Update app.py

app.py

@@ -1,8 +1,9 @@
 # ================================================================
 # Self-Sensing Concrete Assistant — Predictor (XGB) + Hybrid RAG
-# - Predictor tab: identical behavior to your "second code"
+# - Predictor tab: identical behavior to your "second code" (kept)
 # - Literature tab: from your "first code" (Hybrid RAG + MMR)
-# - Hugging Face friendly: online PDF fetching OFF by default
+# - UX: checkboxes clickable, science-oriented layout, and
+#       prediction=0.0 when required fields are incomplete
 # ================================================================
 
 # ---------------------- Runtime flags (HF-safe) ----------------------
@@ -102,6 +103,14 @@ CATEGORICAL_COLS = {
     "Current Type"
 }
 
+# Optional fields (allowed to be missing) — everything else is required
+OPTIONAL_FIELDS = {
+    "Filler 2 Type",
+    "Filler 2 Diameter (µm)",
+    "Filler 2 Length (mm)",
+    "Filler 2 Dimensionality",
+}
+
 DIM_CHOICES     = ["0D", "1D", "2D", "3D", "NA"]
 CURRENT_CHOICES = ["DC", "AC", "NA"]
 
@@ -137,7 +146,41 @@ def _coerce_to_row(form_dict: dict) -> pd.DataFrame:
             row[col] = "" if v in (None, "NA") else str(v).strip()
     return pd.DataFrame([row], columns=MAIN_VARIABLES)
 
+def _is_complete(form_dict: dict) -> bool:
+    """
+    Completeness rule:
+    - All fields except OPTIONAL_FIELDS must be present.
+    - For NUMERIC_COLS (except optional), require not-NaN.
+    - For CATEGORICAL_COLS (except optional), require non-empty string.
+    - 'NA' is allowed only for the optional Filler-2 dimensionality; treated as empty elsewhere.
+    """
+    for col in MAIN_VARIABLES:
+        if col in OPTIONAL_FIELDS:
+            # optional: can be empty/NaN
+            continue
+        v = form_dict.get(col, None)
+        if col in NUMERIC_COLS:
+            try:
+                if v in ("", None) or (isinstance(v, float) and np.isnan(v)):
+                    return False
+            except Exception:
+                return False
+        elif col in CATEGORICAL_COLS:
+            s = "" if v in (None, "NA") else str(v).strip()
+            if s == "":
+                return False
+        else:
+            # generic non-numeric, require non-empty
+            s = "" if v is None else str(v).strip()
+            if s == "":
+                return False
+    return True
+
 def predict_fn(**kwargs):
+    # If incomplete, return 0.0 by spec
+    if not _is_complete(kwargs):
+        return 0.0
+
     mdl = _load_model_or_error()
     if isinstance(mdl, str):
         return mdl
@@ -209,7 +252,7 @@ USE_ONLINE_SOURCES = os.getenv("USE_ONLINE_SOURCES", "false").lower() == "true"
 # Retrieval weights
 W_TFIDF_DEFAULT = 0.50 if not USE_DENSE else 0.30
 W_BM25_DEFAULT  = 0.50 if not USE_DENSE else 0.30
-W_EMB_DEFAULT   = 0.00 if not USE_DENSE else 0.40
+W_EMB_DEFAULT   = 0.00 if USE_DENSE is False else 0.40
 
 # Simple text processing
 _SENT_SPLIT_RE = re.compile(r"(?<=[.!?])\s+|\n+")
@@ -220,7 +263,7 @@ def sent_split(text: str) -> List[str]:
 def tokenize(text: str) -> List[str]:
     return [t.lower() for t in TOKEN_RE.findall(text)]
 
-# PDF text extraction (PyMuPDF preferred; pypdf fallback)
+# PDF text extraction
 def _extract_pdf_text(pdf_path: Path) -> str:
     try:
         import fitz
@@ -287,13 +330,11 @@ def build_or_load_hybrid(pdf_dir: Path):
             rows.append({"doc_path": str(pdf), "chunk_id": i, "text": ch})
             all_tokens.append(tokenize(ch))
     if not rows:
-        # create empty stub to avoid crashes; UI will message user to upload PDFs
         meta = pd.DataFrame(columns=["doc_path", "chunk_id", "text"])
         vectorizer = None; X_tfidf = None; emb = None; all_tokens = None
         return vectorizer, X_tfidf, meta, all_tokens, emb
 
     meta = pd.DataFrame(rows)
-
     from sklearn.feature_extraction.text import TfidfVectorizer
     vectorizer = TfidfVectorizer(
         ngram_range=(1,2),
@@ -334,7 +375,7 @@ def _extract_page(text_chunk: str) -> str:
     m = list(re.finditer(r"\[\[PAGE=(\d+)\]\]", text_chunk or ""))
     return (m[-1].group(1) if m else "?")
 
