Upload app.py

src/app.py

@@ -613,118 +613,118 @@ with tab_kg_exp:
     st.caption("kg_nodes를 탐색하고 임의 노드의 연결 관계를 시각화합니다. kg_edges는 DuckDB로 필요한 부분만 쿼리합니다.")
 
     try:
+        # spinner는 로딩만, UI는 spinner 밖에
         with st.spinner("KG 데이터 로딩 중... (최초 1회 후 캐시됩니다)"):
-            kg_nodes      = load_kg_nodes(data_dir_val)
+            kg_nodes_exp  = load_kg_nodes(data_dir_val)
             kg_edges_path = get_parquet_path("kg_edges.parquet", data_dir_val)
             enriched_path = get_parquet_path("citation_events_enriched.parquet", data_dir_val)
 
-            # ── 전체 노드 타입 분포 (kg_nodes만으로 계산)
-            col_a, col_b = st.columns([1,2])
-            with col_a:
-                st.subheader("Node Type Counts")
-                nt = kg_nodes["node_type"].value_counts().reset_index()
-                nt.columns = ["node_type","count"]
-                st.dataframe(nt, use_container_width=True, hide_index=True)
-
-                # Edge type 집계: DuckDB로 빠르게 계산
-                st.subheader("Edge Type Counts")
-                import duckdb
-                et = duckdb.execute(f"""
-                    SELECT edge_type, COUNT(*) AS count
-                    FROM read_parquet('{kg_edges_path}')
-                    GROUP BY edge_type ORDER BY count DESC
-                """).df()
-                st.dataframe(et, use_container_width=True, hide_index=True)
-
-            with col_b:
-                st.subheader("Node Type Distribution")
-                nt_fig = px.bar(nt, x="node_type", y="count", color="node_type",
-                                color_discrete_map=NODE_TYPE_COLORS)
-                nt_fig.update_layout(showlegend=False, xaxis_title="", yaxis_title="Count")
-                st.plotly_chart(nt_fig, use_container_width=True)
-
-            st.markdown("---")
-            st.subheader("Node Search & Ego Network")
-            exp_col1, exp_col2 = st.columns([1,3])
-            with exp_col1:
-                type_options = ["(all)"] + sorted(kg_nodes["node_type"].unique().tolist())
-                sel_type = st.selectbox("Filter by node type", type_options)
-                filtered_nodes = (kg_nodes if sel_type == "(all)"
-                                  else kg_nodes[kg_nodes["node_type"]==sel_type])
-                search_q = st.text_input("Search node label / DOI")
-                if search_q:
-                    filtered_nodes = filtered_nodes[
-                        filtered_nodes["label"].str.contains(search_q, case=False, na=False) |
-                        filtered_nodes["doi"].str.contains(search_q, case=False, na=False)
-                    ]
-
-                sample = filtered_nodes.head(100)
-                node_options = sample["node_id"].tolist()
-                if not node_options:
-                    st.warning("검색 결과가 없습니다.")
-                else:
-                    sel_node_id = st.selectbox(
-                        "Select node", node_options,
-                        format_func=lambda nid: sample.loc[sample["node_id"]==nid,"label"].iloc[0][:60],
-                    )
-                    sel_node_info = sample[sample["node_id"]==sel_node_id].iloc[0]
-                    st.markdown(f"**Type**: {sel_node_info.get('node_type','')}")
-                    st.markdown(f"**DOI**: {sel_node_info.get('doi','') or '-'}")
-                    st.markdown(f"**Publication**: {sel_node_info.get('publication_name','') or '-'}")
-                    st.markdown(f"**Group**: {sel_node_info.get('group','') or '-'}")
-                    st.markdown(f"**Cited by**: {fmt_num(sel_node_info.get('citedby_count',''))}")
-
-                    max_e = st.slider("Max edges shown", 20, 150, 60, key="kg_exp_max")
-                    if st.button("Show ego network", key="kg_exp_show"):
-                        with st.spinner("DuckDB로 엣지 쿼리 중..."):
-                            exp_edges = query_explorer_edges(sel_node_id, kg_edges_path, max_e)
-                        if exp_edges.empty:
