### Install PINA with Extra Packages

Source: https://github.com/mathlab/pina/blob/master/docs/source/_installation.rst

Installs PINA along with specified extra dependencies for development, testing, documentation, or tutorials.

```bash
$ pip install "pina-mathlab[extras]"
```

--------------------------------

### Install PINA from Source

Source: https://github.com/mathlab/pina/blob/master/docs/source/_installation.rst

Installs the PINA package from its source code after cloning the repository. This uses an editable install.

```bash
$ pip install -e .
```

--------------------------------

### Clone PINA Repository from GitHub

Source: https://github.com/mathlab/pina/blob/master/docs/source/_installation.rst

Clones the official PINA repository from GitHub to install the package from source.

```bash
$ git clone https://github.com/mathLab/PINA
```

--------------------------------

### Install PINA via PIP

Source: https://github.com/mathlab/pina/blob/master/docs/source/_installation.rst

Installs the PINA library using pip for Mac and Linux users. This command fetches pre-built binary packages.

```bash
$ pip install pina-mathlab
```

--------------------------------

### Install PINA with Tutorial Extras

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial16/tutorial.html

Installs the PINA library with tutorial extras, necessary for running the examples in this notebook. This command is typically run in a Google Colab environment.

```shell
!pip install "pina-mathlab[tutorial]"
```

--------------------------------

### Setup for PINA Tutorials (Python)

Source: https://github.com/mathlab/pina/blob/master/tutorials/TUTORIAL_GUIDELINES.md

This Python snippet handles notebook execution on Google Colab and installs necessary PINA packages. It also imports common libraries like torch and matplotlib, and sets up warning filters for a cleaner output.

```python
## Routine needed to run the notebook on Google Colab
try:
    import google.colab
    IN_COLAB = True
except:
    IN_COLAB = False

if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"

import torch                        # if used
import matplotlib.pyplot as plt     # if used
import warnings                     # if needed

warnings.filterwarnings("ignore")

# Additional PINA and problem-specific imports
...
```

--------------------------------

### Install PINA with tutorial extras

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial18/tutorial.html

Installs the PINA library with extra dependencies required for tutorials, specifically for use in Google Colab environments.

```bash
#!pip install "pina-mathlab[tutorial]"
```

--------------------------------

### Install PINA from Source

Source: https://github.com/mathlab/pina/blob/master/README.md

Installs PINA by cloning the repository and building from source. This is useful for development or when needing the latest unreleased features. It requires git and Python environment setup.

```sh
git clone https://github.com/mathLab/PINA
cd PINA
git checkout master
pip install .
```

--------------------------------

### Install PINA and Download Data (Colab)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial7/tutorial.html

Installs the PINA library with tutorial dependencies and downloads necessary data files if running in a Google Colab environment. This setup ensures all required components are available for the tutorial.

```python
import google.colab

IN_COLAB = True
except:
    IN_COLAB = False
if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"
    !mkdir "data"
    !wget "https://github.com/mathLab/PINA/raw/refs/heads/master/tutorials/tutorial7/data/pinn_solution_0.5_0.5" -O "data/pinn_solution_0.5_0.5"
    !wget "https://github.com/mathLab/PINA/raw/refs/heads/master/tutorials/tutorial7/data/pts_0.5_0.5" -O "data/pts_0.5_0.5"
```

--------------------------------

### Install PINA with Tutorial Extras

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial1/tutorial.html

Installs the PINA library with the necessary dependencies for running tutorials, specifically designed for Google Colab environments.

```python
import google.colab

IN_COLAB = True
except:
    IN_COLAB = False
if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"
```

--------------------------------

### Install PINA with Tutorial Dependencies

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial21/tutorial.html

Installs the PINA library with the necessary dependencies for running tutorials, specifically for Google Colab environments. It checks if the script is running in Colab and then uses pip to install the package.

```python
import torch
import matplotlib.pyplot as plt
import warnings

warnings.filterwarnings("ignore")

from pina import Trainer
from pina.solver import SupervisedSolver
from pina.model import KernelNeuralOperator
from pina.model.block import FourierBlock1D
from pina.problem.zoo import SupervisedProblem
```

--------------------------------

### PINN Model Training Setup and Execution (Python)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial7/tutorial.html

This code snippet initializes a PINN model with a specified problem and optimizer, then configures and starts a PyTorch Lightning Trainer. It sets training parameters like maximum epochs, accelerator, default root directory, and includes the custom SaveParameters callback. The trainer is configured to use 100% of the data for training.

```python
max_epochs = 1500
pinn = PINN(
    problem, model, optimizer=TorchOptimizer(torch.optim.Adam, lr=0.005)
)
# define the trainer for the solver
trainer = Trainer(
    solver=pinn,
    accelerator="cpu",
    max_epochs=max_epochs,
    default_root_dir=tmp_dir,
    enable_model_summary=False,
    callbacks=[SaveParameters()],
    train_size=1.0,
    val_size=0.0,
    test_size=0.0,
)
trainer.train()
```

