Upload app.py

src/app.py

@@ -5,8 +5,10 @@ from pathlib import Path
 from typing import List
 
 import pandas as pd
+import networkx as nx
 import streamlit as st
 import plotly.express as px
+import plotly.graph_objects as go
 from pyvis.network import Network
 import streamlit.components.v1 as components
 
@@ -60,8 +62,173 @@ def _read(filename: str, data_dir: Path | None = None) -> pd.DataFrame:
     return pd.read_parquet(data_dir / filename)
 
 
+def plotly_network_fig(
+    nodes_df: pd.DataFrame,
+    edges_df: pd.DataFrame,
+    title: str = "",
+    height: int = 750,
+    seed_node_ids: list | None = None,
+) -> go.Figure:
+    """SVG 기반 Plotly 네트워크 그래프 — 확대해도 선명."""
+    G = nx.Graph()
+    node_meta: dict = {}
+    for _, row in nodes_df.iterrows():
+        nid = str(row["node_id"])
+        G.add_node(nid)
+        node_meta[nid] = row
+
+    for _, row in edges_df.iterrows():
+        s, t = str(row["source"]), str(row["target"])
+        if s in node_meta and t in node_meta:
+            G.add_edge(s, t, edge_type=row.get("edge_type", ""))
+
+    if len(G.nodes) == 0:
+        return go.Figure()
+
+    k = max(1.5, 3.0 / (len(G.nodes) ** 0.4))
+    pos = nx.spring_layout(G, seed=42, k=k, iterations=60)
+
+    # ── edges ─────────────────────────────────
+    ex, ey = [], []
+    for src, tgt in G.edges():
+        x0, y0 = pos.get(src, (0, 0))
+        x1, y1 = pos.get(tgt, (0, 0))
+        ex += [x0, x1, None]
+        ey += [y0, y1, None]
+
+    traces: list[go.BaseTraceType] = [
+        go.Scatter(
+            x=ex, y=ey, mode="lines",
+            line=dict(width=0.8, color="#cbd5e1"),
+            hoverinfo="none", showlegend=False,
+        )
+    ]
+
+    # ── nodes grouped by type ─────────────────
+    for ntype, color in NODE_TYPE_COLORS.items():
+        subset = nodes_df[nodes_df["node_type"] == ntype]
+        if subset.empty:
+            continue
+        xs, ys, hovers, texts = [], [], [], []
+        for _, row in subset.iterrows():
+            nid = str(row["node_id"])
+            if nid not in pos:
+                continue
+            x, y = pos[nid]
+            xs.append(x); ys.append(y)
+            label = str(row.get("label", ""))[:50]
+            texts.append(label if ntype == "seed_paper" else "")
+            hovers.append(
+                f"<b>{label}</b><br>"
+                f"Type: {ntype}<br>"
+                f"DOI: {row.get('doi','') or '-'}<br>"
+                f"Pub: {row.get('publication_name','') or '-'}<br>"
+                f"Group: {row.get('group','') or '-'}"
+            )
+
+        is_seed = ntype == "seed_paper"
+        traces.append(go.Scatter(
+            x=xs, y=ys,
+            mode="markers+text" if is_seed else "markers",
+            text=texts, textposition="top center",
+            hovertext=hovers, hoverinfo="text",
+            name=ntype,
+            marker=dict(
+                size=20 if is_seed else 10,
+                color=color,
+                line=dict(width=1.5 if is_seed else 0.5, color="white"),
+                symbol="circle",
+            ),
+        ))
+
+    fig = go.Figure(data=traces)
+    fig.update_layout(
+        title=dict(text=title, font=dict(size=14)),
+        showlegend=True,
+        legend=dict(title="Node type", itemsizing="constant"),
+        hovermode="closest",
+        height=height,
+        margin=dict(l=0, r=0, t=40 if title else 10, b=0),
+        paper_bgcolor="white",
+        plot_bgcolor="#f8fafc",
+        xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
+        yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
+    )
+    return fig
+
+
+def plotly_ontology_fig(height: int = 750) -> go.Figure:
+    """CitationHub 온톨로지 구조 — Plotly SVG."""
+    node_defs = [
+        ("seed",        "Top5PctCitedPaper", "seed_paper"),