-                            st.warning("연결된 엣지가 없습니다.")
-                        else:
-                            all_ids = set(exp_edges["source"].tolist()) | set(exp_edges["target"].tolist())
-                            exp_nodes = kg_nodes[kg_nodes["node_id"].isin(all_ids)]
-                            st.session_state["exp_nodes"] = exp_nodes
-                            st.session_state["exp_edges"] = exp_edges
-
-            with exp_col2:
-                if "exp_nodes" in st.session_state:
-                    en = st.session_state["exp_nodes"]
-                    ee = st.session_state["exp_edges"]
-                    st.caption(f"Nodes: {len(en)}  |  Edges: {len(ee)}")
-                    st.caption("🖱 Scroll: zoom  |  Drag: pan  |  Click node: info  |  ⛶ button: fullscreen")
-                    components.html(pyvis_from_kg(en, ee, height="740px"), height=760, scrolling=True)
-                else:
-                    st.info("왼쪽에서 노드를 선택하고 'Show ego network'를 클릭하세요.")
-
-            # ── Enriched 인사이트 (DuckDB 집계만)
-            st.markdown("---")
-            st.subheader("Enriched Citation Insights")
-            st.caption("citation_events_enriched: DuckDB로 집계 통계만 쿼리 (전체 로드 없음)")
-            with st.spinner("Enriched 통계 쿼리 중 (DuckDB)..."):
-                sem_df, field_df = query_enriched_stats(enriched_path)
-
-            if not sem_df.empty:
-                sem_df["label"] = sem_df["has_semantic_evidence"].map(
-                    {True:"With evidence", False:"Without evidence",
-                     1:"With evidence", 0:"Without evidence"})
-                col_s1, col_s2 = st.columns(2)
-                with col_s1:
+        # ── 전체 노드/엣지 타입 분포
+        col_a, col_b = st.columns([1, 2])
+        with col_a:
+            st.subheader("Node Type Counts")
+            nt = kg_nodes_exp["node_type"].value_counts().reset_index()
+            nt.columns = ["node_type", "count"]
+            st.dataframe(nt, use_container_width=True, hide_index=True)
+
+            st.subheader("Edge Type Counts")
+            import duckdb as _ddb
+            et = _ddb.execute(f"""
+                SELECT edge_type, COUNT(*) AS count
+                FROM read_parquet('{kg_edges_path}')
+                GROUP BY edge_type ORDER BY count DESC
+            """).df()
+            st.dataframe(et, use_container_width=True, hide_index=True)
+
+        with col_b:
+            st.subheader("Node Type Distribution")
+            nt_fig = px.bar(nt, x="node_type", y="count", color="node_type",
+                            color_discrete_map=NODE_TYPE_COLORS)
+            nt_fig.update_layout(showlegend=False, xaxis_title="", yaxis_title="Count")
+            st.plotly_chart(nt_fig, use_container_width=True)
+
+        # ── Node Search & Ego Network
+        st.markdown("---")
+        st.subheader("Node Search & Ego Network")
+        exp_col1, exp_col2 = st.columns([1, 3])
+        with exp_col1:
+            type_options = ["(all)"] + sorted(kg_nodes_exp["node_type"].unique().tolist())
+            sel_type = st.selectbox("Filter by node type", type_options)
+            filtered_nodes = (kg_nodes_exp if sel_type == "(all)"
+                              else kg_nodes_exp[kg_nodes_exp["node_type"] == sel_type])
+            search_q = st.text_input("Search node label / DOI")
+            if search_q:
+                filtered_nodes = filtered_nodes[
+                    filtered_nodes["label"].str.contains(search_q, case=False, na=False) |
+                    filtered_nodes["doi"].str.contains(search_q, case=False, na=False)
+                ]
+
+            sample = filtered_nodes.head(100)
+            node_options = sample["node_id"].tolist()
+            if not node_options:
+                st.warning("검색 결과가 없습니다.")
+            else:
+                sel_node_id = st.selectbox(
+                    "Select node", node_options,
+                    format_func=lambda nid: sample.loc[sample["node_id"] == nid, "label"].iloc[0][:60],
