| """Figure 1 — Task and heterogeneous graph overview (schematic). |
| |
| Hand-drawn schema with matplotlib patches: author/paper lanes, the three edge |
| types, a highlighted (author, paper) test pair and the binary output, plus a |
| data-scale annotation bar. No real graph is plotted — this is the task definition. |
| """ |
| from pathlib import Path |
| import matplotlib.pyplot as plt |
| from matplotlib.patches import FancyBboxPatch, FancyArrowPatch, Circle, Rectangle |
| from style import apply, save, PALETTE as C, COL2 |
|
|
| KEY = "fig1_graph_overview" |
| TITLE = "Figure 1. Task and heterogeneous graph overview" |
|
|
|
|
| def make(root, out): |
| apply() |
| fig, ax = plt.subplots(figsize=(COL2, 3.5)) |
| ax.set_xlim(0, 13); ax.set_ylim(0, 7); ax.axis("off") |
|
|
| def lane(x, w, color, title): |
| ax.add_patch(FancyBboxPatch((x, 2.2), w, 3.4, boxstyle="round,pad=0.1,rounding_size=0.2", |
| fc=color, ec=color, alpha=0.08, lw=1.5)) |
| ax.text(x + w / 2, 5.9, title, ha="center", fontsize=9.5, fontweight="bold", color=color) |
|
|
| lane(0.3, 3.4, C[0], "Authors (6,611)") |
| lane(9.1, 3.6, C[2], "Papers (79,937)") |
|
|
| authors = [("A1", 1.1, 4.8), ("A2", 2.6, 5.0), ("A3", 1.4, 3.4), ("A4", 2.9, 3.2), ("A5", 2.0, 4.1)] |
| papers = [("P1", 9.6, 4.9), ("P2", 11.0, 4.6), ("P3", 9.9, 3.3), ("P4", 11.2, 3.0), ("P5", 10.4, 4.0)] |
| for n, x, y in authors: |
| ax.add_patch(Circle((x, y), 0.30, fc=C[0], ec="white", lw=1.2, alpha=0.9)) |
| ax.text(x, y, n, ha="center", va="center", fontsize=7.5, color="white", fontweight="bold") |
| for n, x, y in papers: |
| ax.add_patch(Rectangle((x - 0.30, y - 0.26), 0.60, 0.52, fc=C[2], ec="white", lw=1.2, alpha=0.9)) |
| ax.text(x, y, n, ha="center", va="center", fontsize=7.5, color="white", fontweight="bold") |
|
|
| def edge(a, b, color, ls, lw=1.3, arrow=False): |
| sty = "-|>" if arrow else "-" |
| ax.add_patch(FancyArrowPatch(a, b, arrowstyle=sty, mutation_scale=11, |
| color=color, lw=lw, linestyle=ls, |
| connectionstyle="arc3,rad=0.04", alpha=0.85)) |
|
|
| |
| edge(authors[0][1:], papers[0][1:], C[0], "-") |
| edge(authors[4][1:], papers[2][1:], C[0], "-") |
| edge(authors[2][1:], papers[4][1:], C[0], "-") |
| edge(authors[1][1:], papers[1][1:], C[0], "-") |
| |
| edge(authors[0][1:], authors[4][1:], C[1], "--") |
| edge(authors[2][1:], authors[3][1:], C[1], "--") |
| |
| edge(papers[0][1:], papers[4][1:], C[3], ":", lw=1.6, arrow=True) |
| edge(papers[2][1:], papers[3][1:], C[3], ":", lw=1.6, arrow=True) |
|
|
| |
| ta, tp = authors[3][1:], papers[4][1:] |
| edge(ta, tp, C[5], "-", lw=2.6) |
| ax.text((ta[0] + tp[0]) / 2, (ta[1] + tp[1]) / 2 + 0.45, "test pair (author, paper)", |
| ha="center", fontsize=8, color=C[5], fontweight="bold") |
| |
| ax.add_patch(FancyBboxPatch((tp[0] + 0.7, tp[1] - 0.25), 1.7, 0.6, |
| boxstyle="round,pad=0.05,rounding_size=0.12", fc=C[5], ec="white")) |
| ax.text(tp[0] + 1.55, tp[1] + 0.05, "label {0,1}", ha="center", va="center", |
| fontsize=8, color="white", fontweight="bold") |
|
|
| |
| from matplotlib.lines import Line2D |
| leg = [ |
| Line2D([0], [0], color=C[0], lw=1.8, label="author–paper read/cite"), |
| Line2D([0], [0], color=C[1], lw=1.8, ls="--", label="author–author coauthorship"), |
| Line2D([0], [0], color=C[3], lw=1.8, ls=":", label="paper→paper citation (directed)"), |
| Line2D([0], [0], color=C[5], lw=2.6, label="test pair (predict)"), |
| ] |
| ax.legend(handles=leg, loc="lower center", bbox_to_anchor=(0.5, -0.04), |
| ncol=4, fontsize=7.2, handlelength=2.2, columnspacing=1.2) |
|
|
| |
| ax.text(6.5, 0.45, |
| "2,047,262 test pairs · metric: F1-score · edges: 9,663 coauthor / 327,113 citation / 682,421 read", |
| ha="center", fontsize=7.8, color="dimgray") |
| ax.set_title("Heterogeneous author–paper graph and link-prediction task", fontsize=10) |
| save(fig, KEY, out) |
| return dict(key=KEY, title=TITLE, status="ok", files=[f"{KEY}.pdf", f"{KEY}.png", f"{KEY}.svg"], |
| sources=["schematic (no real graph)"], caption=( |
| "Heterogeneous author–paper graph and link-prediction task. Nodes are authors " |
| "(circles, 6,611) and papers (squares, 79,937); relations are author–paper historical " |
| "read/cite, author–author coauthorship, and directed paper→paper citation. For each test " |
| "pair (author, paper) the model predicts a binary label; performance is measured by F1 over " |
| "2,047,262 test pairs.")) |
|
|
|
|
| if __name__ == "__main__": |
| from style import ensure_dirs |
| r = make(Path("."), ensure_dirs(Path("."))) |
| print(r["key"], r["status"]) |
|
|