--------------------------------

### Install PINA and Dependencies for Colab

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial5/tutorial.html

Installs the PINA library with tutorial extras and SciPy for use in Google Colab. It also downloads the necessary dataset for the Darcy Flow problem.

```python
try:
    import google.colab

    IN_COLAB = True
except:
    IN_COLAB = False
if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"
    !pip install scipy
    # get the data
    !wget https://github.com/mathLab/PINA/raw/refs/heads/master/tutorials/tutorial5/Data_Darcy.mat
```

--------------------------------

### Install PINA with Tutorial Dependencies

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial15/tutorial.html

Installs the PINA library with extra dependencies required for running tutorials, specifically for use within Google Colab environments.

```python
try:
    import google.colab

    IN_COLAB = True
except:
    IN_COLAB = False

if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"
```

--------------------------------

### Install PINA with Extra Packages

Source: https://github.com/mathlab/pina/blob/master/README.md

Installs PINA along with optional dependencies for specific use cases like development ('dev'), testing ('test'), documentation building ('doc'), or running tutorials ('tutorial').

```sh
pip install "pina-mathlab[extras]"
```

--------------------------------

### Install PINA and Import Libraries

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial19/tutorial.html

Installs the PINA library with tutorial dependencies if running in Google Colab and imports necessary libraries like torch, Data from torch_geometric, LabelTensor, and Graph from PINA.

```python
import warnings
import torch
from torch_geometric.data import Data

warnings.filterwarnings("ignore")

from pina import LabelTensor, Graph
```

--------------------------------

### PINA Model Training Setup (PyTorch)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

Sets up and trains a PINN model using the PINA library. This includes discretizing the domain, defining the custom `HardMLP` model, creating a `PINN` solver, and configuring a `Trainer` with specific epochs and callbacks.

```python
# generate the data
problem.discretise_domain(1000, "random", domains"all")

# define model
model = HardMLP(len(problem.input_variables), len(problem.output_variables))

# crete the solver
pinn = PINN(problem=problem, model=model)

# create trainer and train
trainer = Trainer(
    solver=pinn,
    max_epochs=1000,
    accelerator="cpu",
    enable_model_summary=False,
    train_size=1.0,
    val_size=0.0,
    test_size=0.0,
    callbacks=[MetricTracker(["train_loss", "initial_loss", "D_loss"])]
)
trainer.train()
```

--------------------------------

### Install PINA Stable Release using Pip

Source: https://github.com/mathlab/pina/blob/master/README.md

Installs the latest stable version of the PINA library from PyPI using pip. This is the recommended method for most users.

```sh
pip install "pina-mathlab"
```

--------------------------------

### PINA Library Imports and Setup

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial7/tutorial.html

Imports essential libraries and modules from PINA, PyTorch, and Matplotlib for building and training PINNs. It also includes warning filters and sets a random seed for reproducibility.

```python
import matplotlib.pyplot as plt
import torch
import warnings

from lightning.pytorch import seed_everything
from lightning.pytorch.callbacks import Callback

from pina import Condition, Trainer
from pina.problem import SpatialProblem, InverseProblem
from pina.operator import laplacian
from pina.model import FeedForward
from pina.equation import Equation, FixedValue
from pina.solver import PINN
from pina.domain import CartesianDomain
from pina.optim import TorchOptimizer

warnings.filterwarnings("ignore")
seed_everything(883)
```

--------------------------------

### Exception Handling in Java

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

Provides a basic example of exception handling in Java using `try-catch` blocks to manage potential runtime errors.

```java
public class ExceptionHandling {
    public static void main(String[] args) {
        try {
            int result = 10 / 0; // This will cause an ArithmeticException
            System.out.println("Result: " + result);
        } catch (ArithmeticException e) {
            System.err.println("Error: Cannot divide by zero.");
        }
    }
}
```

--------------------------------

### Jupyter HTML Widget Model Configuration

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial11/tutorial.html

Defines the configuration for a Jupyter HTML widget, including its model name, module, and version. This is a standard setup for interactive HTML elements in Jupyter environments.

```json
{
  "model_name": "HTMLModel",
  "model_module": "@jupyter-widgets\/controls",
  "model_module_version": "2.0.0",
  "state": {
    "_dom_classes": [],
    "_model_module": "@jupyter-widgets\/controls",
    "_model_module_version": "2.0.0",
    "_model_name": "HTMLModel",
    "_view_count": null,
    "_view_module": "@jupyter-widgets\/controls",
    "_view_module_version": "2.0.0",
    "_view_name": "HTMLView",
    "description": "",
    "description_allow_html": false,
    "layout": "IPY_MODEL_347b288a105f4466a0d23c171caadf5c",
    "placeholder": "\u200b",
    "style": "IPY_MODEL_754f3bf628c74a23b61891e483467c9a",
    "tabbable": null,
    "tooltip": null,
    "value": "Epoch\u2007499:\u2007100%"
  }
}
```