+                )
+                sel_node_info = sample[sample["node_id"] == sel_node_id].iloc[0]
+                st.markdown(f"**Type**: {sel_node_info.get('node_type', '')}")
+                st.markdown(f"**DOI**: {sel_node_info.get('doi', '') or '-'}")
+                st.markdown(f"**Publication**: {sel_node_info.get('publication_name', '') or '-'}")
+                st.markdown(f"**Group**: {sel_node_info.get('group', '') or '-'}")
+                st.markdown(f"**Cited by**: {fmt_num(sel_node_info.get('citedby_count', ''))}")
+
+                max_e = st.slider("Max edges shown", 20, 150, 60, key="kg_exp_max")
+                if st.button("Show ego network", key="kg_exp_show"):
+                    with st.spinner("DuckDB로 엣지 쿼리 중..."):
+                        exp_edges = query_explorer_edges(sel_node_id, kg_edges_path, max_e)
+                    if exp_edges.empty:
+                        st.warning("연결된 엣지가 없습니다.")
+                    else:
+                        all_ids = set(exp_edges["source"].tolist()) | set(exp_edges["target"].tolist())
+                        st.session_state["exp_nodes"] = kg_nodes_exp[kg_nodes_exp["node_id"].isin(all_ids)]
+                        st.session_state["exp_edges"] = exp_edges
+
+        with exp_col2:
+            if "exp_nodes" in st.session_state:
+                en = st.session_state["exp_nodes"]
+                ee = st.session_state["exp_edges"]
+                st.caption(f"Nodes: {len(en)}  |  Edges: {len(ee)}")
+                st.caption("🖱 Scroll: zoom  |  Drag: pan  |  Click node: info  |  ⛶ button: fullscreen")
+                components.html(pyvis_from_kg(en, ee, height="740px"), height=760, scrolling=True)
+            else:
+                st.info("왼쪽에서 노드를 선택하고 'Show ego network'를 클릭하세요.")
+
+        # ── Enriched 인사이��� (DuckDB 집계만)
+        st.markdown("---")
+        st.subheader("Enriched Citation Insights")
+        st.caption("citation_events_enriched: DuckDB로 집계 통계만 쿼리 (전체 로드 없음)")
+        with st.spinner("Enriched 통계 쿼리 중 (DuckDB)..."):
+            sem_df, field_df = query_enriched_stats(enriched_path)
+
+        if not sem_df.empty:
+            sem_df["label"] = sem_df["has_semantic_evidence"].map(
+                {True: "With evidence", False: "Without evidence",
+                 1: "With evidence", 0: "Without evidence"})
+            col_s1, col_s2 = st.columns(2)
+            with col_s1:
+                st.plotly_chart(
+                    px.pie(sem_df, names="label", values="count",
+                           title="Semantic Evidence Coverage")
+                    .update_layout(legend_title=""),
+                    use_container_width=True)
+            with col_s2:
+                if not field_df.empty:
                     st.plotly_chart(
-                        px.pie(sem_df, names="label", values="count",
-                               title="Semantic Evidence Coverage")
-                        .update_layout(legend_title=""),
+                        px.bar(field_df, x="field", y="sem_ratio",
+                               title="Semantic Evidence Rate by Field",
+                               labels={"sem_ratio": "Evidence Rate", "field": "Field"})
+                        .update_layout(xaxis_tickangle=-40),
                         use_container_width=True)
-                with col_s2:
-                    if not field_df.empty:
-                        st.plotly_chart(
-                            px.bar(field_df, x="field", y="sem_ratio",
-                                   title="Semantic Evidence Rate by Field",
-                                   labels={"sem_ratio":"Evidence Rate","field":"Field"})
-                            .update_layout(xaxis_tickangle=-40),
-                            use_container_width=True)
-
-        except Exception as e:
-            st.error(str(e))
+
+    except Exception as e:
+        st.error(str(e))
 
 
 # ═══ 6. GEOGRAPHIC MAP ══════════════════════════════════════════