def from_numpy(X: np.ndarray,
dist_type_schema: Dict[int, str] = None,
lasso_beta: float = 0.0,
ridge_beta: float = 0.0,
use_bias: bool = False,
hidden_layer_units: Iterable[int] = None,
w_threshold: float = None,
max_iter: int = 100,
tabu_edges: List[Tuple[int, int]] = None,
tabu_parent_nodes: List[int] = None,
tabu_child_nodes: List[int] = None,
**kwargs) -> StructureModel:
"""
Learn the `StructureModel`, the graph structure with lasso regularisation
describing conditional dependencies between variables in data presented as a numpy array.
Based on DAGs with NO TEARS.
@inproceedings{zheng2018dags,
author = {Zheng, Xun and Aragam, Bryon and Ravikumar, Pradeep and Xing, Eric P.},
booktitle = {Advances in Neural Information Processing Systems},
title = {{DAGs with NO TEARS: Continuous Optimization for Structure Learning}},
year = {2018},
codebase = {https://github.com/xunzheng/notears}
}
Args:
X: 2d input data, axis=0 is data rows, axis=1 is data columns. Data must be row oriented.
dist_type_schema: The dist type schema corresponding to the passed in data X.
It maps the positional column in X to the string alias of a dist type.
A list of alias names can be found in ``dist_type/__init__.py``.
If None, assumes that all data in X is continuous.
lasso_beta: Constant that multiplies the lasso term (l1 regularisation).
NOTE when using nonlinearities, the l1 loss only applies to the dag_layer.
use_bias: Whether to fit a bias parameter in the NOTEARS algorithm.
ridge_beta: Constant that multiplies the ridge term (l2 regularisation).
When using nonlinear layers use of this parameter is recommended.
hidden_layer_units: An iterable where its length determine the number of layers used,
and the numbers determine the number of nodes used for the layer in order.
w_threshold: fixed threshold for absolute edge weights.
max_iter: max number of dual ascent steps during optimisation.
tabu_edges: list of edges(from, to) not to be included in the graph.
tabu_parent_nodes: list of nodes banned from being a parent of any other nodes.
tabu_child_nodes: list of nodes banned from being a child of any other nodes.
**kwargs: additional arguments for NOTEARS MLP model
Returns:
StructureModel: a graph of conditional dependencies between data variables.
Raises:
ValueError: If X does not contain data.
ValueError: If schema does not correspond to columns.
"""
# n examples, d properties
if not X.size:
raise ValueError("Input data X is empty, cannot learn any structure")
logging.info("Learning structure using 'NOTEARS' optimisation.")
# Check array for NaN or inf values
check_array(X)
if dist_type_schema is not None:
# make sure that there is one provided key per column
if set(range(X.shape[1])).symmetric_difference(
set(dist_type_schema.keys())):
raise ValueError(
"Difference indices and expected indices. Got {} schema".
format(dist_type_schema))
# if dist_type_schema is None, assume all columns are continuous, else init the alias mapped object
dist_types = (
[DistTypeContinuous(idx=idx)
for idx in np.arange(X.shape[1])] if dist_type_schema is None else [
dist_type_aliases[alias](idx=idx)
for idx, alias in dist_type_schema.items()
])
# shape of X before preprocessing
_, d_orig = X.shape
# perform dist type pre-processing (i.e. column expansion)
for dist_type in dist_types:
# NOTE: preprocess_X must be called first to perform possible column expansions
X = dist_type.preprocess_X(X)
tabu_edges = dist_type.preprocess_tabu_edges(tabu_edges)
tabu_parent_nodes = dist_type.preprocess_tabu_nodes(tabu_parent_nodes)
tabu_child_nodes = dist_type.preprocess_tabu_nodes(tabu_child_nodes)
# shape of X after preprocessing
_, d = X.shape
# if None or empty, convert into a list with single item
if hidden_layer_units is None:
hidden_layer_units = [0]
elif isinstance(hidden_layer_units, list) and not hidden_layer_units:
hidden_layer_units = [0]
# if no hidden layer units, still take 1 iteration step with bounds
hidden_layer_bnds = hidden_layer_units[0] if hidden_layer_units[0] else 1
# Flip i and j because Pytorch flattens the vector in another direction
bnds = [
(0, 0) if i == j else
(0, 0) if tabu_edges is not None and (i, j) in tabu_edges else
(0, 0) if tabu_parent_nodes is not None and i in tabu_parent_nodes else
(0, 0) if tabu_child_nodes is not None and j in tabu_child_nodes else
(None, None) for j in range(d) for _ in range(hidden_layer_bnds)
for i in range(d)
]
model = NotearsMLP(n_features=d,
dist_types=dist_types,
hidden_layer_units=hidden_layer_units,
lasso_beta=lasso_beta,
ridge_beta=ridge_beta,
bounds=bnds,
use_bias=use_bias,
**kwargs)
model.fit(X, max_iter=max_iter)
sm = StructureModel(model.adj)
if w_threshold:
sm.remove_edges_below_threshold(w_threshold)
# extract the mean effect and add as edge attribute
mean_effect = model.adj_mean_effect
for u, v, edge_dict in sm.edges.data(True):
sm.add_edge(
u,
v,
origin="learned",
weight=edge_dict["weight"],
mean_effect=mean_effect[u, v],
)
# set bias as node attribute
bias = model.bias
for node in sm.nodes():
value = None
if bias is not None:
value = bias[node]
sm.nodes[node]["bias"] = value
# attach each dist_type object to corresponding node(s)
for dist_type in dist_types:
sm = dist_type.add_to_node(sm)
# preserve the structure_learner as a graph attribute
sm.graph["structure_learner"] = model
# collapse the adj down and store as graph attr
adj = deepcopy(model.adj)
for dist_type in dist_types:
adj = dist_type.collapse_adj(adj)
sm.graph["graph_collapsed"] = StructureModel(adj[:d_orig, :d_orig])
return sm
def from_numpy(
X: np.ndarray,
lasso_beta: float = 0.0,
ridge_beta: float = 0.0,
use_bias: bool = False,
hidden_layer_units: Iterable[int] = None,
w_threshold: float = None,
max_iter: int = 100,
tabu_edges: List[Tuple[int, int]] = None,
tabu_parent_nodes: List[int] = None,
tabu_child_nodes: List[int] = None,
**kwargs
) -> StructureModel:
"""
Learn the `StructureModel`, the graph structure with lasso regularisation
describing conditional dependencies between variables in data presented as a numpy array.