--------------------------------

### Uninstall PINA via PIP

Source: https://github.com/mathlab/pina/blob/master/docs/source/_installation.rst

Uninstalls the PINA library from the system using pip.

```bash
$ pip uninstall pina-mathlab
```

--------------------------------

### Import PINA modules and set up environment

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial11/tutorial.html

Imports necessary libraries including torch, warnings, and core PINA components like Trainer, SupervisedSolver, FeedForward, and SupervisedProblem. It also includes a check for the Google Colab environment and suppresses warnings.

```python
import torch
import warnings

from pina import Trainer
from pina.solver import SupervisedSolver
from pina.model import FeedForward
from pina.problem.zoo import SupervisedProblem

warnings.filterwarnings("ignore")
```

--------------------------------

### Solver Initialization

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial1/tutorial.html

Shows how to initialize a PINN solver with a model, problem definition, and an optimizer.

```APIDOC
## Solver Initialization

### Description
Initialize a Physics-Informed Neural Network (PINN) solver. The solver requires a problem definition and a model. It also accepts an optimizer, scheduler, loss type, and weighting for different conditions, which are set to their default values if not specified.

### Method
N/A (Code Example)

### Endpoint
N/A

### Parameters
#### Request Body
- **problem** (PINA Problem Object) - Required - The physics problem to solve.
- **model** (PINA Model Object) - Required - The neural network model.
- **optimizer** (PINA Optimizer Wrapper) - Required - The optimizer for training (e.g., `TorchOptimizer(torch.optim.RAdam, lr=0.005)`).

### Request Example
```python
import torch
from pina.solver import PINN
from pina.optim import TorchOptimizer

# Assuming 'problem' and 'model' are already defined
# model = FeedForward(...)
# problem = ...

pinn = PINN(problem, model, TorchOptimizer(torch.optim.RAdam, lr=0.005))
```

### Response
#### Success Response (200)
- **pinn_solver** (object) - The initialized PINN solver instance.

#### Response Example
```
<pina.solver.PINN object at 0x...>
```

### Bonus Tip
All physics solvers in PINA can handle both forward and inverse problems without requiring any changes to the model or solver structure. Refer to the PINA tutorial on inverse problems for more information.
```

--------------------------------

### PINA Trainer Setup and Data Preparation

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial8/tutorial.html

This code configures and sets up the PINA Trainer for a supervised learning task. It defines training parameters such as maximum epochs, batch size, accelerator, and data split ratios (train, validation, test). It then sets up the data module and extracts training data.

```python
trainer = Trainer(
    solver=pod_nn_stokes,
    max_epochs=1000,
    batch_size=None,
    accelerator="cpu",
    train_size=0.9,
    val_size=0.0,
    test_size=0.1,
)

# fit the pod basis
trainer.data_module.setup("fit")  # set up the dataset
train_data = trainer.data_module.train_dataset.get_all_data()
x_train = train_data["data"]["target"]  # extract data for training
pod_nn.fit_pod(x=x_train)
```

--------------------------------

### Training Configuration and Execution (Python)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

Sets up and initiates the training process for the `HardMLPtime` model. It configures the solver, trainer with specified epochs, accelerator, and callbacks for metric tracking. This snippet assumes a `problem` object and `PINN` and `Trainer` classes are defined elsewhere.

```python
# define model
model = HardMLPtime(len(problem.input_variables), len(problem.output_variables))

# crete the solver
pinn = PINN(problem=problem, model=model)

# create trainer and train
trainer = Trainer(
    solver=pinn,
    max_epochs=1000,
    accelerator="cpu",
    enable_model_summary=False,
    train_size=1.0,
    val_size=0.0,
    test_size=0.0,
    callbacks=[MetricTracker(["train_loss", "initial_loss", "D_loss"])]
)
trainer.train()
```

--------------------------------

### Set up Supervised Problem and Solver

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial21/tutorial.html

Configures a supervised learning problem using the SupervisedProblem class with input and target data. It then initializes a SupervisedSolver, passing the defined problem and the constructed Neural Operator model, preparing the system for training.

```python
# making the problem
problem = SupervisedProblem(input, target)

# making the solver
solver = SupervisedSolver(problem, model, use_lt=False)
```

--------------------------------

### Install PINA for Google Colab

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial17/tutorial.html

This code snippet checks if the environment is Google Colab and installs the PINA library with tutorial dependencies if it is. This ensures the necessary packages are available for running the tutorial on Colab.

```python
import warnings
import torch
import matplotlib.pyplot as plt

warnings.filterwarnings("ignore")

from pina import Condition, LabelTensor
from pina.problem import AbstractProblem
from pina.geometry import CartesianDomain
```

