Process Data

Date published: 26/09/23

bin.process.log_results(tracking_uri: str, experiment_prefix: str, grn_name: str, feature_matrix: DataFrame, edge_list: DataFrame) → None

Log experiment results to the experiment tracker.

Args:

tracking_uri (str):

The tracking URI.

experiment_prefix (str):

The experiment name prefix.

grn_name (str):

The name of the GRN.

feature_matrix (pd.DataFrame):

The feature matrix.

edge_list (pd.DataFrame):

The edge list.

bin.process.main(config: DictConfig) → None

The main entry point for the plotting pipeline.

Args:

config (DictConfig):

The pipeline configuration.

bin.process.process_network(feature_matrix: DataFrame, edge_list: DataFrame, from_col: str, to_col: str, len_component: int = 5) → tuple[DataFrame, DataFrame]

Construct a graph from edge list data.

Args:

feature_matrix (pd.DataFrame):

The feature matrix.

edge_list (pd.DataFrame):

The edge list.

from_col (str):

The “from” column name.

to_col (str):

The “to” column name.

len_component (int, optional):

The minimum size of a subgraph to filter out. Defaults to 5.

Returns:

tuple[pd.DataFrame, pd.DataFrame]:

The processed graph as a feature matrix and edge list.