Update app.py

app.py

@@ -133,15 +133,72 @@ This is the exact calculation method used to build and verify all 28 national su
 *Nigeria AMR Classifier v2 — Fine-tuned Llama 3.3 70B | AutoScientist 2026 | Science Category*
 """
 
+# ══════════════════════════════════════════════════════════
+# ── Loan Classification Closed-Label Classifier ──────────────
+# ══════════════════════════════════════════════════════════
+@spaces.GPU
+def classify_loan_days(days):
+    if days is None or days < 0:
+        return "Please enter a valid number of days past due (0 or greater)."
+
+    days = int(days)
+    if days <= 89:
+        classification, provision, color = "Performing", "1% (general provision)", "🟢"
+    elif days <= 179:
+        classification, provision, color = "Substandard", "10%", "🟡"
+    elif days <= 359:
+        classification, provision, color = "Doubtful", "50%", "🟠"
+    else:
+        classification, provision, color = "Lost", "100% (full provision, written off)", "🔴"
+
+    return f"""
+## {color} Classification: {classification}
+
+**Your input:** {days} days past due
+
+**Required provisioning:** {provision}
+
+**CBN Prudential Guidelines thresholds:** Performing (0-89 days), Substandard (90-179 days), Doubtful (180-359 days), Lost (360+ days)
+
+This classification was computed live from your input against the real CBN Prudential Guidelines registry, the same deterministic logic used to build and verify all 20 rows in the training dataset.
+
+---
+*Nigeria Loan Classifier v2 — Fine-tuned Llama 4 Scout 17B-16E | AutoScientist 2026 | Personal Finance Category*
+"""
+
+@spaces.GPU
+def classify_npl_ratio(npl_ratio):
+    if npl_ratio is None or npl_ratio < 0:
+        return "Please enter a valid NPL ratio percentage."
+
+    ratio = float(npl_ratio)
+    status = "Compliant" if ratio < 5.0 else "Breach"
+    color = "🟢" if status == "Compliant" else "🔴"
+
+    return f"""
+## {color} Classification: {status}
+
+**Your input:** {ratio}% NPL ratio
+
+**CBN regulatory threshold:** 5.0%
+
+**Result:** {ratio}% {'is below' if status == 'Compliant' else 'exceeds'} the 5% threshold
+
+This is the exact classification method used to verify all 9 bank/industry-level rows in the training dataset, including a real near-miss case at 4.99%.
+
+---
+*Nigeria Loan Classifier v2 — Fine-tuned Llama 4 Scout 17B-16E | AutoScientist 2026 | Personal Finance Category*
+"""
+
 # ══════════════════════════════════════════════════════════
 # ── Build Interface ─────────────────────────────────────────
 # ══════════════════════════════════════════════════════════
 with gr.Blocks(title="Africa Science AI") as demo:
     gr.Markdown("""
-    # 🌍🧫 Africa Science AI Demo
-    ## AutoScientist Challenge 2026, Part 2 | Science Category
+    # 🌍🧫🏦 Africa Science & Finance AI Demo
+    ## AutoScientist Challenge 2026, Part 2
     **Author:** Hussein Adeiza (mabera) — Licensed Environmental Health Officer, Abuja Nigeria
-    **Two models:** HIV Funding Analysis (Llama 4 Scout) + AMR Classifier v2 (Llama 3.3 70B)
+    **Three models:** HIV Funding Analysis + AMR Classifier v2 + Nigeria Loan Classifier v2
     **Powered by Adaptive Data — Adaption Labs**
     """)
 
@@ -193,6 +250,27 @@ with gr.Blocks(title="Africa Science AI") as demo:
                     rate_output = gr.Markdown()
             rate_btn.click(classify_rate, inputs=[n_tested, n_nonsusceptible], outputs=rate_output)
 
+        with gr.Tab("🏦 Loan: Days Past Due Classification"):
+            gr.Markdown("### Enter a loan's days past due and see the CBN classification computed live")
+            gr.Markdown("⚠️ Closed-label classification: results are deterministically computed, not generated. Honest note: this model's win rate was below 50% (base model outperformed adapted); full disclosure in the model card.")
+            with gr.Row():
+                with gr.Column():
+                    loan_days = gr.Number(label="Days past due", value=45, precision=0)
+                    loan_days_btn = gr.Button("🏦 Classify Loan", variant="primary")
+                with gr.Column():
+                    loan_days_output = gr.Markdown()
+            loan_days_btn.click(classify_loan_days, inputs=[loan_days], outputs=loan_days_output)
+
+        with gr.Tab("🏦 Loan: NPL Ratio Compliance"):
+            gr.Markdown("### Enter a bank or industry NPL ratio and see CBN compliance computed live")
+            with gr.Row():
+                with gr.Column():
+                    npl_input = gr.Number(label="NPL ratio (%)", value=4.99, precision=2)
+                    npl_btn = gr.Button("🏦 Check Compliance", variant="primary")
+                with gr.Column():
+                    npl_output = gr.Markdown()
+            npl_btn.click(classify_npl_ratio, inputs=[npl_input], outputs=npl_output)
+
     gr.Markdown("""
     ---
     ### Models — Open Source
@@ -200,11 +278,14 @@ with gr.Blocks(title="Africa Science AI") as demo:
     |-------|----------|----------|---------|------|
     | HIV Funding Analysis (Llama 4 Scout) | Science | 71% (60% general) | 6.0→6.5, Grade C | Domain classification issue disclosed |
     | AMR Classifier v2 (Llama 3.3 70B) | Science | 58% (71% general) | 8.0→8.7, Grade B | 34/34 rows verified |
+    | Loan Classifier v2 (Llama 4 Scout) | Personal Finance | 40% (45% general) | 8.0→8.4, Grade B | 20/20 rows verified; win rate honestly disclosed |
 
     🤗 [HIV Model](https://huggingface.co/mabera/africa-hiv-funding-analysis-model) |
     🤗 [AMR Model](https://huggingface.co/mabera/nigeria-amr-classifier-v2) |
+    🤗 [Loan Model](https://huggingface.co/mabera/nigeria-loan-classifier-v2) |
     🤗 [HIV Dataset](https://huggingface.co/datasets/mabera/africa-hiv-funding-dataset) |
-    🤗 [AMR Dataset](https://huggingface.co/datasets/mabera/nigeria-amr-classifier-v2-dataset)
+    🤗 [AMR Dataset](https://huggingface.co/datasets/mabera/nigeria-amr-classifier-v2-dataset) |
+    🤗 [Loan Dataset](https://huggingface.co/datasets/mabera/nigeria-loan-classifier-v2-dataset)
 
     ### Other Portfolio Demos
     - Part 1 (Healthcare, Legal, Marketing, Finance, Language): [nigeria-health-ai-demo](https://huggingface.co/spaces/mabera/nigeria-health-ai-demo)