Problems from Vladislavleva

These problems are introduced and studied in the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

dcgpy.generate_kotanchek()

Generates the problem Kotanchek from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = \frac{e^{-(x_1-1)^2}}{1.2+(x_2-2.5)^2}\]

\(x_1\) and \(x_2\) are sampled in one hundred randomly selected points in [0.3,4]x[0.3,4].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> from mpl_toolkits.mplot3d import Axes3D
>>> import matplotlib.pyplot as plt
>>> X, Y = generate_kotanchek()
>>> fig = plt.figure()
>>> ax = fig.gca(projection='3d')
>>> ax.scatter(X[:,0], X[:,1], Y)
dcgpy.generate_salutowicz()

Generates the problem Salutowicz from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = e^{-x} x^3 \cos x\sin x (\cos x \sin^2 x - 1)\]

x is sampled in one hundred points uniformly sampled in [0.5,10].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> import matplotlib.pyplot as plt
>>> X, Y = generate_salutowicz()
>>> plt.plot(X,Y, '.')
dcgpy.generate_salutowicz2d()

Generates the problem Salutowicz2D from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = e^{-x} x^3 \cos x_1\sin x_1 (\cos x_1 \sin^2 x_1 - 1) * (x_2 - 5)\]

\(x_1\) and \(x_2\) are sampled in 601 randomly selected points in [0.05,10]x[0.05,10].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> from mpl_toolkits.mplot3d import Axes3D
>>> import matplotlib.pyplot as plt
>>> X, Y = generate_kotanchek()
>>> fig = plt.figure()
>>> ax = fig.gca(projection='3d')
>>> ax.scatter(X[:,0], X[:,1], Y)
dcgpy.generate_uball5d()

Generates the problem UBall5D from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = \frac{10}{5 + \sum_{i=1}^5 (x_i-3)^2}\]

\(x_i\) are sampled in 1024 randomly selected points in \([0.05,6.05]^5\).

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> import matplotlib.pyplot as plt
>>> X, Y = generate_uball5d()
>>> plt.plot(X,Y, '.')
dcgpy.generate_ratpol3d()

Generates the problem RatPol3D from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = 30 \frac{(x_1 - 3)(x_3 - 1)}{x_2^2(x_1-10)}\]

\(x_1\), \(x_2\), \(x_3\) are sampled in 300 randomly selected points in [0.05,2] x [1,2].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> import matplotlib.pyplot as plt
>>> X, Y = generate_ratpol3d()
>>> plt.plot(X,Y, '.')
dcgpy.generate_sinecosine()

Generates the problem SineCosine from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = 6 \sin(x_1)\cos(x_2)\]

\(x_1\), \(x_2\) are sampled in 30 randomly selected points in [0.1,5.9] x [0.1,5.9].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> from mpl_toolkits.mplot3d import Axes3D
>>> import matplotlib.pyplot as plt
>>> fig = plt.figure()
>>> ax = fig.gca(projection='3d')
>>> ax.scatter(X[:,0], X[:,1], Y)
dcgpy.generate_ripple()

Generates the problem Ripple from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = (x_1-3)(x_2-3) + 2\sin((x_1-4)(x_2-4))\]

\(x_1\), \(x_2\) are sampled in 300 randomly selected points in [0.05,6.05] x [0.05,6.05].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> from mpl_toolkits.mplot3d import Axes3D
>>> import matplotlib.pyplot as plt
>>> fig = plt.figure()
>>> ax = fig.gca(projection='3d')
>>> ax.scatter(X[:,0], X[:,1], Y)
dcgpy.generate_ratpol2d()

Generates the problem RatPol2D from the paper:

Vladislavleva, Ekaterina J., Guido F. Smits, and Dick Den Hertog. “Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming.” IEEE Transactions on Evolutionary Computation 13.2 (2008): 333-349.

The functional form of such a problem is:

\[y = \frac{(x_1-3)^4+(x_2-3)^3-(x_2-3)}{(x_2-2)^4+10}\]

\(x_1\), \(x_2\) are sampled in 50 randomly selected points in [0.05,6.05] x [0.05,6.05].

Returns

A tuple containing the points (2D NumPy float array) and labels (2D NumPy float array).

Examples:

>>> from dcgpy import *
>>> from mpl_toolkits.mplot3d import Axes3D
>>> import matplotlib.pyplot as plt
>>> fig = plt.figure()
>>> ax = fig.gca(projection='3d')
>>> ax.scatter(X[:,0], X[:,1], Y)