Update private self-contained Congress Space bundle

README.md

@@ -1,31 +1,30 @@
----
-title: Congress Public Records Slice
-emoji: 🔎
-colorFrom: green
-colorTo: yellow
-sdk: gradio
-sdk_version: "5.23.1"
-python_version: "3.11"
-app_file: app.py
-pinned: false
----
-
-
-# Congress Public Records Slice Space
-
-Neutral Records explorer for a public-record slice of congressional money-and-power linkages.
-
-## Runtime Notes
-
-- This Space first checks for a bundled local `dataset_bundle` inside the Space repo, then falls back to the configured Hugging Face dataset repo.
-- For local testing, set the `PUBLIC_RELEASE_LOCAL_ROOT` environment variable to the release root folder before launching `app.py`.
-- The Space is intentionally neutral and does not assign guilt, wrongdoing, intent, or causality.
-
-## Required Caveats
-
-- This release is a slice of public-record data, not a complete accounting of all potentially relevant data.
-- Future releases may update or expand this slice as source recovery, parsing, and evidence linkage improve.
-- This release does not assign guilt, wrongdoing, intent, or causality to any person or organization.
-- The release shows public-record overlaps, timing, and linkage strength, not proof of illegality or corruption.
-- Some rows remain review-tier or include unresolved official source references and should be read with those labels in mind.
+---
+title: Congress Public Records Slice
+emoji: 🔎
+colorFrom: green
+colorTo: yellow
+sdk: gradio
+sdk_version: "5.23.1"
+python_version: "3.11"
+app_file: app.py
+pinned: false
+---
+
+# Congress Public Records Slice Space
+
+Neutral Records explorer for a public-record slice of congressional money-and-power linkages.
+
+## Runtime Notes
+
+- This Space first checks for a bundled local `dataset_bundle` inside the Space repo, then falls back to the configured Hugging Face dataset repo.
+- For local testing, set the `PUBLIC_RELEASE_LOCAL_ROOT` environment variable to the release root folder before launching `app.py`.
+- The Space is intentionally neutral and does not assign guilt, wrongdoing, intent, or causality.
+
+## Required Caveats
+
+- This release is a slice of public-record data, not a complete accounting of all potentially relevant data.
+- Future releases may update or expand this slice as source recovery, parsing, and evidence linkage improve.
+- This release does not assign guilt, wrongdoing, intent, or causality to any person or organization.
+- The release shows public-record overlaps, timing, and linkage strength, not proof of illegality or corruption.
+- Some rows remain review-tier or include unresolved official source references and should be read with those labels in mind.
 - The public package includes verification summaries and SHA-backed artifact indexes, but it does not include the full internal raw corpus, so external verification is bounded by what is published here.

public_copy.json

@@ -4,6 +4,7 @@
   "subtitle": "Neutral Records explorer for a public-record slice of congressional money-and-power linkages.",
   "dataset_repo_id": "cjc0013/cmp-data",
   "space_repo_id": "cjc0013/cmp",
+  "welcome_markdown": "# Congress Public Records Slice\n\nStart with the **Network Graph** tab.\n\n- Search one House member name first.\n- Green dots are House members, rust dots are funding recipients, and gold dots are sectors.\n- Lines show public-record support in this released slice; thicker lines mean more supporting rows.\n- Use **Explore** and **Event Detail** to inspect the underlying rows, source URLs, and SHA-backed artifacts.\n\nThis is an exploration tool, not an accusation tool.",
   "landing_markdown": "# Congress Public Records Slice\n\nA neutral, review-oriented slice of House public-record linkages across financial disclosures, sector overlap, and community project funding recipient relationships.\n\n- This release is a slice of public-record data, not a complete accounting of all potentially relevant data.\n- Future releases may update or expand this slice as source recovery, parsing, and evidence linkage improve.\n- This release does not assign guilt, wrongdoing, intent, or causality to any person or organization.\n- The release shows public-record overlaps, timing, and linkage strength, not proof of illegality or corruption.\n- Some rows remain review-tier or include unresolved official source references and should be read with those labels in mind.\n- The public package includes verification summaries and SHA-backed artifact indexes, but it does not include the full internal raw corpus, so external verification is bounded by what is published here.",
   "downloads_markdown": "## Downloads\n\n- Dataset repo id: `cjc0013/cmp-data`\n- Space repo id: `cjc0013/cmp`\n\nUse the dataset bundle files for direct review, CSV download, and SHA-backed source checks.",
   "dataset_bundle_prefix": "dataset_bundle"

public_space_app.py

@@ -245,6 +245,18 @@ def _consistency_summary_markdown(consistency: Dict[str, Any]) -> str:
     )
 