--------------------------------

### Check and Install PINA in Google Colab

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial21/tutorial.html

This code block checks if the current environment is Google Colab. If it is, it proceeds to install the 'pina-mathlab[tutorial]' package using pip, ensuring the necessary components for tutorials are available.

```python
## routine needed to run the notebook on Google Colab
try:
    import google.colab

    IN_COLAB = True
except:
    IN_COLAB = False
if IN_COLAB:
    !pip install "pina-mathlab[tutorial]"
```

--------------------------------

### Handle HTTP Requests

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

This snippet demonstrates how to handle HTTP requests. It sets up request handlers for specific routes and defines the logic to be executed when those routes are accessed.

```Unknown
ZGhqZPn66zzjpLO3fu1KOPPqru3bvr+++/V506darchnAjNwCEGrnh3NwIJjMkcgNA5aqSG/VPr6/f9/4ehlb9IdjcKC0t1V133aXzzz9f7du3r3C8s846S1OnTlXHjh21f/9+PffcczrvvPP0ww8/BLVe/GHJp/WNGjXKc8d66Xhlr1mzZjrvT/erWrWqH0ECYG2xP/3sc/ix0mIt3vNm0DvKxcXF2r27VIuXNVTt2uE5KnrokKGeGbu0bds2JSQkeIaH4ui3v/r27ev5/44dOyojI0PNmzfXu+++qyFDhkSsHZFEbgDuRm5UDbnxR25c8cHVql4r1sSWATDT0cPF+vel71YpN37f+7uu+GCgqteqHuLWHXf08FH9+9JZQeXG8OHD9f3335/yvoLdunVTt27dPH+fd955atOmjV599VU9/vjjwTe+EmEvTqWkpKiwsNBrWGFhoRISEio8klHR6WjVqsWpWrXw3iEegPmqRVe+U1jV0+1r145S7TrBnaZ7asePrickJHiFRagEs02tW7euWrVqpfXr14e8PeFAbgAIFLlRMafnRjDLJ1WcG9VrxSq2NsUpwO2qmhvVa1UP+7Yk0NwYMWKEPvzwQ3322WcBn/1UvXp1nX322WHNhXClrEe3bt2Ul5fnNWzRokVeVTgAOFFx6/CcKuoEwWxTDx06pA0bNqhRo0bhbl5IkBsAAkVuVMzpuUFmAEDlDMPQiBEjNGfOHH3yySdq0aJFwNMoKSnRd999F9ZcCLg4dejQIa1atcrzNI9NmzZp1apV2rp1q6Tjp8gOGjTIM/5tt92mjRs36r777tOaNWs0ceJEvfvuuxo5cmRolgAAbCwc29R77rlH//3vf7V582YtWbJEl19+uWJiYnTttddGdNnKkBsAEDpOzw0yAwBCa/jw4Xr77bf1zjvvqE6dOiooKFBBQYF+//2P+2INGjRIo0aN8vz92GOP6aOPPtLGjRu1cuVK3XDDDdqyZYtuvvnmsLUz4Mv6vvrqK/Xq1cvzd9m12oMHD9b06dO1c+dOT3hIUosWLTRv3jyNHDlSL774ok4//XS99tprysrKCkHzAThVcevTFbtmu9nNCLtwbFO3b9+ua6+9Vnv37lWDBg10wQUXaOnSpWrQoEHkFuwE5AaASCA3nJEbZAYAhNYrr7wiSerZs6fX8GnTpummm26SJG3dutXr6YS//vqrhg4dqoKCAtWrV0/p6elasmSJ2rZtG7Z2RhmGYYRt6iFy4MABJSYm6sILRnPvEMBFTu5kHCst1se7XtP+/fuDui9H2bbkqx+Sw3bvkEMHS9WlXWHQbURokBuAO5EbCFbZZ31N3g3ccwpwseJDxZp50dtVzo1wbkuq2karCvs9pwAgWNxDBAAQCHIDAAB7ojgFAAAAAAAA01CcAmBpHAUHAASC3AAAwH4oTgEAAAAAAMA0FKcAWB5HwQEAgSA3AACwF4pTAAAAAAAAMA3FKQC2wFFwAEAgyA0AAOyD4hQAAAAAAABMQ3EKgG0Ut2psdhMAADZCbgAAYA8UpwAAAAAAAGAailMAAAAAAAAwDcUpAAAAAAAAmIbiFAAAAAAAAExDcQoAAAAAAACmoTgFAAAAAAAA01CcAgAAAAAAgGmqmd0A4GT70+KCel/ihqIQtwQAYAfkBgAAgL1RnEJIBNsxsFob6KgAQGSQGwAAAChDcQqnZIUORKT4s6x0RACgcuSGN3IDAACgchSn4OGmzkRVVLae6IAAcBNywz/kBgAAQOUoTrkYnYrQq2id0vkA4ATkRuiRGwAAABSnXIHOhPlO/gzodACwMnLDfOQGAABwE4pTDkSnwvpO/IzocAAwG7lhfeQGAABwMopTDkHHwr7ocAAwA7lhX+QGAABwGopTNkbHwnm4jANAOJEbzkNuAAAAJ6A4ZTN0LNyFo+MAqorccBdyAwAA2BHFKZugc4Gy7wCdDQD+IDdAbgAAALugOGVxdC5wMo6KA6gImQFfyA0AAGB1FKcsig4G/MFRcQBlyA34g9wAAABWRHHKYuhcIBh0NgD3IjcQDHIDAABYCcUpi6BzgVCgswG4B7mBUCA3AACAFUSb3QC3258WRwcDIcd3CnAucgPhwHcKAACYieKUSehcINz4fgHOQm4g3Ph+AQAAs3BZX4Sx44dI4nINwP7IDUQSuQEAAMzAmVMRRAcDZuG7B9gTv12Yhe8eAACIJIpTEcJOHszGdxCwF36zMBvfQQAAECkUpyKAnTtYBd9FwB74rcIq+C4CAIBIoDgVZuzUwWq4qTJgbfw+YTXkBgAACDeKU2HEjhysjO8nYD38LmFlfD8BAEC4UJwKE3bgYAd8TwHr4PcIO+B7CgAAwoHiVBiw4wY74fsKmI/fIeyE7ysAAAi1amY3wGnYYavYweZRZjdBdbYYZjfBkvanxSlxQ5HZzQBcidyoGLlhXeQGAAAIJYpTIUQHwxodicpU1j63d0DoaACRR26QG3ZGbgAAgFChOBUibuxgWL1DEShfy+O2jgcdDSByyA37IzfIDQAAEBoUp0LALR0Mp3Uq/HHyMruh00FHAwg/csO5yA0AAIDAUZyqIid3MNzYqTiVE9eJkzscdDSA8CE33IXcAAAAODWKU1XgxA4GHQv/Ob3DQUcDCD1yw93IDQAAAN8oTgXJaR0MOhdV4/QOB4CqIzdwInIDAADgDxSnXI7OReg5qcPBUXAAJyM3Qo/cAAAAbkdxKgh2P/pNxyJyyta1nTsbdDSAqiM34C9yAwAAuFG02Q1A5BxsHkUHwySse5zKhAkTlJqaqvj4eGVkZGj58uUVjnv06FE99thjSktLU3x8vDp16qQFCxZUaZqAL2y7zMO6x6mQGwAAJ6E4FSA7Hv1mB9c67PpZ2PF7byezZs1STk6OcnNztXLlSnXq1ElZWVnatWuXz/Effvhhvfrqq3rppZf0448/6rbbbtPll1+ur7/+OuhpInzs+Pux67bKiez6Wdjxe28n5AYAwGkoTjlU2c6sHXdo3YDPBicaN26chg4dquzsbLVt21aTJk1SzZo1NXXqVJ/jv/XWW3rwwQd1ySWXqGXLlho2bJguueQSPf/880FPEyA3rI3PBiciNwAATkNxKgB2OQrIzqt92Omzssv3326Ki4u1YsUKZWZmeoZFR0crMzNT+fn5Pt9TVFSk+Ph4r2E1atTQ559/HvQ0ER52+d3YaVvkdnb6rOzy/bcbcgMA4EQUpxyEo6r2xOfmTAcOHPB6FRX5vjnwnj17VFJSouTkZK/hycnJKigo8PmerKwsjRs3TuvWrVNpaakWLVqk999/Xzt37gx6mnAntj/2xOfmTOQGAMDNeFqfn6x+9I+dVPuzwxOanPIEprkHOyneqB6WaR85dFTSR2ratKnX8NzcXI0ZMyYk83jxxRc1dOhQtW7dWlFRUUpLS1N2djaXXlgMuYFwIzcih9wAACC8KE7ZHJ0L57FDZwOntm3bNiUkJHj+jovzXahISkpSTEyMCgsLvYYXFhYqJSXF53saNGiguXPn6siRI9q7d68aN26sBx54QC1btgx6mnAPcsN5yA1nIDcAAG7GZX1+sOrRbzoYzmbVz9eqvwerSUhI8HpV1MmIjY1Venq68vLyPMNKS0uVl5enbt26VTqP+Ph4NWnSRMeOHdO///1vXXbZZVWeJkLDqr8Tq25XEBpW/Xyt+nuwGnIDAOBmnDllU1bdAUVoHWwexZFwF8jJydHgwYPVpUsXde3aVePHj9fhw4eVnZ0tSRo0aJCaNGmisWPHSpKWLVumHTt2qHPnztqxY4fGjBmj0tJS3XfffX5PE+5DbrgDueEO5AYAwGkoTp2CFY/20cFwFyteruGUe4hYxcCBA7V7926NHj1aBQUF6ty5sxYsWOC5Me3WrVsVHf3Hia5HjhzRww8/rI0bN6p27dq65JJL9NZbb6lu3bp+TxPhY7XcIDPcx4oFKnIjtMgNAIDTUJyyEToY7mbFzgZCZ8SIERoxYoTPf1u8eLHX3z169NCPP/5YpWkiPChMwSqseGADoUVuAACchHtOVcJKnQw6GJCs9T2w0u8DQHlW2l7APFb6HpAbAACgIhSnbMBKO5YwH98HwJqs1PFmO4ET8X0AAABWR3GqAlbpZLBDCV+s8r2wyu8EwB+ssn2AtVjle0FuAAAAXyhOWZhVdiRhTXw/AJyM7QIqw/cDAABYFcUpH6xwVI8dSPjDCt8TK/xeALNZ4Xdghe0BrM8K3xMr/F4AAIC18LQ+C7LCjmOkFTUrDtm04rbGhmxadsBT/ACQG1VDbgAAAJiL4hQiJpQdiWDn49QOCB0NAE5kdm44NTMkcgMAAFgLxamTmH2quZOOfkeqUxGIk9vkpI6HmR2N/WlxStxQZMq8AbORG6Fjtdzw1R5yIzTIDQAAcCKKUxZi9w6G1ToV/nBasYoj4YC7kBuRR24AAACEHsUpi7BrB8OOHYvKnLg8du9wAHA2csMayA0AAICqozh1ArMuzbBbB8NpHYuK2LXDwVFwIHLIDf+QG9ZGbgAAALNFm90At7NLB6OoWbHn5UZ2W3Yzvldm33cHcAtywx7stuzkBgAAMBPFKRPZoYNht53rcLPT+rDD9wtAYOzwu7bTdjIS7LQ+7PD9AgAAzsRlffDJLjvSZilbP3a6bAMAwoncqBy5AQAAUDHOnPr/In1quVWPTtrpCK8VWH19Rfp7xiUacBNy4zirbwetxurri9wAAABmoDhlAit3MBAcK3c2rPp9A+A/q/6OrbrdswNyAwAA4A9c1gfL7hzbEZdtAHADciN0yA0AAADOnJIU2VPKrXY0kg5GeFhtvVrtewfYHbmBULPaerXa9w4AADgbxSmXsvLlBE5htXUcqY4G9w8BnMlq2zQncus6JjcAAADFqQiyylFIN+74mon1DSBY5IY7WWV9W+X7BwAAnI/ilMtYZYfXbayy3uloAPZhld+rVbZfbmOV9W6V7yEAAHA2bogeIWbv3FllJ9fNuOktAD
```