+        ("event",       "CitationEvent",     "citation_event"),
+        ("citing",      "CitingPaper",        "citing_paper"),
+        ("intent",      "Intent",             "intent"),
+        ("journal",     "Journal",            "journal"),
+        ("author",      "Author",             "author"),
+        ("affiliation", "Affiliation",        "affiliation"),
+        ("city",        "City",               "city"),
+        ("country",     "Country",            "country"),
+        ("field",       "Field",              "field"),
+    ]
+    edge_defs = [
+        ("event","citing","hasCitingPaper"),    ("event","seed","hasCitedPaper"),
+        ("event","intent","hasPrimaryIntent"),   ("seed","journal","publishedInJournal"),
+        ("seed","author","hasAuthor"),           ("seed","affiliation","hasAffiliation"),
+        ("seed","city","locatedInCity"),         ("seed","country","locatedInCountry"),
+        ("seed","field","belongsToField"),
+    ]
+    G = nx.DiGraph()
+    for nid, _, _ in node_defs:
+        G.add_node(nid)
+    for s, t, _ in edge_defs:
+        G.add_edge(s, t)
+
+    pos = nx.spring_layout(G, seed=7, k=2.5, iterations=80)
+
+    # edges + edge labels
+    ex, ey = [], []
+    ann = []
+    for s, t, lbl in edge_defs:
+        x0, y0 = pos[s]; x1, y1 = pos[t]
+        ex += [x0, x1, None]; ey += [y0, y1, None]
+        mx, my = (x0+x1)/2, (y0+y1)/2
+        ann.append(dict(x=mx, y=my, text=f"<i>{lbl}</i>",
+                        showarrow=False, font=dict(size=9, color="#64748b"),
+                        bgcolor="rgba(255,255,255,0.7)"))
+
+    traces: list[go.BaseTraceType] = [
+        go.Scatter(x=ex, y=ey, mode="lines",
+                   line=dict(width=1.2, color="#94a3b8"),
+                   hoverinfo="none", showlegend=False)
+    ]
+    for nid, label, ntype in node_defs:
+        x, y = pos[nid]
+        color = NODE_TYPE_COLORS.get(ntype, "#94a3b8")
+        traces.append(go.Scatter(
+            x=[x], y=[y], mode="markers+text",
+            text=[label], textposition="top center",
+            hoverinfo="text", hovertext=f"<b>{label}</b><br>Type: {ntype}",
+            name=label, showlegend=False,
+            marker=dict(size=22, color=color,
+                        line=dict(width=1.5, color="white")),
+            textfont=dict(size=11),
+        ))
+
+    fig = go.Figure(data=traces)
+    fig.update_layout(
+        showlegend=False, hovermode="closest", height=height,
+        annotations=ann,
+        margin=dict(l=0, r=0, t=10, b=0),
+        paper_bgcolor="white", plot_bgcolor="#f8fafc",
+        xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
+        yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
+    )
+    return fig
+
+
 def inject_fullscreen(html: str) -> str:
-    btn = """
+    extra = """
     <button onclick="var el=document.getElementById('mynetwork');
       if(el){if(el.requestFullscreen)el.requestFullscreen();
       else if(el.webkitRequestFullscreen)el.webkitRequestFullscreen();}"
@@ -73,8 +240,23 @@ def inject_fullscreen(html: str) -> str:
                 color:#64748b;background:rgba(255,255,255,0.85);
                 padding:5px 10px;border-radius:6px;">
       🖱 Scroll: zoom &nbsp;|&nbsp; Drag: pan &nbsp;|&nbsp; Click node: info</div>
+    <script>
+    // HiDPI 캔버스 해상도 보정 (Canvas 흐림 최소화)
+    (function fixDPI() {
+      var canvas = document.querySelector('#mynetwork canvas');
+      if (!canvas) { setTimeout(fixDPI, 200); return; }
+      var dpr = window.devicePixelRatio || 1;
+      if (dpr <= 1) return;
+      try {
+        if (typeof network !== 'undefined') {
+          network.canvas.pixelRatio = dpr;
+          network.redraw();
+        }
+      } catch(e) {}
+    })();
+    </script>
     """
-    return html.replace("</body>", btn + "</body>")
+    return html.replace("</body>", extra + "</body>")
 
