Upload app.py

app.py

@@ -16,7 +16,6 @@ audio + parsed metadata (viral loads default to 0) and show "not available" trut
 import os
 import json
 import numpy as np
-import pandas as pd
 import joblib
 import gradio as gr
 
@@ -38,10 +37,31 @@ LUT = xl.build_lookup(XLSX)                      # ground truth + viral loads fr
 FE, AST, AST_DEV = ae.load_ast()                 # AST weights download on first run
 
 LBL = {"S": "Survivor (S)", "T": "Terminal (T)"}
-COLUMNS = ["File", "Colony", "Country", "Month", "Viral C/D/K",
-           "Pred 0–3", "Truth 0–3", "Pred 4–6", "Truth 4–6", "OK"]
-COL_WIDTHS = ["175px", "95px", "100px", "105px", "140px",
-              "105px", "110px", "105px", "110px", "60px"]
+HEADERS = ["File", "Colony", "Country", "Month", "Viral CBPV / DWV / KBV",
+           "Predicted 0–3", "Actual 0–3", "Predicted 4–6", "Actual 4–6", "Match"]
+
+
+def _results_html(rows):
+    """Render results as a self-styled HTML table (full control, no truncation)."""
+    th = "".join(
+        f'<th style="border:1px solid #e3e3e3;padding:9px 14px;background:#f4f4f4;'
+        f'color:#000;font-weight:600;text-align:left;white-space:nowrap;">{h}</th>'
+        for h in HEADERS)
+    trs = []
+    for r in rows:
+        tds = []
+        for i, v in enumerate(r):
+            extra = "white-space:nowrap;"
+            if HEADERS[i] == "Match":
+                c = {"✓": "#157347", "✗": "#b42318"}.get(v, "#888")
+                extra += f"text-align:center;font-weight:700;font-size:16px;color:{c};"
+            tds.append(f'<td style="border:1px solid #e3e3e3;padding:9px 14px;color:#000;'
+                       f'{extra}">{v}</td>')
+        trs.append("<tr>" + "".join(tds) + "</tr>")
+    return ('<div style="overflow-x:auto;width:100%;">'
+            '<table style="border-collapse:collapse;background:#fff;color:#000;'
+            'font-family:-apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;font-size:14px;">'
+            f'<thead><tr>{th}</tr></thead><tbody>{"".join(trs)}</tbody></table></div>')
 
 
 def _predict_one(path):
@@ -77,7 +97,7 @@ def _predict_one(path):
 
 def predict_batch(files, progress=gr.Progress()):
     if not files:
-        return pd.DataFrame(columns=COLUMNS), "Upload one or more `.wav` files, then click **Predict**."
+        return "", "Upload one or more `.wav` files (or click an example), then press **Predict**."
     paths = [f if isinstance(f, str) else f.name for f in files]
     rows = []
     for p in progress.tqdm(paths, desc="Scoring recordings"):
@@ -86,28 +106,23 @@ def predict_batch(files, progress=gr.Progress()):
         except Exception as e:  # noqa
             rows.append([os.path.basename(p), "?", "?", "?", "",
                          "error", str(e)[:30], "error", "", "✗"])
-    df = pd.DataFrame(rows, columns=COLUMNS)
-    known = df[df["OK"] != "—"]
-    n_ok = int((known["OK"] == "✓").sum())
-    summary = (f"Scored **{len(df)}** file(s) · **{len(known)}** found in the Excel workbook "
-               f"· **{n_ok}/{len(known)}** predicted correctly (both horizons).")
-    return df, summary
+    n_known = sum(1 for r in rows if r[9] != "—")
+    n_ok = sum(1 for r in rows if r[9] == "✓")
+    summary = (f"Scored **{len(rows)}** file(s) · **{n_known}** found in the Excel workbook "
+               f"· **{n_ok}/{n_known}** predicted correctly (both horizons).")
+    return _results_html(rows), summary
 
 
 CSS = """
 .gradio-container {background:#ffffff !important; color:#000000 !important;
   font-family: -apple-system, Segoe UI, Roboto, Helvetica, Arial, sans-serif; max-width:1150px;}
 .gradio-container * {color:#000000;}
-h1,h2,h3,p,span,label,td,th,div {color:#000000 !important;}
+h1,h2,h3,p,label {color:#000000 !important;}
 button.primary, .primary {background:#000000 !important; color:#ffffff !important;
   border:1px solid #000000 !important; border-radius:6px !important;}
 button.primary:hover, .primary:hover {background:#222222 !important;}
+button.primary *, .primary * {color:#ffffff !important;}
 .secondary {background:#ffffff !important; color:#000000 !important; border:1px solid #000000 !important;}
-table {border-collapse:collapse !important;}
-th {background:#f5f5f5 !important; color:#000000 !important; font-weight:600 !important;
-  white-space:nowrap !important; text-overflow:clip !important;}
-td,th {border:1px solid #dddddd !important; padding:6px 10px !important; color:#000000 !important;
-  overflow-wrap:anywhere;}
 footer {display:none !important;}
 """
 THEME = gr.themes.Base(primary_hue=gr.themes.colors.gray,
@@ -134,8 +149,8 @@ with gr.Blocks(title="Bee Colony Survival — Multimodal Predictor", theme=THEME
         btn = gr.Button("Predict", variant="primary")
         clear = gr.Button("Clear", variant="secondary")
     summary = gr.Markdown()
-    table = gr.Dataframe(headers=COLUMNS, wrap=True, interactive=False, label="Results",
-                         column_widths=COL_WIDTHS)
+    gr.Markdown("### Results")
+    table = gr.HTML()
     if example_files:
         gr.Markdown("**Example recordings** — click any one to load it and run the prediction "
                     "(all are Terminal colonies the model correctly detects). "
@@ -151,8 +166,7 @@ with gr.Blocks(title="Bee Colony Survival — Multimodal Predictor", theme=THEME
             label="Bundled examples",
         )
     btn.click(predict_batch, inputs=audio_in, outputs=[table, summary])
-    clear.click(lambda: (None, pd.DataFrame(columns=COLUMNS), ""),
-                outputs=[audio_in, table, summary])
+    clear.click(lambda: (None, "", ""), outputs=[audio_in, table, summary])
 
 if __name__ == "__main__":
     demo.launch()