--------------------------------

### Get Current Year

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current year from a Date object.

```javascript
function GetCurrentYear(date) {
  return date.getFullYear();
}
```

--------------------------------

### Get Current Millisecond

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current millisecond (0-999) from a Date object.

```javascript
function GetCurrentMillisecond(date) {
  return date.getMilliseconds();
}
```

--------------------------------

### Get Current Second

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current second (0-59) from a Date object.

```javascript
function GetCurrentSecond(date) {
  return date.getSeconds();
}
```

--------------------------------

### Import PINA modules and utilities

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial18/tutorial.html

Imports necessary libraries and modules from PINA, including Trainer, solver interfaces, FeedForward model, and SupervisedProblem. It also sets up warnings and plotting utilities.

```python
import warnings
import torch
import matplotlib.pyplot as plt

warnings.filterwarnings("ignore")

from pina import Trainer
from pina.solver import SingleSolverInterface, SupervisedSolverInterface
from pina.model import FeedForward
from pina.problem.zoo import SupervisedProblem
```

--------------------------------

### Get Current Minute

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current minute (0-59) from a Date object.

```javascript
function GetCurrentMinute(date) {
  return date.getMinutes();
}
```

--------------------------------

### Instantiate and Inspect AdvectionProblem

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial16/tutorial.html

Demonstrates how to import and instantiate the AdvectionProblem from the PINA library. It also prints information about the problem's conditions, inheritance, and domain types.

```python
from pina.problem.zoo import AdvectionProblem

# defining the problem
problem = AdvectionProblem()

# some infos
print(
    f"The {problem.__class__.__name__} has {len(problem.conditions)} "
    f"conditions with names {list(problem.conditions.keys())} \n"
    "The problem inherits from "
    f"{([cls.__name__ for cls in problem.__class__.__bases__])} \n"
    f"and the domains are of type {type(problem.domains['t0']).__name__}"
)
```

--------------------------------

### Get Current Hour

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current hour (0-23) from a Date object.

```javascript
function GetCurrentHour(date) {
  return date.getHours();
}
```