Based on DAGs with NO TEARS.
@inproceedings{zheng2018dags,
author = {Zheng, Xun and Aragam, Bryon and Ravikumar, Pradeep and Xing, Eric P.},
booktitle = {Advances in Neural Information Processing Systems},
title = {{DAGs with NO TEARS: Continuous Optimization for Structure Learning}},
year = {2018},
codebase = {https://github.com/xunzheng/notears}
}
Args:
X: 2d input data, axis=0 is data rows, axis=1 is data columns. Data must be row oriented.
lasso_beta: Constant that multiplies the lasso term (l1 regularisation).
NOTE when using nonlinearities, the l1 loss only applies to the dag_layer.
use_bias: Whether to fit a bias parameter in the NOTEARS algorithm.
ridge_beta: Constant that multiplies the ridge term (l2 regularisation).
When using nonlinear layers use of this parameter is recommended.
hidden_layer_units: An iterable where its length determine the number of layers used,
and the numbers determine the number of nodes used for the layer in order.
w_threshold: fixed threshold for absolute edge weights.
max_iter: max number of dual ascent steps during optimisation.
tabu_edges: list of edges(from, to) not to be included in the graph.
tabu_parent_nodes: list of nodes banned from being a parent of any other nodes.
tabu_child_nodes: list of nodes banned from being a child of any other nodes.
**kwargs: additional arguments for NOTEARS MLP model
Returns:
StructureModel: a graph of conditional dependencies between data variables.
Raises:
ValueError: If X does not contain data.
"""
# n examples, d properties
if not X.size:
raise ValueError("Input data X is empty, cannot learn any structure")
logging.info("Learning structure using 'NOTEARS' optimisation.")
# Check array for NaN or inf values
check_array(X)
_, d = X.shape
# if None or empty, convert into a list with single item
if hidden_layer_units is None:
hidden_layer_units = [0]
elif isinstance(hidden_layer_units, list) and not hidden_layer_units:
hidden_layer_units = [0]
# if no hidden layer units, still take 1 iteration step with bounds
hidden_layer_bnds = hidden_layer_units[0] if hidden_layer_units[0] else 1
# Flip i and j because Pytorch flattens the vector in another direction
bnds = [
(0, 0)
if i == j
else (0, 0)
if tabu_edges is not None and (i, j) in tabu_edges
else (0, 0)
if tabu_parent_nodes is not None and i in tabu_parent_nodes
else (0, 0)
if tabu_child_nodes is not None and j in tabu_child_nodes
else (None, None)
for j in range(d)
for _ in range(hidden_layer_bnds)
for i in range(d)
]
model = NotearsMLP(
n_features=d,
hidden_layer_units=hidden_layer_units,
lasso_beta=lasso_beta,
ridge_beta=ridge_beta,
bounds=bnds,
use_bias=use_bias,
**kwargs
)
model.fit(X, max_iter=max_iter)
sm = StructureModel(model.adj)
if w_threshold:
sm.remove_edges_below_threshold(w_threshold)
mean_effect = model.adj_mean_effect
# extract the mean effect and add as edge attribute
for u, v, edge_dict in sm.edges.data(True):
sm.add_edge(
u,
v,
origin="learned",
weight=edge_dict["weight"],
mean_effect=mean_effect[u, v],
)
# set bias as node attribute
bias = model.bias
for node in sm.nodes():
value = None
if bias is not None:
value = bias[node]
sm.nodes[node]["bias"] = value
# preserve the structure_learner as a graph attribute
sm.graph["structure_learner"] = model
return sm