 
 # ── 메인 데이터 로드 (11개) ────────────────────────────────────
@@ -557,8 +739,7 @@ with tab_cnet:
 # ═══ 3. ONTOLOGY ════════════════════════════════════════════════
 with tab_ontology:
     st.subheader("CitationHub Ontology")
-    st.caption("🖱 Scroll: zoom  |  Drag: pan  |  Click node: info  |  ⛶ button: fullscreen")
-    components.html(pyvis_ontology(), height=820, scrolling=True)
+    st.plotly_chart(plotly_ontology_fig(height=750), use_container_width=True)
 
 
 # ═══ 4. KNOWLEDGE GRAPH ══════════════════════════════════════════
@@ -599,8 +780,9 @@ with tab_kg:
                     .update_layout(showlegend=False, xaxis_title="", yaxis_title="Count"),
                     use_container_width=True)
 
-                st.caption("🖱 Scroll: zoom  |  Drag: pan  |  Click node: info  |  ⛶ button: fullscreen")
-                components.html(pyvis_from_kg(nodes_sub, edges_sub), height=820, scrolling=True)
+                st.plotly_chart(
+                    plotly_network_fig(nodes_sub, edges_sub, height=750),
+                    use_container_width=True)
     except Exception as e:
         st.error(str(e))
 
@@ -613,7 +795,6 @@ with tab_kg_exp:
         with st.spinner("Loading..."):
             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)
 
         # ── 노드/엣지 타입 분포 통계
         col_a, col_b = st.columns([1, 2])
@@ -674,35 +855,9 @@ with tab_kg_exp:
                 c2.metric("Edges", fmt_num(len(exp_edges)))
                 c3.metric("Node types", fmt_num(exp_nodes["node_type"].nunique()))
 
