def naive_factorization(data=None,
node_id=0,
context=None,
scope=None,
**kwargs):
assert scope is not None, "No scope"
prod_node = Product()
prod_node.scope = scope
prod_node.id = node_id
y, x = get_YX(data, context.feature_size)
result = []
for i, rv in enumerate(scope):
prod_node.children.append(None)
data_slice = concatenate_yx(y[:, i].reshape(-1, 1), x)
result.append((
SplittingOperations.CREATE_LEAF_NODE,
{
"data": data_slice,
"parent_id": prod_node.id,
"pos": len(prod_node.children) - 1,
"scope": [rv],
},
))
return prod_node, result
def _deserialize_product(self, node, node_map):
child_ids = node.product.children
# Resolve references to child nodes by ID.
children = [node_map.get(id) for id in child_ids]
# Check all childs have been resolved.
assert None not in children, "Child node ID could not be resolved"
product = Product(children = children)
product.id = node.id
return product
def remove_non_informative_features(data=None,
node_id=0,
scope=None,
context=0,
uninformative_features_idx=None,
**kwargs):
assert uninformative_features_idx is not None, "parameter uninformative_features_idx can't be None"
prod_node = Product()
prod_node.scope = scope
prod_node.id = node_id
y, x = get_YX(data, context.feature_size)
non_zero_variance_rvs = []
non_zero_variance_idx = []
result = []
for idx, zero_var in enumerate(uninformative_features_idx):
rv = scope[idx]
if not zero_var:
non_zero_variance_rvs.append(rv)
non_zero_variance_idx.append(idx)
continue
prod_node.children.append(None)
data_slice = concatenate_yx(y[:, idx].reshape(-1, 1), x)
result.append((
SplittingOperations.CREATE_LEAF_NODE,
{
"data": data_slice,
"parent_id": prod_node.id,
"pos": len(prod_node.children) - 1,
"scope": [rv],
},
))
assert len(result) > 0
if len(non_zero_variance_idx) > 0:
prod_node.children.append(None)
result.append((
SplittingOperations.GET_NEXT_OP,
{
"data": concatenate_yx(data[:, non_zero_variance_idx], x),
"parent_id": prod_node.id,
"pos": len(prod_node.children) - 1,
"scope": non_zero_variance_rvs,
},
))
return prod_node, result
def create_product(data=None,
node_id=0,
parent_id=0,
pos=0,
context=None,
scope=None,
split_cols=None,
**kwargs):
assert split_cols is not None, "No split_cols lambda"
assert scope is not None, "No scope"
data_slices = split_cols(data, context, scope)
result = []
if len(data_slices) == 1:
result.append((
SplittingOperations.GET_NEXT_OP,
{
"data": data,
"parent_id": parent_id,
"pos": pos,
"no_independencies": True,
"scope": scope,
},
))
return None, result
node = Product()
node.scope.extend(scope)
node.id = node_id
for data_slice, scope_slice, _ in data_slices:
assert isinstance(scope_slice, list), "slice must be a list"
node.children.append(None)
result.append((
SplittingOperations.GET_NEXT_OP,
{
"data": data_slice,
"parent_id": node_id,
"pos": len(node.children) - 1,
"scope": scope_slice,
},
))
return node, result
def remove_non_informative_features(data=None,
node_id=0,
scope=None,
**kwargs):
prod_node = Product()
prod_node.scope = scope
prod_node.id = node_id
uninformative_features_idx = np.var(data[:, scope], 0) == 0
zero_variance_rvs = [s for s in scope]
result = []
for idx, zero_var in enumerate(uninformative_features_idx):
if not zero_var:
continue
prod_node.children.append(None)
rv = scope[idx]
data_slice = data[:, rv].reshape(-1, 1)
result.append((
SplittingOperations.CREATE_LEAF_NODE,
{
"data": data_slice,
"parent_id": node_id,
"pos": len(prod_node.children) - 1,
"scope": [rv],
},
))
del zero_variance_rvs[idx]
assert len(result) > 0
prod_node.children.append(None)
result.append((
SplittingOperations.GET_NEXT_OP,
{
"data": data[:, zero_variance_rvs],
"parent_id": node_id,
"pos": len(prod_node.children) - 1,
"scope": zero_variance_rvs,
},
))
return prod_node, result