# %%
import json
import pandas as pd
from pathlib import Path
base = Path("/mnt/data")
# -----------------------------
# Source: encode sector -> services/standards/anchors used (✓)
# Derived from the user's UCLS sector write-up in the conversation.
# -----------------------------
sectors = {
"Defense & Security": {
"services": {"NaaS","AaaS","RegaaS","IDaaS","ValaaS","OaaS","TaaS","RaaS","ProvAaaS","VaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"STIX/TAXII","RDF/JSON-LD","W3C VC"},
"anchors": {"Sequences","Strains","Specimens","Digital Credentials"},
},
"Manufacturing & Supply Chain": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","VaaS","DaaS","AnaaS","VizaaS"},
"standards": {"GS1 EPCIS","RDF/JSON-LD","W3C VC"},
"anchors": {"Batch Certificates","Cultures/Sequences"},
},
# The user's taxonomy merges Manufacturing & Supply Chain into one sector.
# We'll treat "Supply Chain" as an alias node pointing to same attributes for overlay clarity.
"Supply Chain": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","VaaS","DaaS","AnaaS","VizaaS"},
"standards": {"GS1 EPCIS","RDF/JSON-LD","W3C VC"},
"anchors": {"Batch Certificates","Cultures/Sequences"},
},
"Smart Cities & Infrastructure": {
"services": {"NaaS","IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"OGC","RDF","JSON-LD","W3C VC"},
"anchors": {"Digital Certificates","Relevés/Specimens"},
},
"Energy Systems": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","VaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"RDF/OWL","CFIHOS","OPC UA","ISO 15926","W3C VC"},
"anchors": {"Digital Credentials","Material Samples"},
},
"Climate & Geoscience": {
"services": {"OaaS","TaaS","RaaS","ProvAaaS","InteropaaS","DaaS","AnaaS","VizaaS"},
"standards": {"OGC","NetCDF","RDF","JSON-LD"},
"anchors": {"Type Relevé","Specimens","Isotope Anchors"},
},
}
# -----------------------------
# Helper: compute overlay edges between triplets using intersection metrics
# -----------------------------
def build_overlay(group_name, sector_names):
nodes = []
edges = []
# Collect nodes with attributes
for s in sector_names:
meta = sectors[s]
nodes.append({
"sector": s,
"services": sorted(meta["services"]),
"standards": sorted(meta["standards"]),
"anchors": sorted(meta["anchors"]),
})
# Pairwise edges with shared attributes
for i in range(len(sector_names)):
for j in range(i+1, len(sector_names)):
a = sectors[sector_names[i]]
b = sectors[sector_names[j]]
shared_services = sorted(a["services"].intersection(b["services"]))
shared_standards = sorted(a["standards"].intersection(b["standards"]))
shared_anchors = sorted(a["anchors"].intersection(b["anchors"]))
edges.append({
"group": group_name,
"source": sector_names[i],
"target": sector_names[j],
"shared_services": shared_services,
"shared_services_count": len(shared_services),
"shared_standards": shared_standards,
"shared_standards_count": len(shared_standards),
"shared_anchors": shared_anchors,
"shared_anchors_count": len(shared_anchors),
"overlap_score": len(shared_services) + 0.5*len(shared_standards) + 0.5*len(shared_anchors),
})
return nodes, edges
# Define overlay groups
overlay_specs = {
"Defense–Manufacturing–SupplyChain": ["Defense & Security","Manufacturing & Supply Chain","Supply Chain"],
"SmartCities–Energy–Climate": ["Smart Cities & Infrastructure","Energy Systems","Climate & Geoscience"],
}
manifest = {
"name": "UCLS Overlays",
"version": "1.0",
"generated": True,
"groups": {},
}
all_edges = []
all_nodes = []
for group, members in overlay_specs.items():
nodes, edges = build_overlay(group, members)
all_nodes += [{"group": group, **n} for n in nodes]
all_edges += edges
manifest["groups"][group] = {"members": members, "edge_count": len(edges)}
# -----------------------------
# Output CSV/JSON for each group + combined
# -----------------------------
def write_group_files(group, members):
nodes = [n for n in all_nodes if n["group"] == group]
edges = [e for e in all_edges if e["group"] == group]
# CSV edges
df_e = pd.DataFrame(edges)
df_n = pd.DataFrame(nodes)
e_csv = base / f"overlay_{group}_edges.csv"
