---
myst:
    substitutions:
        macro:
            python: 1-5,19-40,43-56,58-65,71-75
            cpp: 6-10,17-33,36-48,50-58,65-68
        bloc1:
            python: 29-30
            cpp: 7,25
        bloc2:
            python: 34-35
            cpp: 28-29
        bloc3:
            python: 37-38,40,44-46
            cpp: 8,31,33,37-39
        bloc4:
            python: "48"
            cpp: "41"
        bloc5:
            python: 50,52-53,56,58
            cpp: 9,43,45,48,50
        bloc6:
            python: 60,62-65,71-75
            cpp: 52,54-57,64-68
        console:
            python: 2-46
            cpp: 6-50
---
# Macro "**modelerClassificationNeuralNetworks.{{extension}}**"

## Objective

The objective of this macro is to build a surrogate model (an Artificial Neural Network) from a 
database for a **"Classification"** Problem. From a first database loaded from the ASCII file 
`problem2Classes_001000.dat`, which defines three variables $(x,y) \in [-1., 1]^{2}$ and $rc01 \in 
\{0, 1\}$ on 1000 patterns,

{{
    "```{figure} " + parent_dir +
        "/roottest/build/uranie/doc/modeler/use_cases/" + language 
        + "/classification_neural_network/modelerClassificationNeuralNetworks_App.png\n"
    + ":align: center\n"
    + ":name: use_cases_modelerClassificationNeuralNetworks_App\n"
    + figure_scale + "\n"
    + "```"
}}
            
two ASCII files are created, one with the 800st patterns (`_problem2Classes_app_.dat`), the other 
with the 200 last patterns (`_problem2Classes_val_.dat`). The surrogate model is built with the 
database extracted from the first of the two files, the second allowing to perform calculations with 
a function.

## Macro {{uranie}}

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + macro[language] + "\n"
    + "```"
}}
            
The main {{tds}} loads the main ASCII data file `problem2Classes_001000.dat`

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc1[language] + "\n"
    + "```"
}}
            
The database is split with the internal iterator attribute in two parts by exporting the 800st 
patterns in a file and the remaining 200 in another one

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc2[language] + "\n"
    + "```"
}}
            
A second {{tds}} loads `_problem2Classes_app_.dat` and builds the surrogate model over all the 
variables with 3 hidden layers, a **Hyperbolic Tangent (TanH)** activation function (normalization) 
in the 3 hidden layers and set the function tolerance to 1e-.6. The **"@"** character behind the 
output name defines a **classification** problem.

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc3[language] + "\n"
    + "```"
}}
            
The model is exported in an external file in C++ language `"uranie_ann_problem2Classes.C"` where the 
function name is `ANNproblem2Classes`

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc4[language] + "\n"
    + "```"
}}
            
The model is loaded from the macro `uranie_ann_problem2Classes.C` and applied on the second database 
with the function `ANNproblem2Classes`.

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc5[language] + "\n"
    + "```"
}}
            
We draw on a 3D graph, the learning database (in green) and the estimations by the Artificial Neural 
Network with red points.

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/uranie/doc/modeler/use_cases/" + language + "/modelerClassificationNeuralNetworks." 
        + extension 
    + "\n"
    + ":language: " + language + "\n"
    + ":lines: " + bloc6[language] + "\n"
    + "```"
}}
            
## Graph

{{
    "```{figure} " + parent_dir +
        "/roottest/build/uranie/doc/modeler/use_cases/" + language 
        + "/classification_neural_network/modelerClassificationNeuralNetworks.png\n"
    + ":align: center\n"
    + ":name: use_cases_modelerClassificationNeuralNetworks\n"
    + figure_scale + "\n"
    + "\n"
    + "Graph of the macro **\"modelerClassificationNeuralNetworks." + extension + "\"**" + "\n"
    + "```"
}}
            
## Console

{{
    "```{literalinclude} " + parent_dir +
        "/roottest/build/uranie/doc/modeler/use_cases/" + language 
        + "/modelerClassificationNeuralNetworks_clean.log\n"
    + ":language: none\n"
    + ":lines: " + console[language] + "\n"
    + "```"
}}