--------------------------------

### Import Core PINA and Utility Libraries

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial8/tutorial.html

Imports essential libraries for the tutorial, including PINA's core components like Trainer, FeedForward models, SupervisedSolver, TorchOptimizer, and specific blocks like PODBlock and RBFBlock. It also imports standard Python libraries for plotting and numerical operations.

```python
import matplotlib
import matplotlib.pyplot as plt
import torch
import numpy as np
import warnings

from pina import Trainer
from pina.model import FeedForward
from pina.solver import SupervisedSolver
from pina.optim import TorchOptimizer
from pina.problem.zoo import SupervisedProblem
from pina.model.block import PODBlock, RBFBlock

warnings.filterwarnings("ignore")
```

--------------------------------

### Get Current Month

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current month (0-indexed) from a Date object.

```javascript
function GetCurrentMonth(date) {
  return date.getMonth();
}
```

--------------------------------

### Array Initialization in C++

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

Shows different ways to initialize arrays in C++, including direct initialization and using loops.

```cpp
#include <iostream>

int main() {
    // Direct initialization
    int arr1[5] = {10, 20, 30, 40, 50};

    // Initialization with a loop
    int arr2[3];
    for (int i = 0; i < 3; ++i) {
        arr2[i] = (i + 1) * 100;
    }

    std::cout << "arr1[2]: " << arr1[2] << std::endl;
    std::cout << "arr2[1]: " << arr2[1] << std::endl;

    return 0;
}
```

--------------------------------

### Get String Length

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Returns the number of characters in a string. This is a fundamental string property.

```javascript
function GetStringLength(str) {
  return str.length;
}
```

--------------------------------

### Configure and Train PINN Solver

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial1/tutorial.html

Sets up and trains a PINN solver using the Trainer class. It configures training parameters such as maximum epochs, logging, callbacks, accelerator, and data split ratios. Dependencies include the Trainer and MetricTracker from PINA.

```python
from pina.callbacks import MetricTracker
from pina.trainer import Trainer

# create the trainer
trainer = Trainer(
    solver=pinn,  # The PINN solver to be used for training
    max_epochs=1500,  # Maximum number of training epochs
    logger=True,  # Enables logging (default logger is CSVLogger)
    callbacks=[MetricTracker()],  # Tracks training metrics using MetricTracker
    accelerator="cpu",  # Specifies the computing device ("cpu", "gpu", ...)
    train_size=1.0,  # Fraction of the dataset used for training (100%)
    test_size=0.0,  # Fraction of the dataset used for testing (0%)
    val_size=0.0,  # Fraction of the dataset used for validation (0%)
    enable_model_summary=False,  # Disables model summary printing
)

# train
trainer.train()
```

--------------------------------

### Get Object Values

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves an array of a given object's own enumerable property values.

```javascript
function GetObjectValues(obj) {
  return Object.values(obj);
}
```

--------------------------------

### Get Current Day of Month

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current day of the month (1-indexed) from a Date object.

```javascript
function GetCurrentDayOfMonth(date) {
  return date.getDate();
}
```

--------------------------------

### Load and Inspect PyTorch Geometric QM7b Dataset

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial19/tutorial.html

Demonstrates loading the QM7b dataset using PyTorch Geometric and inspecting the first data object within the shuffled dataset. This shows how to integrate external graph datasets into a workflow.

```python
from torch_geometric.datasets import QM7b

dataset = QM7b(root="./tutorial_logs").shuffle()

# save the dataset
input_ = [data for data in dataset]
input_[0]
```

--------------------------------

### Get Object Keys

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves an array of a given object's own enumerable property names (keys).

```javascript
function GetObjectKeys(obj) {
  return Object.keys(obj);
}
```

--------------------------------

### Get Array Length

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Returns the number of elements in an array. This is a basic property of array data structures.

```javascript
function GetArrayLength(arr) {
  return arr.length;
}
```

--------------------------------

### Initialize and Train PINN Solver

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial17/tutorial.html

Sets up a PINN solver and trains it for a specified number of epochs. It uses a MetricTracker callback to monitor training progress. The trainer can utilize accelerators like 'cpu' or 'gpu'. Model summary can be enabled or disabled.

```python
from pina.solver import PINN
from pina.callback import MetricTracker

# define the solver
solver = PINN(poisson_problem, model)

# define trainer
trainer = Trainer(
    solver,
    max_epochs=1500,
    callbacks=[MetricTracker()],
    accelerator="cpu",
    enable_model_summary=False,
)

# train
trainer.train()
```

--------------------------------

### Get Current Date and Time

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the current date and time. This is often used for logging or timestamping.

```javascript
function GetCurrentDateTime() {
  return new Date();
}
```

