Index

Models.

GTFS2VecEmbedder(
    hidden_size=48,
    embedding_size=64,
    skip_autoencoder=False,
)

Bases: Embedder

GTFS2Vec Embedder.

PARAMETER	DESCRIPTION
hidden_size	Hidden size in encoder and decoder. Defaults to 48. TYPE: int DEFAULT: 48
embedding_size	Embedding size. Defaults to 64. TYPE: int DEFAULT: 64
skip_autoencoder	Skip using autoencoder as part of embedding. TYPE: bool DEFAULT: False

Source code in srai/embedders/gtfs2vec/embedder.py

def __init__(
    self, hidden_size: int = 48, embedding_size: int = 64, skip_autoencoder: bool = False
) -> None:
    """
    Init GTFS2VecEmbedder.

    Args:
        hidden_size (int, optional): Hidden size in encoder and decoder. Defaults to 48.
        embedding_size (int, optional): Embedding size. Defaults to 64.
        skip_autoencoder (bool, optional): Skip using autoencoder as part of embedding.
        Defaults to False.
    """
    import_optional_dependencies(
        dependency_group="torch", modules=["torch", "pytorch_lightning"]
    )
    self._model: Optional[GTFS2VecModel] = None
    self._hidden_size = hidden_size
    self._embedding_size = embedding_size
    self._skip_autoencoder = skip_autoencoder
    self._is_fitted = False

transform(regions_gdf, features_gdf, joint_gdf)

Embed a given data.

PARAMETER	DESCRIPTION
regions_gdf	Region indexes and geometries. TYPE: GeoDataFrame
features_gdf	Feature indexes, geometries and feature values. TYPE: GeoDataFrame
joint_gdf	Joiner result with region-feature multi-index. TYPE: GeoDataFrame

RETURNS	DESCRIPTION
DataFrame	pd.DataFrame: Embedding and geometry index for each region in regions_gdf.

RAISES	DESCRIPTION
ValueError	If any of the gdfs index names is None.
ValueError	If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
ValueError	If index levels in gdfs don't overlap correctly.
ValueError	If number of features is incosistent with the model.
ModelNotFitException	If model is not fit.

Source code in srai/embedders/gtfs2vec/embedder.py

def transform(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
) -> pd.DataFrame:
    """
    Embed a given data.

    Args:
        regions_gdf (gpd.GeoDataFrame): Region indexes and geometries.
        features_gdf (gpd.GeoDataFrame): Feature indexes, geometries and feature values.
        joint_gdf (gpd.GeoDataFrame): Joiner result with region-feature multi-index.

    Returns:
        pd.DataFrame: Embedding and geometry index for each region in regions_gdf.

    Raises:
        ValueError: If any of the gdfs index names is None.
        ValueError: If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
        ValueError: If index levels in gdfs don't overlap correctly.
        ValueError: If number of features is incosistent with the model.
        ModelNotFitException: If model is not fit.
    """
    self._validate_indexes(regions_gdf, features_gdf, joint_gdf)
    features = self._prepare_features(regions_gdf, features_gdf, joint_gdf)

    if self._skip_autoencoder:
        return features
    return self._embed(features)

fit(regions_gdf, features_gdf, joint_gdf)

Fit model to a given data.

PARAMETER	DESCRIPTION
regions_gdf	Region indexes and geometries. TYPE: GeoDataFrame
features_gdf	Feature indexes, geometries and feature values. TYPE: GeoDataFrame
joint_gdf	Joiner result with region-feature multi-index. TYPE: GeoDataFrame

RAISES	DESCRIPTION
ValueError	If any of the gdfs index names is None.
ValueError	If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
ValueError	If index levels in gdfs don't overlap correctly.

Source code in srai/embedders/gtfs2vec/embedder.py

def fit(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
) -> None:
    """
    Fit model to a given data.

