Index

Highway2Vec.

Highway2VecEmbedder(hidden_size=64, embedding_size=30)

Bases: Embedder

Highway2Vec Embedder.

PARAMETER	DESCRIPTION
hidden_size	Hidden size in encoder and decoder. Defaults to 64. TYPE: int DEFAULT: 64
embedding_size	Embedding size. Defaults to 30. TYPE: int DEFAULT: 30

Source code in srai/embedders/highway2vec/embedder.py

def __init__(self, hidden_size: int = 64, embedding_size: int = 30) -> None:
    """
    Init Highway2Vec Embedder.

    Args:
        hidden_size (int, optional): Hidden size in encoder and decoder. Defaults to 64.
        embedding_size (int, optional): Embedding size. Defaults to 30.
    """
    import_optional_dependencies(
        dependency_group="torch", modules=["torch", "pytorch_lightning"]
    )

    self._model: Optional[Highway2VecModel] = None
    self._hidden_size = hidden_size
    self._embedding_size = embedding_size
    self._is_fitted = False

transform(regions_gdf, features_gdf, joint_gdf)

Embed regions using features.

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/highway2vec/embedder.py

def transform(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
) -> pd.DataFrame:  # pragma: no cover
    """
    Embed regions using features.

    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.
    """
    import torch

    self._validate_indexes(regions_gdf, features_gdf, joint_gdf)
    self._check_is_fitted()
    features_df = self._remove_geometry_if_present(features_gdf)

    self._model.eval()  # type: ignore
    embeddings = self._model(torch.Tensor(features_df.values)).detach().numpy()  # type: ignore
    embeddings_df = pd.DataFrame(embeddings, index=features_df.index)
    embeddings_joint = joint_gdf.join(embeddings_df)
    embeddings_aggregated = embeddings_joint.groupby(level=[0]).mean()

    return embeddings_aggregated

fit(
    regions_gdf,
    features_gdf,
    joint_gdf,
    trainer_kwargs=None,
    dataloader_kwargs=None,
)

Fit the model to the 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
trainer_kwargs	Trainer kwargs. Defaults to None. TYPE: Optional[Dict[str, Any]] DEFAULT: None
dataloader_kwargs	Dataloader kwargs. Defaults to None. TYPE: Optional[Dict[str, Any]] DEFAULT: None

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/highway2vec/embedder.py

def fit(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
    trainer_kwargs: Optional[dict[str, Any]] = None,
    dataloader_kwargs: Optional[dict[str, Any]] = None,
) -> None:
    """
    Fit the model to the 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.
        trainer_kwargs (Optional[Dict[str, Any]], optional): Trainer kwargs. Defaults to None.
        dataloader_kwargs (Optional[Dict[str, Any]], optional): Dataloader kwargs.
            Defaults to None.

    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.
    """
    import pytorch_lightning as pl
    import torch
    from torch.utils.data import DataLoader

    self._validate_indexes(regions_gdf, features_gdf, joint_gdf)
    features_df = self._remove_geometry_if_present(features_gdf)

    num_features = len(features_df.columns)
    self._model = Highway2VecModel(
        n_features=num_features, n_hidden=self._hidden_size, n_embed=self._embedding_size
    )

    dataloader_kwargs = dataloader_kwargs or {}
    if "batch_size" not in dataloader_kwargs:
        dataloader_kwargs["batch_size"] = 128

    dataloader = DataLoader(torch.Tensor(features_df.values), **dataloader_kwargs)

    trainer_kwargs = trainer_kwargs or {}
    if "max_epochs" not in trainer_kwargs:
        trainer_kwargs["max_epochs"] = 10

    trainer = pl.Trainer(**trainer_kwargs)
    trainer.fit(self._model, dataloader)
    self._is_fitted = True

fit_transform(
    regions_gdf,
    features_gdf,
    joint_gdf,
    trainer_kwargs=None,
    dataloader_kwargs=None,
)

Fit the model to the data and return the embeddings.

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
trainer_kwargs	Trainer kwargs. Defaults to None. TYPE: Optional[Dict[str, Any]] DEFAULT: None
dataloader_kwargs	Dataloader kwargs. Defaults to None. TYPE: Optional[Dict[str, Any]] DEFAULT: None

RETURNS	DESCRIPTION
DataFrame	pd.DataFrame: Region embeddings.

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/highway2vec/embedder.py

def fit_transform(
    self,
    regions_gdf: gpd.GeoDataFrame,
    features_gdf: gpd.GeoDataFrame,
    joint_gdf: gpd.GeoDataFrame,
    trainer_kwargs: Optional[dict[str, Any]] = None,
    dataloader_kwargs: Optional[dict[str, Any]] = None,
) -> pd.DataFrame:
    """
    Fit the model to the data and return the embeddings.

    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.
        trainer_kwargs (Optional[Dict[str, Any]], optional): Trainer kwargs. Defaults to None.
        dataloader_kwargs (Optional[Dict[str, Any]], optional): Dataloader kwargs.
            Defaults to None.

    Returns:
        pd.DataFrame: Region embeddings.

    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.fit(regions_gdf, features_gdf, joint_gdf, trainer_kwargs, dataloader_kwargs)
    return self.transform(regions_gdf, features_gdf, joint_gdf)

save(path)

Save the model to a directory.

PARAMETER	DESCRIPTION
path	Path to the directory. TYPE: Path

Source code in srai/embedders/highway2vec/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}
    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: Highway2VecEmbedder

Source code in srai/embedders/highway2vec/embedder.py

@classmethod
def load(cls, path: Union[Path, str]) -> "Highway2VecEmbedder":
    """
    Load the model from a directory.

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

    Returns:
        Hex2VecEmbedder: The loaded embedder.
    """
    return cls._load(path, Highway2VecModel)

Highway2VecModel(
    n_features, n_hidden=64, n_embed=30, lr=0.001
)

Bases: Model

Autoencoder based embedding model for highway2vec.

PARAMETER	DESCRIPTION
n_features	Number of features. TYPE: int
n_hidden	Number of hidden units. Defaults to 64. TYPE: int DEFAULT: 64
n_embed	Embedding size. Defaults to 30. TYPE: int DEFAULT: 30
lr	Learning rate. Defaults to 1e-3. TYPE: float DEFAULT: 0.001

Source code in srai/embedders/highway2vec/model.py

def __init__(self, n_features: int, n_hidden: int = 64, n_embed: int = 30, lr: float = 1e-3):
    """
    Init Highway2VecModel.

    Args:
        n_features (int): Number of features.
        n_hidden (int, optional): Number of hidden units. Defaults to 64.
        n_embed (int, optional): Embedding size. Defaults to 30.
        lr (float, optional): Learning rate. Defaults to 1e-3.
    """
    import_optional_dependencies(
        dependency_group="torch", modules=["torch", "pytorch_lightning"]
    )
    from torch import nn

    super().__init__()

    self.save_hyperparameters()

    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),
    )
    self.n_features = n_features
    self.n_hidden = n_hidden
    self.n_embed = n_embed
    self.lr = lr

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/highway2vec/model.py

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

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

training_step(batch, batch_idx)

Training step.

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

Source code in srai/embedders/highway2vec/model.py

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

    Args:
        batch (torch.Tensor): Batch.
        batch_idx (int): Batch index.
    """
    return self._common_step(batch, batch_idx, "train")

configure_optimizers()

Configure optimizer.

Source code in srai/embedders/highway2vec/model.py

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

    optimizer = torch.optim.Adam(self.parameters(), lr=self.lr)
    return optimizer