 
+def _embed_html_document(document_html: str, *, height: int = 760) -> str:
+    escaped = html.escape(document_html, quote=True)
+    return (
+        "<div style=\"border: 1px solid #d6d0c4; border-radius: 12px; overflow: hidden; background: #fbf7ee;\">"
+        f"<iframe srcdoc=\"{escaped}\" "
+        "style=\"width: 100%; border: 0; background: #fbf7ee;\" "
+        f"height=\"{int(height)}\" "
+        "sandbox=\"allow-scripts allow-same-origin allow-popups allow-downloads\"></iframe>"
+        "</div>"
+    )
+
+
 def _render_graph(nodes: pd.DataFrame, edges: pd.DataFrame) -> str:
     if edges.empty:
         return "<div style=\"padding: 1rem; border: 1px solid #d6d0c4; background: #fffdf8; color: #3a3a3a;\">No relationships match the current filters.</div>"
@@ -332,7 +344,7 @@ def _render_graph(nodes: pd.DataFrame, edges: pd.DataFrame) -> str:
             color=edge_style["color"],
             dashes=edge_style["dashes"],
         )
-    return network.generate_html(notebook=False)
+    return _embed_html_document(network.generate_html(notebook=False))
 
 
 def _event_detail(events: pd.DataFrame, provenance: pd.DataFrame, event_id: str) -> Tuple[str, pd.DataFrame]:
@@ -421,18 +433,7 @@ def build_app(copy_path: str | Path):
     overview_member_limit = int(graph_defaults.get("overview_member_limit", 8))
 
     with gr.Blocks(title=copy_payload.get("title", "Congress Public Records Slice")) as app:
-        gr.Markdown(copy_payload.get("landing_markdown", ""))
-        with gr.Tab("Explore"):
-            with gr.Row():
-                member_query = gr.Textbox(label="Member name or slug")
-                event_type = gr.Dropdown(label="Event type", choices=event_type_choices, value="all")
-                score_label = gr.Dropdown(label="Score label", choices=score_label_choices, value="all")
-                text_query = gr.Textbox(label="Issuer or sector search")
-            explore_df = gr.Dataframe(value=events.head(100), interactive=False)
-            def _update_events(member_query: str, event_type: str, score_label: str, text_query: str):
-                return _filter_events(events, member_query, event_type, score_label, text_query)
-            for control in (member_query, event_type, score_label, text_query):
-                control.change(_update_events, [member_query, event_type, score_label, text_query], explore_df)
+        gr.Markdown(copy_payload.get("welcome_markdown", copy_payload.get("landing_markdown", "")))
         with gr.Tab("Network Graph"):
             gr.Markdown(_graph_intro_markdown(data["graph_config"]))
             with gr.Row():
@@ -453,6 +454,17 @@ def build_app(copy_path: str | Path):
             for control in (family, member_graph_query, target_query, graph_score, review_status, hide_unresolved_only, max_edges):
                 control.change(_update_graph, [family, member_graph_query, target_query, graph_score, review_status, hide_unresolved_only, max_edges], [graph_html, graph_df])
             app.load(_update_graph, [family, member_graph_query, target_query, graph_score, review_status, hide_unresolved_only, max_edges], [graph_html, graph_df])
+        with gr.Tab("Explore"):
+            with gr.Row():
+                member_query = gr.Textbox(label="Member name or slug")
+                event_type = gr.Dropdown(label="Event type", choices=event_type_choices, value="all")
+                score_label = gr.Dropdown(label="Score label", choices=score_label_choices, value="all")
+                text_query = gr.Textbox(label="Issuer or sector search")
+            explore_df = gr.Dataframe(value=events.head(100), interactive=False)
+            def _update_events(member_query: str, event_type: str, score_label: str, text_query: str):
+                return _filter_events(events, member_query, event_type, score_label, text_query)
+            for control in (member_query, event_type, score_label, text_query):
+                control.change(_update_events, [member_query, event_type, score_label, text_query], explore_df)
         with gr.Tab("Event Detail"):
             event_id = gr.Dropdown(label="Event id", choices=event_id_choices, value=event_id_choices[0] if event_id_choices else None)
             event_detail_md = gr.Markdown()

requirements.txt

@@ -1,3 +1,2 @@
-pandas>=2.2.0
-pyvis>=0.3.2
-
+pandas>=2.2.0
+pyvis>=0.3.2