Update MetaModelValidation_doc.i.in. Draft of Python interface.

python/src/FunctionalChaosValidation.i

@@ -0,0 +1,11 @@
+// SWIG file FunctionalChaosValidation.i
+
+%{
+#include "openturns/FunctionalChaosValidation.hxx"
+%}
+
+%include FunctionalChaosValidation.i
+
+%include openturns/FunctionalChaosValidation.hxx
+
+namespace OT {%extend FunctionalChaosValidation {FunctionalChaosValidation(const FunctionalChaosValidation & other){return new OT::FunctionalChaosValidation(other);}}}

python/src/LinearModelValidation.i

@@ -0,0 +1,11 @@
+// SWIG file LinearModelValidation.i
+
+%{
+#include "openturns/LinearModelValidation.hxx"
+%}
+
+%include LinearModelValidation.i
+
+%include openturns/LinearModelValidation.hxx
+
+namespace OT {%extend LinearModelValidation {LinearModelValidation(const LinearModelValidation & other){return new OT::LinearModelValidation(other);}}}

python/src/MetaModelValidation_doc.i.in

@@ -3,6 +3,12 @@
 
 Refer to :ref:`cross_validation`.
 
+
+Available constructors:
+    MetaModelValidation(*inputValidationSample, outputValidationSample, metaModel*)
+    MetaModelValidation(*outputValidationSample, outputPredictionSample*)
+
+
 Parameters
 ----------
 inputValidationSample, outputValidationSample : 2-d sequence of float
@@ -11,35 +17,38 @@ inputValidationSample, outputValidationSample : 2-d sequence of float
 metaModel : :class:`~openturns.Function`
     Metamodel to validate.
 
+outputPredictionSample: 2-d sequence of float
+    The output prediction sample from the metamodel.
+
 Notes
 -----
-A MetaModelValidation object is used for the validation process of a metamodel.
+A `MetaModelValidation` object is used for the validation of a metamodel.
 For that purpose, a dataset independent of the learning step, is used to score the surrogate model.
 Its main functionalities are :
 
-- To compute the predictivity factor :math:`Q_2`
-- To get the residual sample, its non parametric distribution
-- To draw a `model vs metamodel` validation graph.
-
-
-Currently only one dimensional output models are available.
+- To compute the coefficient of determination :math:`R^2`
+- To get the residual sample and its non parametric distribution
+- To draw a validation graph presenting the metamodel predictions against
+  the model observations.
 
+More details on this topic are presented in :ref:`cross_validation`.
+
 Examples
 --------
 >>> import openturns as ot
 >>> from math import pi
->>> dist = ot.Uniform(-pi/2, pi/2)
+>>> dist = ot.Uniform(-pi / 2, pi / 2)
 >>> # Model here is sin(x)
 >>> model = ot.SymbolicFunction(['x'], ['sin(x)'])
 >>> # We can build several types of models (kriging, pc, ...)
 >>> # We use a Taylor development (order 5) and compare the metamodel with the model
->>> metaModel = ot.SymbolicFunction(['x'], ['x - x^3/6.0 + x^5/120.0'])
+>>> metaModel = ot.SymbolicFunction(['x'], ['x - x^3 / 6.0 + x^5 / 120.0'])
 >>> x = dist.getSample(10)
 >>> y = model(x)
 >>> # Validation of the model
 >>> val = ot.MetaModelValidation(x, y, metaModel)
->>> # Compute the first indicator : q2
->>> q2 = val.computeR2Score()
+>>> # Compute the R2 score
+>>> r2Score = val.computeR2Score()
 >>> # Get the residual
 >>> residual = val.getResidualSample()
 >>> # Get the histogram of residual
@@ -102,9 +111,9 @@ mean squared error of the metamodel:
 The sample :math:`R^2` is:
 
 .. math::
-    \hat{R}^2 = 1 - \frac{\frac{1}{n} \sum_{j=1}^{n} (y^{(j)} - \tilde{g}(\bdx^{(j)}))^2}{\hat{\sigma}^2_Y}
+    \hat{R}^2 = 1 - \frac{\frac{1}{n} \sum_{j=1}^{n} \left(y^{(j)} - \tilde{g}\left(\bdx^{(j)}\right)\right)^2}{\hat{\sigma}^2_Y}
 
-where :math:`\tilde{g}` is the metamodel, :math:`n \in \Nset` is the sample size,
+where :math:`n \in \Nset` is the sample size, :math:`\tilde{g}` is the metamodel,
 :math:`\{\bdx^{(j)} \in \Rset^{n_X}\}_{j = 1, ..., n}` is the input experimental design,
 :math:`\{y^{(j)} \in \Rset\}_{j = 1, ..., n}` is the output of the model and
 :math:`\hat{\sigma}^2_Y` is the sample variance of the output:
@@ -132,7 +141,15 @@ Notes
 The residual sample is given by :
 
 .. math::
-    \epsilon_{l} = Y_{l} -\hat{f}(X_l)"
+
+    r^{(j)} = y^{(j)} - \tilde{g}\left(\vect{x}^{(j)}\right)
+
+for :math:`j = 1, ..., n` where :math:`n \in \Nset` is the sample size,
+:math:`y^{(j)}` is the model observation,
+:math:`\tilde{g}` is the metamodel and :math:`\vect{x}^{(j)}` is the :math:`j`-th input observation.
+
+If the output is multi-dimensional, the residual sample has dimension :math:`n_y \in \Nset`,
+where :math:`n_y` is the output dimension."
 
 
 // ---------------------------------------------------------------------
@@ -164,4 +181,45 @@ The residual distribution is built thanks to :class:`~openturns.KernelSmoothing`
 Returns
 -------
 graph : :class:`~openturns.GridLayout`
-    The visual validation graph."
+    The visual validation graph.
+
+Notes
+-----
+If the output is multi-dimensional, the graph has 1 row and :math:`n_y \in \Nset`
+columns, where :math:`n_y` is the output dimension."
+
+// ---------------------------------------------------------------------
+
+%feature("docstring") OT::MetaModelValidation::computeMeanSquaredError
+"Accessor to the mean squared error.
+
+Returns
+-------
+meanSquaredError : :class:`~openturns.Point`
+    The mean squared error of each marginal output dimension.
+
+Notes
+-----
+The sample mean squared error is:
+
+.. math::
+    \widehat{\operatorname{MSE}} 
+    = \frac{1}{n} \sum_{j=1}^{n} \left(y^{(j)} - \tilde{g}\left(\bdx^{(j)}\right)\right)^2
+
+where :math:`n \in \Nset` is the sample size, :math:`\tilde{g}` is the metamodel,
+:math:`\{\bdx^{(j)} \in \Rset^{n_X}\}_{j = 1, ..., n}` is the input experimental design and
+:math:`\{y^{(j)} \in \Rset\}_{j = 1, ..., n}` is the output of the model.
+
+If the output is multi-dimensional, the same calculations are repeated separately for
+each output marginal :math:`k` for :math:`k = 1, ..., n_y` where :math:`n_y \in \Nset`
+is the output dimension."
+
+// ---------------------------------------------------------------------
+
+%feature("docstring") OT::MetaModelValidation::getMetamodelPredictions
+"Accessor to the output predictions from the metamodel.
+
+Returns
+-------
+outputMetamodelSample : :class:`~openturns.Sample`
+    Output sample of the metamodel."