Final final updates to app.py

app.py

@@ -207,20 +207,6 @@ def read_input(file, text):
     return open(path, encoding="utf-8", errors="replace").read()
 
 
-def bar(k, n, colour):
-    #count + a thin bar showing what share of the segments got flagged
-    return (f"<td><div class='cell'><b>{k}</b><span class='bar'>"
-            f"<span style='width:{k / n * 100:.0f}%;background:{colour}'></span></span></div></td>")
-
-
-def meter(p, thr):
-    #track from 0 to 1, fill = top bert score, white tick = threshold
-    colour = "#818cf8" if p >= thr else "#4b5370"
-    return (f"<div class='cell'><span class='meter'><span class='fill' style='width:{p * 100:.0f}%;background:{colour}'></span>"
-            f"<span class='tick' style='left:{thr * 100:.0f}%'></span></span>"
-            f"<span class='small'>{p:.2f} / {thr:.2f}</span></div>")
-
-
 @GPU
 def analyse(file, text):
     raw = read_input(file, text)
@@ -274,15 +260,14 @@ def analyse(file, text):
     v = np.array([vader_flags(s) for s in segs])
     t = tfidf_probs(segs)
     b = bert_probs(segs)
-    n = len(segs)
     rows = ""
     for i, c in enumerate(CATEGORIES):
-        counts = [int(v[:, i].sum()), int((t[:, i] >= 0.5).sum()), int((b[:, i] >= BERT_THRESHOLDS[c]).sum())]
-        cells = "".join(bar(k, n, col) for k, col in zip(counts, ["#f472b6", "#a78bfa", "#34d399"]))
-        rows += f"<tr><td>{NAMES[c]}</td>{cells}<td>{meter(b[:, i].max(), BERT_THRESHOLDS[c])}</td></tr>"
-    s5 = (f"<h4>5. Classification: all three models</h4>"
-          f"<table><tr><th>Category</th><th>VADER</th><th>TF-IDF</th><th>BERT + LoRA</th><th>BERT top score vs threshold</th></tr>{rows}</table>"
-          f"<p class='small'>Segments flagged out of {n}. White line = BERT threshold, the bar fills to the top segment score </p>")
+        rows += (f"<tr><td>{NAMES[c]}</td><td>{int(v[:, i].sum())}</td><td>{int((t[:, i] >= 0.5).sum())}</td>"
+                 f"<td><b>{int((b[:, i] >= BERT_THRESHOLDS[c]).sum())}</b></td><td>{b[:, i].max():.2f} / {BERT_THRESHOLDS[c]:.2f}</td></tr>")
+    s5 = (f"<h4>5. Classification: all three models</h4><table><tr><th>Category</th><th>VADER</th><th>TF-IDF</th><th>BERT + LoRA</th>"
+          f"<th>BERT top prob / threshold</th></tr>{rows}</table>"
+          f"<p class='small'>Numbers are segments flagged out of {len(segs)}. BERT is my final model. "
+          f"A research prototype, it flags passages for a person to read and does not diagnose anyone.</p>")
 
     order = np.argsort(-b.max(axis=1))   #strongest segments first for shap
     choices = [f"#{k + 1}  (BERT max {b[k].max():.2f})  {segs[k][:60]}..." for k in order]
@@ -311,21 +296,37 @@ def explain(state, choice, category):
             f"<div class='seg' style='line-height:1.9'>{spans}</div>")
 
 
+#files for the examiners to try (loose in the space or inside a test_set folder)
+TEST_SET = [("ridesk-12-6-02.txt", "Sally Ride, Shuttle"), ("crippenrl-10-16-12.txt", "Robert Crippen, Shuttle"),
+            ("whitsonpa-9-6-12.txt", "Peggy Whitson, ISS"), ("pettitdr-8-17-15.pdf", "Donald Pettit, ISS (PDF)"),
+            ("harttj-4-10-03.txt", "Terry Hart, Shuttle"), ("rossjl-12-4-03.txt", "Jerry Ross, Shuttle"),
+            ("mullanerm-1-24-03.txt", "Mike Mullane, Shuttle"), ("armstrongna-9-19-01.txt", "Neil Armstrong, Apollo")]
+PIPELINE_TESTS = [("1_WORKS_cover_page_transcript.txt", "Works: transcript with cover page"),
+                  ("2_TEST_one_short_sentence.txt", "Test: one short sentence"),
+                  ("3_TEST_speaker_names_not_in_capitals.txt", "Test: speaker names not in capitals"),
+                  ("4_TEST_curly_apostrophe_in_name.txt", "Test: curly apostrophe in a name"),
+                  ("5_TEST_technical_no_strain.txt", "Test: technical, no strain")]
+
+
+def find_files(pairs):
+    found = []
+    for name, label in pairs:
+        for folder in [os.path.join(HERE, "test_set"), HERE]:
+            if os.path.exists(os.path.join(folder, name)):
+                found.append((os.path.join(folder, name), label))
+                break
+    return found
+
+
 #  the page 
 
 CSS = """
 .gradio-container {background: radial-gradient(ellipse at top, #141b33 0%, #05070f 70%) !important;}
 * {box-shadow: none !important;}
 .seg {border: 1px solid #ffffff44; border-radius: 12px; padding: 8px 12px; margin: 6px 0; color: #e6ebff;}
-table {width: 100%; border-collapse: collapse; border: none !important; color: #e6ebff;}
-th, td {border: none !important; border-bottom: 1px solid #ffffff33 !important; padding: 6px 8px; text-align: left;}
+table {width: 100%; border-collapse: collapse; color: #e6ebff;}
+th, td {border-bottom: 1px solid #ffffff33; padding: 6px 8px; text-align: left;}
 .small {color: #9aa4c4; font-size: 13px;}
-.cell {display: flex; align-items: center; gap: 8px;}
-.bar {flex: 1; min-width: 40px; height: 6px; background: #ffffff14; border-radius: 3px; overflow: hidden;}
-.bar span {display: block; height: 100%;}
-.meter {position: relative; flex: 1; min-width: 80px; height: 8px; background: #ffffff14; border-radius: 4px;}
-.meter .fill {position: absolute; left: 0; top: 0; bottom: 0; border-radius: 4px;}
-.meter .tick {position: absolute; top: -4px; bottom: -4px; width: 2px; background: #fff;}
 """
 
 with gr.Blocks(title="SPACEMIND") as demo:
@@ -340,6 +341,16 @@ with gr.Blocks(title="SPACEMIND") as demo:
                 clearButton = gr.ClearButton()
                 runButton = gr.Button("Run the pipeline", variant="primary")
 
+            #held out test astronauts --> the model never saw them in training
+            heldOut = find_files(TEST_SET)
+            if heldOut:
+                gr.Examples([[p] for p, _ in heldOut], inputs=fileInput, example_labels=[l for _, l in heldOut],
+                            label="Load a transcript from my held-out test set")
+            tests = find_files(PIPELINE_TESTS)
+            if tests:
+                gr.Examples([[p] for p, _ in tests], inputs=fileInput, example_labels=[l for _, l in tests],
+                            label="Pipeline tests (where it works and where it breaks)")
+
         #right side: the stages
         with gr.Column():
             out1 = gr.Textbox(label="1. Input (word count)")