e_json = base / f"overlay_{group}_edges.json"
n_csv = base / f"overlay_{group}_nodes.csv"
n_json = base / f"overlay_{group}_nodes.json"
df_e.to_csv(e_csv, index=False)
df_n.to_csv(n_csv, index=False)
e_json.write_text(json.dumps(edges, indent=2))
n_json.write_text(json.dumps(nodes, indent=2))
return dict(edge_csv=str(e_csv), edge_json=str(e_json), node_csv=str(n_csv), node_json=str(n_json))
file_index = {}
for group, members in overlay_specs.items():
file_index[group] = write_group_files(group, members)
# Combined files
edges_df = pd.DataFrame(all_edges)
nodes_df = pd.DataFrame(all_nodes)
edges_df.to_csv(base / "overlays_all_edges.csv", index=False)
nodes_df.to_csv(base / "overlays_all_nodes.csv", index=False)
Path(base / "overlays_manifest.json").write_text(json.dumps({**manifest, "files": file_index}, indent=2))
# -----------------------------
# Append to WordPress markdown if present, else create a small section
# -----------------------------
md_path = base / "ucls_directory_wordpress.md"
append_md = []
append_md.append("\n\n---\n\n## Inter-Sector Overlays (UCLS)\n")
append_md.append("> Auto-generated overlay graphs showing shared services, standards, and anchors.\n\n")
def links_for_group(group, files):
return (
f"### {group.replace('–',' — ')}\n"
f"- **Edges (CSV):** {Path(files['edge_csv']).as_posix()}\n"
f"- **Edges (JSON):** {Path(files['edge_json']).as_posix()}\n"
f"- **Nodes (CSV):** {Path(files['node_csv']).as_posix()}\n"
f"- **Nodes (JSON):** {Path(files['node_json']).as_posix()}\n"
)
for group, files in file_index.items():
append_md.append(links_for_group(group, files))
append_md.append(
"\n### Combined\n"
f"- **All Overlays — Edges (CSV):** {(base/'overlays_all_edges.csv').as_posix()}\n"
f"- **All Overlays — Nodes (CSV):** {(base/'overlays_all_nodes.csv').as_posix()}\n"
f"- **Manifest (JSON):** {(base/'overlays_manifest.json').as_posix()}\n"
)
if md_path.exists():
# Append
with md_path.open("a") as f:
f.write("".join(append_md))
updated = True
else:
# Create minimal MD with overlay section only
md_path.write_text("# UCLS Inter-Sector Overlays\n" + "".join(append_md))
updated = False
# Return a quick summary of what was written
summary = {
"markdown_appended": updated,
"markdown_path": md_path.as_posix(),
"overlay_files": file_index,
"combined": {
"edges_csv": (base/"overlays_all_edges.csv").as_posix(),
"nodes_csv": (base/"overlays_all_nodes.csv").as_posix(),
"manifest_json": (base/"overlays_manifest.json").as_posix()
}
}
summary
# Re-run generation after kernel reset
import json
import pandas as pd
from pathlib import Path
base = Path("/mnt/data")
sectors = {
"Defense & Security": {
"services": {"NaaS","AaaS","RegaaS","IDaaS","ValaaS","OaaS","TaaS","RaaS","ProvAaaS","VaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"STIX/TAXII","RDF/JSON-LD","W3C VC"},
"anchors": {"Sequences","Strains","Specimens","Digital Credentials"},
},
"Manufacturing & Supply Chain": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","VaaS","DaaS","AnaaS","VizaaS"},
"standards": {"GS1 EPCIS","RDF/JSON-LD","W3C VC"},
"anchors": {"Batch Certificates","Cultures/Sequences"},
},
"Supply Chain": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","VaaS","DaaS","AnaaS","VizaaS"},
"standards": {"GS1 EPCIS","RDF/JSON-LD","W3C VC"},
"anchors": {"Batch Certificates","Cultures/Sequences"},
},
"Smart Cities & Infrastructure": {
"services": {"NaaS","IDaaS","OaaS","TaaS","ProvAaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"OGC","RDF","JSON-LD","W3C VC"},
"anchors": {"Digital Certificates","Relevés/Specimens"},
},
"Energy Systems": {
"services": {"IDaaS","OaaS","TaaS","ProvAaaS","VaaS","InteropaaS","ACaaS","DaaS","AnaaS","VizaaS"},
"standards": {"RDF/OWL","CFIHOS","OPC UA","ISO 15926","W3C VC"},
"anchors": {"Digital Credentials","Material Samples"},
},
"Climate & Geoscience": {
"services": {"OaaS","TaaS","RaaS","ProvAaaS","InteropaaS","DaaS","AnaaS","VizaaS"},
"standards": {"OGC","NetCDF","RDF","JSON-LD"},
"anchors": {"Type Relevé","Specimens","Isotope Anchors"},
},
}
def build_overlay(group_name, sector_names):
nodes = []