-                st.caption("🖱 Scroll: zoom  |  Drag: pan  |  Click node: info  |  ⛶ button: fullscreen")
-                components.html(pyvis_from_kg(exp_nodes, exp_edges, height="780px"),
-                                height=800, scrolling=True)
-
-        # ── Enriched 인사이트
-        st.markdown("---")
-        st.subheader("CitationHub Semantic Evidence Distribution")
-        with st.spinner("Loading..."):
-            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=""),
+                    plotly_network_fig(exp_nodes, exp_edges, height=750),
                     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))
@@ -820,3 +975,114 @@ with tab_analytics:
     st.markdown("---")
     st.subheader("Field Reference")
     st.dataframe(fields_df, use_container_width=True, hide_index=True)
+
+    # ── Intent Evolution over Years ────────────────────────────
+    st.markdown("---")
+    st.subheader("CitationHub Intent Evolution over Years")
+    st.caption("How citation intents have changed across all papers over time")
+    intent_trend_raw = (
+        events.dropna(subset=["citing_year"])
+        .assign(year=lambda df: df["citing_year"].astype(int))
+        .groupby(["year", "primary_intent"]).size()
+        .reset_index(name="count")
+    )
+    if not intent_trend_raw.empty:
+        st.plotly_chart(
+            px.area(
+                intent_trend_raw, x="year", y="count", color="primary_intent",
+                color_discrete_map=INTENT_COLORS,
+                labels={"primary_intent": "Intent", "count": "Citations", "year": "Year"},
+            ).update_layout(
+                legend_title="Intent",
+                xaxis_title="Year", yaxis_title="# Citations",
+                hovermode="x unified",
+            ),
+            use_container_width=True,
+        )
+
+    # ── Top Citing Venues ───────────────────────────────────────
+    st.markdown("---")
+    col_v1, col_v2 = st.columns(2)
+
+    with col_v1:
+        st.subheader("Top Citing Venues")
+        st.caption("Journals/conferences that cite seed papers most")
+        venue_cnt = (
+            events[events["citing_venue"].str.strip() != ""]
+            .groupby("citing_venue").size()
+            .reset_index(name="count")
+            .sort_values("count", ascending=False).head(20)
+        )
+        if not venue_cnt.empty:
+            st.plotly_chart(
+                px.bar(venue_cnt, x="count", y="citing_venue", orientation="h",
+                       labels={"count": "Citations", "citing_venue": ""})
+                .update_layout(yaxis=dict(autorange="reversed"),
+                               xaxis_title="Citations", yaxis_title="", height=520),
+                use_container_width=True,
+            )
+
+    with col_v2:
+        st.subheader("Intent Mix by Field")
+        st.caption("How each field uses citations differently")
+        fi_pct = (
+            seed[["seed_paper_id", "field"]]
+            .merge(events[["seed_paper_id", "primary_intent"]], on="seed_paper_id", how="inner")
+            .groupby(["field", "primary_intent"]).size().reset_index(name="count")
+        )
+        if not fi_pct.empty:
+            totals = fi_pct.groupby("field")["count"].transform("sum")
+            fi_pct["pct"] = (fi_pct["count"] / totals * 100).round(1)
+            top_fields = fi_pct.groupby("field")["count"].sum().nlargest(12).index
+            fi_pct_top = fi_pct[fi_pct["field"].isin(top_fields)]
+            st.plotly_chart(
+                px.bar(fi_pct_top, x="pct", y="field", color="primary_intent",
+                       orientation="h", color_discrete_map=INTENT_COLORS,
+                       labels={"pct": "% of citations", "field": "", "primary_intent": "Intent"})
+                .update_layout(
+                    barmode="stack",
+                    yaxis=dict(autorange="reversed"),
+                    xaxis_title="% of citations", yaxis_title="",
+                    legend_title="Intent", height=520,
+                ),
+                use_container_width=True,
+            )
+
+    # ── Export ─────────────────────────────────────────────────
+    st.markdown("---")
+    st.subheader("Export Data")
+    col_e1, col_e2, col_e3 = st.columns(3)
+
+    with col_e1:
+        csv_seed = seed_filtered[
+            ["title", "doi", "journal", "author", "country", "field", "citedby_count"]
+        ].to_csv(index=False).encode("utf-8")
+        st.download_button(
+            "⬇ Seed Papers (CSV)",
+            csv_seed, "seed_papers.csv", "text/csv",
+            use_container_width=True,
+        )
+
+    with col_e2:
+        cite_export = seed_events[
+            ["citing_title", "citing_doi", "citing_year", "citing_venue",
+             "primary_intent", "context_count", "is_influential"]
+        ].rename(columns={
+            "citing_title": "title", "citing_doi": "doi",
+            "citing_year": "year", "citing_venue": "venue",
+            "primary_intent": "intent", "context_count": "contexts",
+            "is_influential": "influential",
+        }).to_csv(index=False).encode("utf-8")
+        st.download_button(
+            "⬇ Citation Events (CSV)",
+            cite_export, "citation_events.csv", "text/csv",
+            use_container_width=True,
+        )
+
+    with col_e3:
+        intent_csv = intent_summary.to_csv(index=False).encode("utf-8")
+        st.download_button(
+            "⬇ Intent Summary (CSV)",
+            intent_csv, "intent_summary.csv", "text/csv",
+            use_container_width=True,
+        )