    Args:
        regions_gdf (gpd.GeoDataFrame): Region indexes and geometries.
        features_gdf (gpd.GeoDataFrame): Feature indexes, geometries and feature values.
        joint_gdf (gpd.GeoDataFrame): Joiner result with region-feature multi-index.

    Raises:
        ValueError: If any of the gdfs index names is None.
        ValueError: If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
        ValueError: If index levels in gdfs don't overlap correctly.
    """
    self._validate_indexes(regions_gdf, features_gdf, joint_gdf)
    features = self._prepare_features(regions_gdf, features_gdf, joint_gdf)

    if not self._skip_autoencoder:
        self._model = self._train_model_unsupervised(features)

fit_transform(regions_gdf, features_gdf, joint_gdf)

Fit model and transform a given data.

PARAMETER	DESCRIPTION
regions_gdf	Region indexes and geometries. TYPE: GeoDataFrame
features_gdf	Feature indexes, geometries and feature values. TYPE: GeoDataFrame
joint_gdf	Joiner result with region-feature multi-index. TYPE: GeoDataFrame

RETURNS	DESCRIPTION
DataFrame	pd.DataFrame: Embedding and geometry index for each region in regions_gdf.

RAISES	DESCRIPTION
ValueError	If any of the gdfs index names is None.
ValueError	If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
ValueError	If index levels in gdfs don't overlap correctly.

Source code in srai/embedders/gtfs2vec/embedder.py

def fit_transform(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
) -> pd.DataFrame:
    """
    Fit model and transform a given data.

    Args:
        regions_gdf (gpd.GeoDataFrame): Region indexes and geometries.
        features_gdf (gpd.GeoDataFrame): Feature indexes, geometries and feature values.
        joint_gdf (gpd.GeoDataFrame): Joiner result with region-feature multi-index.

    Returns:
        pd.DataFrame: Embedding and geometry index for each region in regions_gdf.

    Raises:
        ValueError: If any of the gdfs index names is None.
        ValueError: If joint_gdf.index is not of type pd.MultiIndex or doesn't have 2 levels.
        ValueError: If index levels in gdfs don't overlap correctly.
    """
    self._validate_indexes(regions_gdf, features_gdf, joint_gdf)
    features = self._prepare_features(regions_gdf, features_gdf, joint_gdf)

    if self._skip_autoencoder:
        return features
    else:
        self._model = self._train_model_unsupervised(features)
        return self._embed(features)

save(path)

Save the model to a directory.

PARAMETER	DESCRIPTION
path	Path to the directory. TYPE: Path

Source code in srai/embedders/gtfs2vec/embedder.py

def save(self, path: Union[Path, str]) -> None:
    """
    Save the model to a directory.

    Args:
        path (Path): Path to the directory.
    """
    embedder_config = {
        "hidden_size": self._hidden_size,
        "embedding_size": self._embedding_size,
        "skip_autoencoder": self._skip_autoencoder,
    }
    self._save(path, embedder_config)

load(path)

classmethod

Load the model from a directory.

PARAMETER	DESCRIPTION
path	Path to the directory. TYPE: Path

RETURNS	DESCRIPTION
Hex2VecEmbedder	The loaded embedder. TYPE: GTFS2VecEmbedder

Source code in srai/embedders/gtfs2vec/embedder.py

@classmethod
def load(cls, path: Union[Path, str]) -> "GTFS2VecEmbedder":
    """
    Load the model from a directory.

    Args:
        path (Path): Path to the directory.

    Returns:
        Hex2VecEmbedder: The loaded embedder.
    """
    return cls._load(path, GTFS2VecModel)

GTFS2VecModel(n_features, n_hidden=48, n_embed=64)

Bases: Model

Autoencoder based embedding model for gtfs2vec.

