def _build_graph(self, target, commands, outs):
import networkx
from dvc.stage import Stage
from dvc.repo.graph import get_pipeline
target_stage = Stage.load(self.repo, target)
G = get_pipeline(self.repo.pipelines, target_stage)
nodes = set()
for stage in networkx.dfs_preorder_nodes(G, target_stage):
if commands:
if stage.cmd is None:
continue
nodes.add(stage.cmd)
elif outs:
for out in stage.outs:
nodes.add(str(out))
else:
nodes.add(stage.relpath)
edges = []
for from_stage, to_stage in networkx.edge_dfs(G, target_stage):
if commands:
if to_stage.cmd is None:
continue
edges.append((from_stage.cmd, to_stage.cmd))
elif outs:
for from_out in from_stage.outs:
for to_out in to_stage.outs:
edges.append((str(from_out), str(to_out)))
else:
edges.append((from_stage.relpath, to_stage.relpath))
return list(nodes), edges, networkx.is_tree(G)
def _build_graph(self, target, commands=False, outs=False):
import networkx
from dvc import dvcfile
from dvc.repo.graph import get_pipeline
from dvc.utils import parse_target
path, name = parse_target(target)
target_stage = dvcfile.Dvcfile(self.repo, path).stages[name]
G = get_pipeline(self.repo.pipelines, target_stage)
nodes = set()
for stage in networkx.dfs_preorder_nodes(G, target_stage):
if commands:
if stage.cmd is None:
continue
nodes.add(stage.cmd)
elif not outs:
nodes.add(stage.addressing)
edges = []
for from_stage, to_stage in networkx.edge_dfs(G, target_stage):
if commands:
if to_stage.cmd is None:
continue
edges.append((from_stage.cmd, to_stage.cmd))
elif not outs:
edges.append((from_stage.addressing, to_stage.addressing))
if outs:
nodes, edges = self._build_output_graph(G, target_stage)
return list(nodes), edges, networkx.is_tree(G)
def _build(G, target=None, full=False, outs=False):
import networkx as nx
from dvc.repo.graph import get_pipeline, get_pipelines
if target:
H = get_pipeline(get_pipelines(G), target)
if not full:
descendants = nx.descendants(G, target)
descendants.add(target)
H.remove_nodes_from(set(G.nodes()) - descendants)
else:
H = G
if outs:
G = nx.DiGraph()
for stage in H.nodes:
G.add_nodes_from(stage.outs)
for from_stage, to_stage in nx.edge_dfs(H):
G.add_edges_from([(from_out, to_out)
for from_out in from_stage.outs
for to_out in to_stage.outs])
H = G
def _relabel(node):
from dvc.stage import Stage
return node.addressing if isinstance(node, Stage) else str(node)
return nx.relabel_nodes(H, _relabel, copy=False)
def _build(G, target=None, full=False):
import networkx as nx
from dvc.repo.graph import get_pipeline, get_pipelines
if target:
H = get_pipeline(get_pipelines(G), target)
if not full:
descendants = nx.descendants(G, target)
descendants.add(target)
H.remove_nodes_from(set(G.nodes()) - descendants)
else:
H = G
def _relabel(stage):
return stage.addressing
return nx.relabel_nodes(H, _relabel, copy=False)
def __build_graph(self, target, commands, outs):
import networkx
from dvc.stage import Stage
from dvc.repo.graph import get_pipeline
stage = Stage.load(self.repo, target)
node = relpath(stage.path, self.repo.root_dir)
G = get_pipeline(self.repo.pipelines, node)
stages = networkx.get_node_attributes(G, "stage")
nodes = []
for n in G:
stage = stages[n]
if commands:
if stage.cmd is None:
continue
nodes.append(stage.cmd)
elif outs:
for out in stage.outs:
nodes.append(str(out))
else:
nodes.append(stage.relpath)
edges = []
for e in G.edges():
from_stage = stages[e[0]]
to_stage = stages[e[1]]
if commands:
if to_stage.cmd is None:
continue
edges.append((from_stage.cmd, to_stage.cmd))
elif outs:
for from_out in from_stage.outs:
for to_out in to_stage.outs:
edges.append((str(from_out), str(to_out)))
else:
edges.append((from_stage.relpath, to_stage.relpath))
return nodes, edges, networkx.is_tree(G)