[1], 1.0, 6)

        # Same test, but with constraints in place.
        res = minimize(func, [-1.0,1.0], args=(-1.0,), jac=func_deriv,
               constraints=cons, method='SLSQP', options={'disp': False})

        from symfit.core.minimizers import SLSQP
        fit = Fit(- model, constraints=constraints)
        self.assertEqual(fit.constraints[0].constraint_type, Ge)
        self.assertEqual(fit.constraints[1].constraint_type, Eq)
        fit_result = fit.execute()
        self.assertAlmostEqual(fit_result.value(x), res.x[0], 6)
        self.assertAlmostEqual(fit_result.value(y), res.x[1], 6)

    def test_interdependency_constrained(self):
        """
        Test a model with interdependent components, and with constraints which
        depend on the Model's output.
        This is done in the MatrixSymbol formalism, using a Tikhonov
        regularization as an example. In this, a matrix inverse has to be
        calculated and is used multiple times. Therefore we split that term of
        into a seperate component, so the inverse only has to be computed once
        per model call.

        See https://arxiv.org/abs/1901.05348 for a more detailed background.
        """
        N = Symbol('N', integer=True)
        M = MatrixSymbol('M', N, N)
        W = MatrixSymbol('W', N, N)
        I = MatrixSymbol('I', N, N)
        y = MatrixSymbol('y', N, 1)
        c = MatrixSymbol('c', N, 1)
        a, = parameters('a')
        z, = variables('z')
        i = Idx('i')

        model_dict = {
            W: Inverse(I + M / a ** 2),
            c: - W * y,
            z: sqrt(c.T * c)
        }
        # Sympy currently does not support derivatives of matrix expressions,
        # so we use CallableModel instead of Model.
        model = CallableModel(model_dict)

        # Generate data
        iden = np.eye(2)
        M_mat = np.array([[2, 1], [3, 4]])
        y_vec = np.array([[3], [5]])
        eval_model = model(I=iden, M=M_mat, y=y_vec, a=0.1)
        # Calculate the answers 'manually' so I know it was done properly
        W_manual = np.linalg.inv(iden + M_mat / 0.1 ** 2)
        c_manual = - np.atleast_2d(W_manual.dot(y_vec))
        z_manual = np.atleast_1d(np.sqrt(c_manual.T.dot(c_manual)))

        self.assertEqual(y_vec.shape, (2, 1))
        self.assertEqual(M_mat.shape, (2, 2))
        self.assertEqual(iden.shape, (2, 2))
        self.assertEqual(W_manual.shape, (2, 2))
        self.assertEqual(c_manual.shape, (2, 1))
        self.assertEqual(z_manual.shape, (1, 1))
        np.testing.assert_almost_equal(W_manual, eval_model.W)
        np.testing.assert_almost_equal(c_manual, eval_model.c)
        np.testing.assert_almost_equal(z_manual, eval_model.z)
        fit = Fit(model, z=z_manual, I=iden, M=M_mat, y=y_vec)
        fit_result = fit.execute()

        # See if a == 0.1 was reconstructed properly. Since only a**2 features
        # in the equations, we check for the absolute value. Setting a.min = 0.0
        # is not appreciated by the Minimizer, it seems.
        self.assertAlmostEqual(np.abs(fit_result.value(a)), 0.1)

    def test_2_gaussian_2d_fitting(self):
        """
        Tests fitting to a scalar gaussian with 2 independent variables with
        tight bounds.
        """
        mean = (0.3, 0.4)  # x, y mean 0.6, 0.4
        cov = [[0.01**2, 0], [0, 0.01**2]]
        data = np.random.multivariate_normal(mean, cov, 3000000)
        mean = (0.7, 0.8)  # x, y mean 0.6, 0.4
        cov = [[0.01**2, 0], [0, 0.01**2]]
        data_2 = np.random.multivariate_normal(mean, cov, 3000000)
        data = np.vstack((data, data_2))

        # Insert them as y,x here as np fucks up cartesian conventions.
        ydata, xedges, yedges = np.histogram2d(data[:, 1], data[:, 0], bins=100,
                                               range=[[0.0, 1.0], [0.0, 1.0]])
        xcentres = (xedges[:-1] + xedges[1:]) / 2
        ycentres = (yedges[:-1] + yedges[1:]) / 2

