A newer version of the Streamlit SDK is available:
1.39.0
Table of Contents
main
:orange[PINN]
PINN.pinns
PINNd_p Objects
class PINNd_p(nn.Module)
$d \mapsto P$
PINNhd_ma Objects
class PINNhd_ma(nn.Module)
$h,d \mapsto m_a $
PINNT_ma Objects
class PINNT_ma(nn.Module)
$ m_a, U \mapsto T$
:orange[utils]
utils.test
utils.dataset_loader
get_dataset
def get_dataset(raw: bool = False,
sample_size: int = 1000,
name: str = 'dataset.pkl',
source: str = 'dataset.csv',
boundary_conditions: list = None) -> _pickle
Gets augmented dataset
Arguments:
rawbool, optional - either to use source data or augmented. Defaults to False.sample_sizeint, optional - sample size. Defaults to 1000.namestr, optional - name of wanted dataset. Defaults to 'dataset.pkl'.boundary_conditionslist,optional - y1,y2,x1,x2.
Returns:
_pickle- pickle buffer
utils.ndgan
DCGAN Objects
class DCGAN()
define_discriminator
def define_discriminator(inputs=8)
function to return the compiled discriminator model
generate_latent_points
def generate_latent_points(latent_dim, n)
generate points in latent space as input for the generator
define_gan
def define_gan(generator, discriminator)
define the combined generator and discriminator model
summarize_performance
def summarize_performance(epoch, generator, discriminator, latent_dim, n=200)
evaluate the discriminator and plot real and fake samples
train_gan
def train_gan(g_model,
d_model,
gan_model,
latent_dim,
num_epochs=2500,
num_eval=2500,
batch_size=2)
function to train gan model
utils.data_augmentation
dataset Objects
class dataset()
Creates dataset from input source
__init__
def __init__(number_samples: int,
name: str,
source: str,
boundary_conditions: list = None)
summary
Arguments:
number_samplesint - descriptionnamestr - descriptionsourcestr - descriptionboundary_conditionslist - y1,y2,x1,x2
:orange[nets]
nets.envs
SCI Objects
class SCI()
data_flow
def data_flow(columns_idx: tuple = (1, 3, 3, 5),
idx: tuple = None,
split_idx: int = 800) -> torch.utils.data.DataLoader
Data prep pipeline
Arguments:
columns_idxtuple, optional - Columns to be selected (sliced 1:2 3:4) for feature fitting. Defaults to (1,3,3,5).idxtuple, optional - 2|3 indexes to be selected for feature fitting. Defaults to None. Use either idx or columns_idx (for F:R->R idx, for F:R->R2 columns_idx) split_idx (int) : Index to split for training
Returns:
torch.utils.data.DataLoader- Torch native dataloader
init_seed
def init_seed(seed)
Initializes seed for torch optional()
compile
def compile(columns: tuple = None,
idx: tuple = None,
optim: torch.optim = torch.optim.AdamW,
loss: nn = nn.L1Loss,
model: nn.Module = dmodel,
custom: bool = False) -> None
Builds model, loss, optimizer. Has defaults
Arguments:
columnstuple, optional - Columns to be selected for feature fitting. Defaults to (1,3,3,5). optim - torch Optimizer loss - torch Loss function (nn)
train
def train(epochs: int = 10) -> None
Train model If sklearn instance uses .fit()
inference
def inference(X: tensor, model_name: str = None) -> np.ndarray
Inference of (pre-)trained model
Arguments:
Xtensor - your data in domain of train
Returns:
np.ndarray- predictions
RCI Objects
class RCI(SCI)
data_flow
def data_flow(columns_idx: tuple = (1, 3, 3, 5),
idx: tuple = None,
split_idx: int = 800) -> torch.utils.data.DataLoader
Data prep pipeline
Arguments:
columns_idxtuple, optional - Columns to be selected (sliced 1:2 3:4) for feature fitting. Defaults to (1,3,3,5).idxtuple, optional - 2|3 indexes to be selected for feature fitting. Defaults to None. Use either idx or columns_idx (for F:R->R idx, for F:R->R2 columns_idx) split_idx (int) : Index to split for training
Returns:
torch.utils.data.DataLoader- Torch native dataloader
compile
def compile(columns: tuple = None,
idx: tuple = (3, 1),
optim: torch.optim = torch.optim.AdamW,
loss: nn = nn.L1Loss,
model: nn.Module = PINNd_p,
lr: float = 0.001) -> None
Builds model, loss, optimizer. Has defaults
Arguments:
columnstuple, optional - Columns to be selected for feature fitting. Defaults to None.idxtuple, optional - indexes to be selected Default (3,1) optim - torch Optimizer loss - torch Loss function (nn)
nets.dense
Net Objects
class Net(nn.Module)
4 layer model, different activations and neurons count on layer
__init__
def __init__(input_dim: int = 2, hidden_dim: int = 200)
Init
Arguments:
input_dimint, optional - Defaults to 2.hidden_dimint, optional - Defaults to 200.
nets.design
B_field_norm
def B_field_norm(Bmax, L, k=16, plot=True)
Returns vec B_z
Arguments:
Bmaxany - maximum B in thruster k - magnetic field profile number
nets.deep_dense
dmodel Objects
class dmodel(nn.Module)
4 layers Torch model. Relu activations, hidden layers are same size.
__init__
def __init__(in_features=1, hidden_features=200, out_features=1)
Init
Arguments:
in_featuresint, optional - Input features. Defaults to 1.hidden_featuresint, optional - Hidden dims. Defaults to 200.out_featuresint, optional - Output dims. Defaults to 1.