edges = []
for s in sector_names:
meta = sectors[s]
nodes.append({
"sector": s,
"services": sorted(meta["services"]),
"standards": sorted(meta["standards"]),
"anchors": sorted(meta["anchors"]),
})
for i in range(len(sector_names)):
for j in range(i+1, len(sector_names)):
a = sectors[sector_names[i]]
b = sectors[sector_names[j]]
shared_services = sorted(a["services"].intersection(b["services"]))
shared_standards = sorted(a["standards"].intersection(b["standards"]))
shared_anchors = sorted(a["anchors"].intersection(b["anchors"]))
edges.append({
"group": group_name,
"source": sector_names[i],
"target": sector_names[j],
"shared_services": shared_services,
"shared_services_count": len(shared_services),
"shared_standards": shared_standards,
"shared_standards_count": len(shared_standards),
"shared_anchors": shared_anchors,
"shared_anchors_count": len(shared_anchors),
"overlap_score": len(shared_services) + 0.5*len(shared_standards) + 0.5*len(shared_anchors),
})
return nodes, edges
overlay_specs = {
"Defense–Manufacturing–SupplyChain": ["Defense & Security","Manufacturing & Supply Chain","Supply Chain"],
"SmartCities–Energy–Climate": ["Smart Cities & Infrastructure","Energy Systems","Climate & Geoscience"],
}
manifest = {"name": "UCLS Overlays","version": "1.0","generated": True,"groups": {}}
all_edges, all_nodes = [], []
for group, members in overlay_specs.items():
nodes, edges = build_overlay(group, members)
all_nodes += [{"group": group, **n} for n in nodes]
all_edges += edges
manifest["groups"][group] = {"members": members, "edge_count": len(edges)}
def write_group_files(group, members):
nodes = [n for n in all_nodes if n["group"] == group]
edges = [e for e in all_edges if e["group"] == group]
df_e = pd.DataFrame(edges)
df_n = pd.DataFrame(nodes)
e_csv = base / f"overlay_{group}_edges.csv"
e_json = base / f"overlay_{group}_edges.json"
n_csv = base / f"overlay_{group}_nodes.csv"
n_json = base / f"overlay_{group}_nodes.json"
df_e.to_csv(e_csv, index=False)
df_n.to_csv(n_csv, index=False)
e_json.write_text(json.dumps(edges, indent=2))
n_json.write_text(json.dumps(nodes, indent=2))
return dict(edge_csv=str(e_csv), edge_json=str(e_json), node_csv=str(n_csv), node_json=str(n_json))
file_index = {group: write_group_files(group, members) for group, members in overlay_specs.items()}
# Combined
edges_df = pd.DataFrame(all_edges)
nodes_df = pd.DataFrame(all_nodes)
edges_df.to_csv(base / "overlays_all_edges.csv", index=False)
nodes_df.to_csv(base / "overlays_all_nodes.csv", index=False)
(base / "overlays_manifest.json").write_text(json.dumps({**manifest, "files": file_index}, indent=2))
# Append markdown links
md_path = base / "ucls_directory_wordpress.md"
append_md = []
append_md.append("\n\n---\n\n## Inter-Sector Overlays (UCLS)\n")
append_md.append("> Auto-generated overlay graphs showing shared services, standards, and anchors.\n\n")
for group, files in file_index.items():
append_md.append(f"### {group.replace('–',' — ')}\n")
append_md.append(f"- **Edges (CSV):** {Path(files['edge_csv']).as_posix()}\n")
append_md.append(f"- **Edges (JSON):** {Path(files['edge_json']).as_posix()}\n")
append_md.append(f"- **Nodes (CSV):** {Path(files['node_csv']).as_posix()}\n")
append_md.append(f"- **Nodes (JSON):** {Path(files['node_json']).as_posix()}\n\n")
append_md.append(
"### Combined\n"
f"- **All Overlays — Edges (CSV):** {(base/'overlays_all_edges.csv').as_posix()}\n"
f"- **All Overlays — Nodes (CSV):** {(base/'overlays_all_nodes.csv').as_posix()}\n"
f"- **Manifest (JSON):** {(base/'overlays_manifest.json').as_posix()}\n"
)
if md_path.exists():
with md_path.open("a") as f:
f.write("".join(append_md))
action = "appended to existing WordPress MD"
else:
md_path.write_text("# UCLS Inter-Sector Overlays\n" + "".join(append_md))
action = "created new overlay MD"
{
"action": action,
"wordpress_md": md_path.as_posix(),
"groups": file_index,
"combined": {
"edges_csv": (base/"overlays_all_edges.csv").as_posix(),
"nodes_csv": (base/"overlays_all_nodes.csv").as_posix(),
"manifest_json": (base/"overlays_manifest.json").as_posix()
}
}