-def hybrid_search(query: str, k=8, w_tfidf=W_TFIDF_DEFAULT, w_bm25=W_BM25_DEFAULT, w_emb=W_EMB_DEFAULT):
+def hybrid_search(query: str, k=8, w_tfidf=0.5, w_bm25=0.5, w_emb=0.0):
     if rag_meta is None or rag_meta.empty:
         return pd.DataFrame()
 
@@ -403,7 +444,6 @@ def mmr_select_sentences(question: str, hits: pd.DataFrame, top_n=4, pool_per_ch
 
     sent_texts = [p["sent"] for p in pool]
 
-    # Embedding-based relevance if available, else TF-IDF
     use_dense = USE_DENSE and st_query_model is not None
     if use_dense:
         try:
@@ -483,9 +523,9 @@ def rag_reply(
     model: str = None,
     temperature: float = 0.2,
     strict_quotes_only: bool = False,
-    w_tfidf: float = W_TFIDF_DEFAULT,
-    w_bm25: float  = W_BM25_DEFAULT,
-    w_emb: float   = W_EMB_DEFAULT
+    w_tfidf: float = 0.5,
+    w_bm25: float  = 0.5,
+    w_emb: float   = 0.0
 ) -> str:
     hits = hybrid_search(question, k=k, w_tfidf=w_tfidf, w_bm25=w_bm25, w_emb=w_emb)
     if hits is None or hits.empty:
@@ -547,101 +587,62 @@ def rag_chat_fn(message, history, top_k, n_sentences, include_passages,
 
 # ========================= UI (predictor styling kept) =========================
 CSS = """
-/* App-wide background stays blue→green gradient */
+/* Science-oriented: crisp contrast + readable numerics */
+* {font-family: ui-sans-serif, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial;}
 .gradio-container {
-    background: linear-gradient(135deg, #1e3a8a 0%, #166534 60%, #15803d 100%) !important;
+    background: linear-gradient(135deg, #0b1020 0%, #0c2b1a 60%, #0a2b4d 100%) !important; /* deep science vibe */
 }
-* {font-family: ui-sans-serif, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial;}
-.card {background: rgba(255,255,255,0.07) !important; border: 1px solid rgba(255,255,255,0.12);}
-label.svelte-1ipelgc {color: #e0f2fe !important;}
-
-/* ----------------- RAG Tab (scoped by elem_id) ----------------- */
-#rag-tab .block, #rag-tab .group, #rag-tab .accordion {
-    background: linear-gradient(160deg, #1f2937 0%, #14532d 55%, #0b3b68 100%) !important; /* gray → green → blue */
-    border-radius: 0.75rem;
-    border: 1px solid rgba(255,255,255,0.12);
+.card {background: rgba(255,255,255,0.06) !important; border: 1px solid rgba(255,255,255,0.14); border-radius: 12px;}
+label {color: #e8f7ff !important; text-shadow: 0 1px 0 rgba(0,0,0,0.35); cursor: pointer;}
+input[type="number"] {font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", monospace;}
+/* Checkbox clickability fixes (some themes overlay labels) */
+input[type="checkbox"], .gr-checkbox, .gr-checkbox > * {
+    pointer-events: auto !important;
 }
+.gr-checkbox label, .gr-check-radio label { pointer-events: auto !important; cursor: pointer; }
+#rag-tab input[type="checkbox"] { accent-color: #60a5fa !important; }
 