        # Make a valid grid to match ydata
        xx, yy = np.meshgrid(xcentres, ycentres, sparse=False)
        # xdata = np.dstack((xx, yy)).T

        x = Variable()
        y = Variable()

        x0_1 = Parameter(0.7, min=0.6, max=0.9)
        sig_x_1 = Parameter(0.1, min=0.0, max=0.2)
        y0_1 = Parameter(0.8, min=0.6, max=0.9)
        sig_y_1 = Parameter(0.1, min=0.0, max=0.2)
        A_1 = Parameter()
        g_1 = A_1 * Gaussian(x, x0_1, sig_x_1) * Gaussian(y, y0_1, sig_y_1)

        x0_2 = Parameter(0.3, min=0.2, max=0.5)
        sig_x_2 = Parameter(0.1, min=0.0, max=0.2)
        y0_2 = Parameter(0.4, min=0.2, max=0.5)
        sig_y_2 = Parameter(0.1, min=0.0, max=0.2)
        A_2 = Parameter()
        g_2 = A_2 * Gaussian(x, x0_2, sig_x_2) * Gaussian(y, y0_2, sig_y_2)

        model = g_1 + g_2
        fit = Fit(model, xx, yy, ydata)
        fit_result = fit.execute()

        self.assertIsInstance(fit.fit, ConstrainedNumericalLeastSquares)

        img = model(x=xx, y=yy, **fit_result.params)
        img_g_1 = g_1(x=xx, y=yy, **fit_result.params)
        img_g_2 = g_2(x=xx, y=yy, **fit_result.params)
        np.testing.assert_array_equal(img, img_g_1 + img_g_2)

        # Equal up to some precision. Not much obviously.
        self.assertAlmostEqual(fit_result.value(x0_1), 0.7, 3)
        self.assertAlmostEqual(fit_result.value(y0_1), 0.8, 3)
        self.assertAlmostEqual(fit_result.value(x0_2), 0.3, 3)
        self.assertAlmostEqual(fit_result.value(y0_2), 0.4, 3)

    def test_global_fitting(self):
        """
        Test a global fitting scenario with datasets of unequal length. In this
        scenario, a quartic equation is fitted where the constant term is shared
        between the datasets. (e.g. identical background noise)
        """
        x_1, x_2, y_1, y_2 = variables('x_1, x_2, y_1, y_2')
        y0, a_1, a_2, b_1, b_2 = parameters('y0, a_1, a_2, b_1, b_2')

        # The following vector valued function links all the equations together
        # as stated in the intro.
        model = Model({
            y_1: a_1 * x_1**2 + b_1 * x_1 + y0,
            y_2: a_2 * x_2**2 + b_2 * x_2 + y0,
        })

        # Generate data from this model
        # xdata = np.linspace(0, 10)
        xdata1 = np.linspace(0, 10)
        xdata2 = xdata1[::2]  # Make the sets of unequal size

        ydata1, ydata2 = model(x_1=xdata1, x_2=xdata2, a_1=101.3, b_1=0.5, a_2=56.3, b_2=1.1111, y0=10.8)
        # Add some noise to make it appear like real data
        np.random.seed(1)
        ydata1 += np.random.normal(0, 2, size=ydata1.shape)
        ydata2 += np.random.normal(0, 2, size=ydata2.shape)

        xdata = [xdata1, xdata2]
        ydata = [ydata1, ydata2]

        # Guesses
        a_1.value = 100
        a_2.value = 50
        b_1.value = 1
        b_2.value = 1
        y0.value = 10

        eval_jac = model.eval_jacobian(x_1=xdata1, x_2=xdata2, a_1=101.3,
                                       b_1=0.5, a_2=56.3, b_2=1.1111, y0=10.8)
        self.assertEqual(len(eval_jac), 2)
        for comp in eval_jac:
            self.assertEqual(len(comp), len(model.params))

        sigma_y = np.concatenate((np.ones(20), [2., 4., 5, 7, 3]))

        fit = Fit(model, x_1=xdata[0], x_2=xdata[1],
                  y_1=ydata[0], y_2=ydata[1], sigma_y_2=sigma_y)
        fit_result = fit.execute()

        # fit_curves = model(x_1=xdata[0], x_2=xdata[1], **fit_result.params)
        self.assertAlmostEqual(fit_result.value(y0), 1.061892e+01, 3)
        self.assertAlmostEqual(fit_result.value(a_1), 1.013269e+02, 3)
        self.assertAlmostEqual(fit_result.value(a_2), 5.625694e+01, 3)
        self.assertAlmostEqual(fit_result.value(b_1), 3.362240e-01, 3)
        self.assertAlmostEqual(fit_result.value(b_2), 1.565253e+00, 3)

 def test_chained_min(self):
     """Test fitting with a chained minimizer"""
     curvals = [p.value for p in self.model.params]
     fit = Fit(self.model, self.xx, self.yy, self.ydata,
               minimizer=[DifferentialEvolution, BFGS])
     fit_result = fit.execute(
         DifferentialEvolution={'seed': 0, 'tol': 1e-4, 'maxiter': 10}
     )
     self.assertAlmostEqual(fit_result.value(self.x0_1), 0.4, 4)
     self.assertAlmostEqual(fit_result.value(self.y0_1), 0.4, 4)
     self.assertEqual(curvals, [p.value for p in self.model.params])