Add survey dataset viewer app

app.py

@@ -0,0 +1,171 @@
+"""
+ILSA-Survey-Dataset — Clickable Source Viewer
+"""
+
+import gradio as gr
+import pandas as pd
+from huggingface_hub import hf_hub_download
+
+REPO_ID = "dedemerve/ILSA-Survey-Dataset"
+MAX_CELL_CHARS = 300
+
+_CACHE = {}
+
+SHEETS = {
+    "Articles (130 studies)": "data/articles_master.csv",
+    "Main Findings (202 outcomes)": "data/main_findings.csv",
+    "Confounders (1907 predictors)": "data/confounders.csv",
+}
+
+
+def _is_blank(val) -> bool:
+    if val is None:
+        return True
+    try:
+        if pd.isna(val):
+            return True
+    except (TypeError, ValueError):
+        pass
+    return str(val).strip().lower() in ("", "none", "null", "nan", "n/a", "<na>")
+
+
+def _truncate(val) -> str:
+    if _is_blank(val):
+        return ""
+    s = str(val)
+    return s if len(s) <= MAX_CELL_CHARS else s[:MAX_CELL_CHARS] + "…"
+
+
+_LONGTEXT_HINTS = ("interpretation", "summary", "description", "definition", "finding",
+                   "confounder", "notes", "abstract", "text", "criteria", "explanation",
+                   "outcome", "primary", "technique", "filter")
+_SHORT_HINTS = ("year", "doi", "type", "category", "used", "id", "url", "label", "size")
+
+
+def _column_width(col: str) -> str:
+    c = col.lower()
+    if col == "Source":
+        return "200px"
+    if "title" in c or c in ("name",):
+        return "280px"
+    if "journal" in c or "venue" in c or "authors" in c:
+        return "220px"
+    if any(h in c for h in _LONGTEXT_HINTS):
+        return "300px"
+    if any(h in c for h in _SHORT_HINTS):
+        return "110px"
+    return "160px"
+
+
+def _load_raw(sheet_key: str) -> pd.DataFrame:
+    if sheet_key not in _CACHE:
+        csv_path = SHEETS[sheet_key]
+        local = hf_hub_download(repo_id=REPO_ID, filename=csv_path, repo_type="dataset")
+        _CACHE[sheet_key] = pd.read_csv(local, dtype=str)
+    return _CACHE[sheet_key]
+
+
+def _make_source_link(row) -> str:
+    for col in ("source_url", "paper_url"):
+        val = row.get(col)
+        if not _is_blank(val):
+            url = str(val).strip()
+            return f"[Open paper]({url})"
+    doi = row.get("doi")
+    if not _is_blank(doi):
+        doi = str(doi).strip()
+        url = doi if doi.startswith("http") else f"https://doi.org/{doi}"
+        return f"[Open via DOI]({url})"
+    import urllib.parse
+    title = row.get("title", "")
+    if not _is_blank(title):
+        q = urllib.parse.quote_plus(str(title).strip())
+        return f"[Search Google Scholar](https://scholar.google.com/scholar?q={q})"
+    return ""
+
+
+def build_table(sheet_key: str, search_text: str, max_rows: int):
+    if not sheet_key:
+        return gr.update(), "Select a table to get started."
+    try:
+        df = _load_raw(sheet_key).copy()
+    except Exception as e:
+        return gr.update(), f"Could not load data: {e}"
+
+    total_rows = len(df)
+
+    if search_text:
+        title_col = next((c for c in df.columns if "title" in c.lower()), None)
+        if title_col:
+            df = df[df[title_col].astype(str).str.contains(search_text, case=False, na=False)]
+
+    filtered_rows = len(df)
+    df = df.head(max_rows)
+
+    # Build Source link column if link-related columns exist
+    link_cols = [c for c in df.columns if c in ("source_url", "paper_url", "doi")]
+    has_links = bool(link_cols)
+
+    if has_links:
+        source_col = df.apply(_make_source_link, axis=1)
+        cols_to_drop = [c for c in ("source_url", "paper_url") if c in df.columns]
+        df = df.drop(columns=cols_to_drop)
+        df.insert(0, "Source", source_col)
+
+    for col in df.columns:
+        if col == "Source":
+            continue
+        df[col] = df[col].apply(_truncate)
+
+    datatype = ["markdown" if col == "Source" else "str" for col in df.columns]
+    column_widths = [_column_width(col) for col in df.columns]
+
+    info = (
+        f"**{sheet_key}** — {total_rows} rows total, "
+        f"{filtered_rows} after filtering, showing {len(df)} rows."
+    )
+    if has_links:
+        info += " Click **Source** to open the paper."
+
+    return gr.update(value=df, datatype=datatype, column_widths=column_widths), info
+
+
+with gr.Blocks(title="ILSA Survey Dataset Viewer") as demo:
+    gr.Markdown(
+        f"""
+        # ILSA Survey Dataset — Clickable Source Viewer
+
+        Browse the three relational tables from the survey paper
+        *"Artificial Intelligence Applications in International Large-Scale Assessments:
+        A Survey with LLM-Assisted Evidence Synthesis"* (Dede & Çetinkaya, 2026).
+
+        Each row in the **Articles** table links directly to the paper via DOI.
+
+        Dataset: [`{REPO_ID}`](https://huggingface.co/datasets/{REPO_ID}) &nbsp;|&nbsp;
+        Website: [dedemerve.github.io/ILSA-Survey-Extractor](https://dedemerve.github.io/ILSA-Survey-Extractor/)
+        """
+    )
+    with gr.Row():
+        sheet_dd = gr.Dropdown(
+            choices=list(SHEETS.keys()),
+            value=list(SHEETS.keys())[0],
+            label="Table",
+        )
+    with gr.Row():
+        search_box = gr.Textbox(
+            label="Search by title (Articles table only)",
+            placeholder="e.g. PISA, reading, ICCS…",
+        )
+        max_rows_box = gr.Slider(minimum=20, maximum=2000, value=200, step=20, label="Max rows")
+        load_btn = gr.Button("Load / Filter", variant="primary")
+
+    status_md = gr.Markdown("Loading…")
+    table = gr.Dataframe(label="Results", wrap=True, datatype="str", max_height=650)
+
+    demo.load(build_table, inputs=[sheet_dd, search_box, max_rows_box], outputs=[table, status_md])
+    sheet_dd.change(build_table, inputs=[sheet_dd, search_box, max_rows_box], outputs=[table, status_md])
+    load_btn.click(build_table, inputs=[sheet_dd, search_box, max_rows_box], outputs=[table, status_md])
+    search_box.submit(build_table, inputs=[sheet_dd, search_box, max_rows_box], outputs=[table, status_md])
+
+if __name__ == "__main__":
+    demo.launch()