-/* High-contrast labels inside the RAG tab */
-#rag-tab label, #rag-tab .label-wrap, #rag-tab .prose, #rag-tab .markdown {
-    color: #e8f7ff !important;              /* bright blue-gray text */
-    text-shadow: 0 1px 0 rgba(0,0,0,0.35);   /* subtle lift for readability */
+/* RAG tab background and elements */
+#rag-tab .block, #rag-tab .group, #rag-tab .accordion {
+    background: linear-gradient(160deg, #1f2937 0%, #14532d 55%, #0b3b68 100%) !important;
+    border-radius: 12px;
+    border: 1px solid rgba(255,255,255,0.14);
 }
-
-/* Inputs in RAG tab: blue-gray fields with clear borders */
 #rag-tab input, #rag-tab textarea, #rag-tab select, #rag-tab .scroll-hide, #rag-tab .chatbot textarea {
-    background: rgba(17, 24, 39, 0.85) !important; /* deep gray-blue */
-    border: 1px solid #60a5fa !important;          /* bright blue border */
+    background: rgba(17, 24, 39, 0.85) !important;
+    border: 1px solid #60a5fa !important;
     color: #e5f2ff !important;
 }
-
-/* Sliders (track + thumb) for RAG controls */
-#rag-tab input[type="range"] {
-    accent-color: #22c55e !important;  /* green accent for track */
-}
-#rag-tab input[type="range"]::-webkit-slider-thumb {
-    background: #22c55e !important;    /* green thumb */
-}
-#rag-tab input[type="range"]::-moz-range-thumb {
-    background: #22c55e !important;
-}
-
-/* Checkboxes and toggles */
-#rag-tab input[type="checkbox"] {
-    accent-color: #60a5fa !important;  /* blue checks */
-}
-
-/* Buttons in RAG: primary blue, secondary gray-green */
+#rag-tab input[type="range"] { accent-color: #22c55e !important; }
 #rag-tab button {
-    border-radius: 0.75rem !important;
+    border-radius: 10px !important;
     font-weight: 600 !important;
 }
-#rag-tab button.primary, #rag-tab button[aria-label*="Send"] {
-    background: #2563eb !important;   /* blue */
-    color: #ffffff !important;
-    border: 1px solid #93c5fd !important;
-}
-#rag-tab button.secondary {
-    background: #374151 !important;   /* gray */
-    color: #e5e7eb !important;
-}
-
-/* Chat area */
 #rag-tab .chatbot {
-    background: rgba(15, 23, 42, 0.6) !important;  /* slate/blue overlay */
+    background: rgba(15, 23, 42, 0.6) !important;
     border: 1px solid rgba(148, 163, 184, 0.35) !important;
 }
 #rag-tab .message.user {
-    background: rgba(34, 197, 94, 0.15) !important;  /* translucent green */
+    background: rgba(34, 197, 94, 0.15) !important;
     border-left: 3px solid #22c55e !important;
 }
 #rag-tab .message.bot {
-    background: rgba(59, 130, 246, 0.15) !important; /* translucent blue */
+    background: rgba(59, 130, 246, 0.15) !important;
     border-left: 3px solid #60a5fa !important;
     color: #eef6ff !important;
 }
 
-/* Markdown answers + code blocks in RAG */
-#rag-tab .prose pre, #rag-tab code, #rag-tab .prose code {
-    background: rgba(2, 6, 23, 0.7) !important;     /* deep navy for code */
-    border: 1px solid rgba(99, 102, 241, 0.35) !important; /* indigo edge */
-    color: #e5f2ff !important;
-}
-
-/* Tiny helper: make small helper text readable */
-#rag-tab .text-xs, #rag-tab .text-sm, #rag-tab .description, #rag-tab .caption, #rag-tab .info {
-    color: #d1fae5 !important; /* minty green for microcopy */
-    opacity: 0.95 !important;
-}
+/* Predictor output emphasis */
+#pred-out .wrap { font-size: 20px; font-weight: 700; color: #ecfdf5; }
 """
 
 theme = gr.themes.Soft(
     primary_hue="blue",
     neutral_hue="green"
 ).set(
-    body_background_fill="#1e3a8a",
+    body_background_fill="#0b1020",
     body_text_color="#e0f2fe",
-    input_background_fill="#172554",
+    input_background_fill="#0f172a",
     input_border_color="#1e40af",
     button_primary_background_fill="#2563eb",
     button_primary_text_color="#ffffff",
@@ -653,9 +654,8 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
     gr.Markdown(
         "<h1 style='margin:0'>Self-Sensing Concrete Assistant</h1>"
         "<p style='opacity:.9'>"
-        "Left tab: ML prediction for Stress Gauge Factor (kept identical to your deployed predictor). "
-        "Right tab: Literature Q&A via Hybrid RAG (BM25 + TF-IDF + optional dense) with MMR sentence selection. "
-        "Upload PDFs into <code>papers/</code> in your Space repo."
+        "Left: ML prediction for Stress Gauge Factor (original scale, MPa<sup>-1</sup>). "
+        "Right: Literature Q&A via Hybrid RAG (BM25 + TF-IDF + optional dense) with MMR sentence selection."
         "</p>"
     )
 
