Skip to content

feat(treeplot): lay out the tree without igraph #7984

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kz930 wants to merge 1 commit into
base: main
Choose a base branch
from
+76 −14
Open

feat(treeplot): lay out the tree without igraph #7984

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
81 changes: 68 additions & 13 deletions ...c/main/scala/org/apache/texera/amber/operator/visualization/treeplot/TreePlotOpDesc.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,8 +72,6 @@ class TreePlotOpDesc extends PythonOperatorDescriptor {
|
|import plotly.graph_objects as go
|import plotly.io
|import igraph
|from igraph import Graph, EdgeSeq
|import pandas as pd
|import ast
|
Expand Down Expand Up @@ -108,6 +106,66 @@ class TreePlotOpDesc extends PythonOperatorDescriptor {
| )
| return annotations
|
| def build_tree_layout(self, edges):
| # Tidy top-down tree: depth picks the row, a leaf takes the next
| # free column and a parent sits centred over its own children.
| labels = []
| known = set()
| for parent, child in edges:
| for node in (parent, child):
| if node not in known:
| known.add(node)
| labels.append(node)
|
| children = {label: [] for label in labels}
| has_parent = set()
| seen = set()
| for parent, child in edges:
| if (parent, child) not in seen:
| seen.add((parent, child))
| children[parent].append(child)
| has_parent.add(child)
|
| depth = {}
| column = {}
| claimed = {}
| placed = set()
| next_column = 0
|
| def grow(root):
| nonlocal next_column
| placed.add(root)
| stack = [(root, 0, False)]
| while stack:
| node, level, folded = stack.pop()
| if folded:
| kids = claimed[node]
| if kids:
| column[node] = sum(column[kid] for kid in kids) / len(kids)
| else:
| column[node] = next_column
| next_column += 1
| continue
| depth[node] = level
| # A node belongs to whichever parent reaches it first, so a
| # cycle or a shared child is never laid out twice.
| kids = [kid for kid in children[node] if kid not in placed]
| placed.update(kids)
| claimed[node] = kids
| stack.append((node, level, True))
| for kid in reversed(kids):
| stack.append((kid, level + 1, False))
|
| for label in labels:
| if label not in placed and label not in has_parent:
| grow(label)
| # Whatever is left sits in a cycle that no root can reach.
| for label in labels:
| if label not in placed:
| grow(label)
| # The y-axis is inverted here so the tree grows top-down.
| return labels, [(column[label], -depth[label]) for label in labels]
|
| @overrides
| def process_table(self, table: Table, port: int) -> Iterator[Optional[TableLike]]:
| if table.empty:
Expand All @@ -127,14 +185,10 @@ class TreePlotOpDesc extends PythonOperatorDescriptor {
| yield {'html-content': self.render_error("No valid [parent, child] pairs found in column " + $edgeListColumn + ".")}
| return
|
| G = Graph.TupleList(edges, directed=True)
| labels = G.vs['name']
|
| layout_algorithm = 'rt'
| try:
| lay = G.layout(layout_algorithm)
| labels, coords = self.build_tree_layout(edges)
| except Exception as e:
| yield {'html-content': self.render_error(f"Layout algorithm '{layout_algorithm}' failed: {e}")}
| yield {'html-content': self.render_error(f"Tree layout failed: {e}")}
| return
|
| HORIZONTAL_DENSITY = 120
Expand All @@ -143,8 +197,8 @@ class TreePlotOpDesc extends PythonOperatorDescriptor {
| MIN_WIDTH = 800
| MIN_HEIGHT = 600
|
| if len(lay.coords) > 1:
| x_coords, y_coords = zip(*lay.coords)
| if len(coords) > 1:
| x_coords, y_coords = zip(*coords)
| x_range = max(x_coords) - min(x_coords)
| y_range = max(y_coords) - min(y_coords)
| plot_width = max(MIN_WIDTH, x_range * HORIZONTAL_DENSITY + PADDING)
Expand All @@ -153,12 +207,13 @@ class TreePlotOpDesc extends PythonOperatorDescriptor {
| plot_width = MIN_WIDTH
| plot_height = MIN_HEIGHT
|
| # Invert the y-axis to make the tree grow top-down.
| position = {k: (lay[k][0], -lay[k][1]) for k in range(len(labels))}
| position = {k: coords[k] for k in range(len(labels))}
| index_of = {label: k for k, label in enumerate(labels)}
|
| Xe = []
| Ye = []
| for edge in G.get_edgelist():
| for parent, child in edges:
| edge = (index_of[parent], index_of[child])
| Xe += [position[edge[0]][0], position[edge[1]][0], None]
| Ye += [position[edge[0]][1], position[edge[1]][1], None]
|
Expand Down
9 changes: 8 additions & 1 deletion ...st/scala/org/apache/texera/amber/operator/visualization/treeplot/TreePlotOpDescSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,13 @@ class TreePlotOpDescSpec extends AnyFlatSpec with BeforeAndAfter with Matchers {
val code = opDesc.generatePythonCode()
assert(carries(code, "edge_pairs"))
code should include("class ProcessTableOperator(UDFTableOperator)")
code should include("Graph.TupleList")
code should include("self.build_tree_layout(edges)")
}

// igraph is GPL v2, Category X under the ASF 3rd party license policy, so the
// layout has to stay something the repository can actually ship.
it should "not reach for igraph" in {
opDesc.edgeListColumn = "edge_pairs"
opDesc.generatePythonCode().toLowerCase should not include "igraph"
}
}
Loading