--------------------------------

### HTML Widget Configuration (Jupyter)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial11/tutorial.html

Configuration for an HTML widget displaying training progress, including model name, module, version, and state. The state defines the HTML content with epoch and iteration details.

```json
{
  "model_name": "HTMLModel",
  "model_module": "@jupyter-widgets\/controls",
  "model_module_version": "2.0.0",
  "state": {
    "_dom_classes": [],
    "_model_module": "@jupyter-widgets\/controls",
    "_model_module_version": "2.0.0",
    "_model_name": "HTMLModel",
    "_view_count": null,
    "_view_module": "@jupyter-widgets\/controls",
    "_view_module_version": "2.0.0",
    "_view_name": "HTMLView",
    "description": "",
    "description_allow_html": false,
    "layout": "IPY_MODEL_702d1a2da9eb4056907f2aee81439764",
    "placeholder": "\u200b",
    "style": "IPY_MODEL_5201f9f136b54b8fbaf849d085b50021",
    "tabbable": null,
    "tooltip": null,
    "value": "Epoch\u200799:\u2007100%"
  }
}
```

--------------------------------

### Create a Supervised Learning Problem Instance

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial15/tutorial.html

Initializes a SupervisedProblem object from the PINA library, using the prepared input graph data and normalized target properties derived from the QM9 dataset.

```python
# build the problem
problem = SupervisedProblem(input_=input_, output_=target_)
```

--------------------------------

### File Reading in Python

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

A Python example for reading content from a file. This is essential for data input and persistence.

```python
try:
    with open('data.txt', 'r') as f:
        content = f.read()
        print(content)
except FileNotFoundError:
    print('File not found.')
```

--------------------------------

### Get Day of Week

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves the day of the week (0 for Sunday, 1 for Monday, etc.) from a Date object.

```javascript
function GetDayOfWeek(date) {
  return date.getDay();
}
```

--------------------------------

### Initialize PINA Trainer with default settings

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial11/tutorial.html

Initializes the PINA Trainer by passing the configured SupervisedSolver. The Trainer automatically selects the best available accelerator (TPU, IPU, HPU, GPU, MPS, CPU) by default.

```python
trainer = Trainer(solver=solver)
```

--------------------------------

### Get Object Entries

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial9/tutorial.html

Retrieves an array of a given object's own enumerable string-keyed property [key, value] pairs.

```javascript
function GetObjectEntries(obj) {
  return Object.entries(obj);
}
```

--------------------------------

### HTML Widget Model Configuration

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial11/tutorial.html

Defines the configuration for an HTML widget, including its model name, module, and version. It specifies the state of the HTML content, such as descriptions and associated layout and style models.

```json
{
  "model_name": "HTMLModel",
  "model_module": "@jupyter-widgets\/controls",
  "model_module_version": "2.0.0",
  "state": {
    "_dom_classes": [],
    "_model_module": "@jupyter-widgets\/controls",
    "_model_module_version": "2.0.0",
    "_model_name": "HTMLModel",
    "_view_count": null,
    "_view_module": "@jupyter-widgets\/controls",
    "_view_module_version": "2.0.0",
    "_view_name": "HTMLView",
    "description": "",
    "description_allow_html": false,
    "layout": "IPY_MODEL_6c2ae8a8b0d5471098c9194185b8e202",
    "placeholder": "\u200b",
    "style": "IPY_MODEL_d4617c3ffb8947b8b42749c571db47b9",
    "tabbable": null,
    "tooltip": null,
    "value": "\u20071\/1\u2007[00:00<00:00,\u200798.26it\/s,\u2007v_num=1,\u2007data_loss=124.0,\u2007train_loss=124.0]"
  }
}
```

--------------------------------

### Get Numeric Month Name (JavaScript)

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial13/tutorial.html

Retrieves the full English name of a month given its numeric index (0-11).

```javascript
function getNumericMonthName(month) {
  const monthNames = [
    "January", "February", "March", "April", "May", "June", "July",
    "August", "September", "October", "November", "December"
  ];
  return monthNames[month];
}
```

--------------------------------

### Handle generic operations

Source: https://github.com/mathlab/pina/blob/master/docs/source/tutorials/tutorial3/tutorial.html

This snippet demonstrates how to handle generic operations. It sets up handlers for performing common mathlab-specific operations. It defines the logic to be executed when those generic operations are initiated.

```Unknown
CiAgICAgICAgAABmoDhlAit3MBAcK3c2rPp9A+A/q/6OrbrdswNyAwAA4A9c1gfL7hzbEZdtAHADciN0yA0AAADOnJIU2VPKrXY0kg5GeFhtvVrtewfYHbmBULPaerXa9w4AADgbxSmXsvLlBE5htXUcqY4G9w8BnMlq2zQncus6JjcAAADFqQiyylFIN+74mon1DSBY5IY7WWV9W+X7BwAAnI/ilMtYZYfXbayy3uloAPZhld+rVbZfbmOV9W6V7yEAAHA2bogeIWbv3FllJ9fNuOktAD
```