PARAMETER	DESCRIPTION
n_features	Number of features. TYPE: int
n_hidden	Number of hidden units. Defaults to 48. TYPE: int DEFAULT: 48
n_embed	Embedding size. Defaults to 64. TYPE: int DEFAULT: 64

Source code in srai/embedders/gtfs2vec/model.py

def __init__(
    self,
    n_features: int,
    n_hidden: int = 48,
    n_embed: int = 64,
) -> None:
    """
    Init GTFS2VecModel.

    Args:
        n_features (int): Number of features.
        n_hidden (int, optional): Number of hidden units. Defaults to 48.
        n_embed (int, optional): Embedding size. Defaults to 64.
    """
    super().__init__()
    import_optional_dependencies(
        dependency_group="torch", modules=["torch", "pytorch_lightning"]
    )
    from torch import nn

    self.n_features = n_features
    self.n_hidden = n_hidden
    self.n_embed = n_embed
    self.encoder = nn.Sequential(
        nn.Linear(n_features, n_hidden), nn.ReLU(), nn.Linear(n_hidden, n_embed)
    )
    self.decoder = nn.Sequential(
        nn.Linear(n_embed, n_hidden), nn.ReLU(), nn.Linear(n_hidden, n_features)
    )

get_config()

Get model config.

Source code in srai/embedders/_base.py

def get_config(self) -> dict[str, Any]:
    """Get model config."""
    model_config = {
        k: v
        for k, v in vars(self).items()
        if k[0] != "_"
        and k
        not in (
            "training",
            "prepare_data_per_node",
            "allow_zero_length_dataloader_with_multiple_devices",
        )
    }

    return model_config

save(path)

Save the model to a directory.

PARAMETER	DESCRIPTION
path	Path to the directory. TYPE: Path

Source code in srai/embedders/_base.py

def save(self, path: Union[Path, str]) -> None:
    """
    Save the model to a directory.

    Args:
        path (Path): Path to the directory.
    """
    import torch

    torch.save(self.state_dict(), path)

load(path, **kwargs)

classmethod

Load model from a file.

PARAMETER	DESCRIPTION
path	Path to the file. TYPE: Union[Path, str]
**kwargs	Additional kwargs to pass to the model constructor. TYPE: dict DEFAULT: {}

Source code in srai/embedders/_base.py

@classmethod
def load(cls, path: Union[Path, str], **kwargs: Any) -> "Model":
    """
    Load model from a file.

    Args:
        path (Union[Path, str]): Path to the file.
        **kwargs (dict): Additional kwargs to pass to the model constructor.
    """
    import torch

    if isinstance(path, str):
        path = Path(path)

    model = cls(**kwargs)
    model.load_state_dict(torch.load(path))
    return model

forward(x)

Forward pass.

PARAMETER	DESCRIPTION
x	Input tensor. TYPE: Tensor

Source code in srai/embedders/gtfs2vec/model.py

def forward(self, x: "torch.Tensor") -> "torch.Tensor":
    """
    Forward pass.

    Args:
        x (torch.Tensor): Input tensor.
    """
    embedding: torch.Tensor = self.encoder(x)
    return embedding

configure_optimizers()

Configure optimizer.

Source code in srai/embedders/gtfs2vec/model.py

def configure_optimizers(self) -> "torch.optim.Optimizer":
    """Configure optimizer."""
    import torch

    optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)
    return optimizer

training_step(batch, batch_idx)

Training step.

PARAMETER	DESCRIPTION
batch	Batch. TYPE: Tensor
batch_idx	Batch index. TYPE: Any

Source code in srai/embedders/gtfs2vec/model.py

def training_step(self, batch: "torch.Tensor", batch_idx: Any) -> "torch.Tensor":
    """
    Training step.

    Args:
        batch (torch.Tensor): Batch.
        batch_idx (Any): Batch index.
    """
    from torch.nn import functional as F

    x = batch
    z = self.encoder(x)
    x_hat = self.decoder(z)
    loss = F.mse_loss(x_hat, x)
    self.log("train_loss", loss)
    return loss