@@ -699,7 +699,7 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
 
                 with gr.Column(scale=5):
                     with gr.Group(elem_classes=["card"]):
-                        out_pred = gr.Number(label="Predicted Stress GF (MPa-1)", precision=6)
+                        out_pred = gr.Number(label="Predicted Stress GF (MPa-1)", value=0.0, precision=6, elem_id="pred-out")
                         with gr.Row():
                             btn_pred  = gr.Button("Predict", variant="primary")
                             btn_clear = gr.Button("Clear")
@@ -707,11 +707,12 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
 
                     with gr.Accordion("About this model", open=False, elem_classes=["card"]):
                         gr.Markdown(
-                            "- Pipeline: ColumnTransformer -> (RobustScaler + OneHot) -> XGBoost\n"
-                            "- Target: Stress GF (MPa^-1) on original scale (model trains on log1p).\n"
+                            "- Pipeline: ColumnTransformer → (RobustScaler + OneHot) → XGBoost\n"
+                            "- Target: Stress GF (MPa<sup>-1</sup>) on original scale (model trains on log1p).\n"
                             "- Missing values are safely imputed per-feature.\n"
                             "- Trained columns:\n"
-                            f"  `{', '.join(MAIN_VARIABLES)}`"
+                            f"  `{', '.join(MAIN_VARIABLES)}`",
+                            elem_classes=["prose"]
                         )
 
             # Wire predictor buttons
@@ -729,7 +730,7 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
                 return predict_fn(**data)
 
             btn_pred.click(_predict_wrapper, inputs=inputs_in_order, outputs=out_pred)
-            btn_clear.click(lambda: _clear_all(), inputs=None, outputs=inputs_in_order)
+            btn_clear.click(lambda: _clear_all(), inputs=None, outputs=inputs_in_order).then(lambda: 0.0, outputs=out_pred)
             btn_demo.click(lambda: _fill_example(), inputs=None, outputs=inputs_in_order)
 
         # ------------------------- Literature Tab -------------------------
@@ -741,14 +742,14 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
             with gr.Row():
                 top_k = gr.Slider(5, 12, value=8, step=1, label="Top-K chunks")
                 n_sentences = gr.Slider(2, 6, value=4, step=1, label="Answer length (sentences)")
-                include_passages = gr.Checkbox(value=False, label="Include supporting passages")
+                include_passages = gr.Checkbox(value=False, label="Include supporting passages", interactive=True)
             with gr.Accordion("Retriever weights (advanced)", open=False):
                 w_tfidf = gr.Slider(0.0, 1.0, value=W_TFIDF_DEFAULT, step=0.05, label="TF-IDF weight")
                 w_bm25  = gr.Slider(0.0, 1.0, value=W_BM25_DEFAULT,  step=0.05, label="BM25 weight")
-                w_emb   = gr.Slider(0.0, 1.0, value=W_EMB_DEFAULT,   step=0.05, label="Dense weight (set 0 if disabled)")
+                w_emb   = gr.Slider(0.0, 1.0, value=(0.0 if not USE_DENSE else 0.40), step=0.05, label="Dense weight (set 0 if disabled)")
             with gr.Accordion("LLM & Controls", open=False):
-                strict_quotes_only = gr.Checkbox(value=False, label="Strict quotes only (no paraphrasing)")
-                use_llm     = gr.Checkbox(value=False, label="Use LLM to paraphrase selected sentences")
+                strict_quotes_only = gr.Checkbox(value=False, label="Strict quotes only (no paraphrasing)", interactive=True)
+                use_llm     = gr.Checkbox(value=False, label="Use LLM to paraphrase selected sentences", interactive=True)
                 model_name  = gr.Textbox(value=os.getenv("OPENAI_MODEL", OPENAI_MODEL),
                                          label="LLM model", placeholder="e.g., gpt-5 or gpt-5-mini")
                 temperature = gr.Slider(0.0, 1.0, value=0.2, step=0.05, label="Temperature")