update main.py , tambahan endpoint recommend

main.py

@@ -1,23 +1,30 @@
-# main.py
+# ======================================================================
+# --- main.py (GABUNGAN DUA API) ---
+# ======================================================================
 
 import os
+import json
+import networkx as nx
 import pandas as pd
 import skops.io as sio
-from fastapi import FastAPI
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
+from typing import List, Dict, Any
 
-# ==============================
-# 1. Inisialisasi aplikasi FastAPI
-# ==============================
+# ======================================================================
+# 1. Inisialisasi Aplikasi FastAPI
+# ======================================================================
 app = FastAPI(
-    title="API Prediksi Risiko Akademik Mahasiswa",
-    description="API untuk memprediksi risiko akademik mahasiswa menggunakan model Machine Learning.",
-    version="1.0.0"
+    title="API Layanan Akademik Mahasiswa",
+    description="Menggabungkan API Prediksi Risiko Akademik dan Rekomendasi Mata Kuliah.",
+    version="1.1.0"
 )
 
-# ==============================
-# 2. Struktur data input (Pydantic)
-# ==============================
+# ======================================================================
+# 2. Struktur Data Input/Output (Pydantic)
+# ======================================================================
+
+# --- Model untuk API Prediksi Risiko (App 1) ---
 class StudentFeatures(BaseModel):
     IPK_Terakhir: float
     IPS_Terakhir: float
@@ -30,34 +37,33 @@ class StudentFeatures(BaseModel):
     Tren_IPS_Slope: float
     Perubahan_Kinerja_Terakhir: float
     IPK_Ternormalisasi_SKS: float
-    Profil_Tren: str  # Fitur kategorikal sebelum di-encode
-
-# ==============================
-# 3. Muat model (kompatibel dengan skops >= 0.10)
-# ==============================
-MODEL_PATH = os.path.join(os.path.dirname(__file__), "model_risiko_akademik.skops")
-
-try:
-    trusted_types = [
-        "numpy.ndarray",
-        "numpy.core.multiarray.scalar",
-        "sklearn.tree._classes.DecisionTreeClassifier",
-        "_codecs.encode",
-        "joblib.numpy_pickle.NumpyArrayWrapper",
-        "numpy.core.multiarray._reconstruct",
-        "numpy.dtype",
-        "sklearn.tree._tree.Tree"
-    ]
-    
-    # Muat model dengan daftar tipe yang sudah didefinisikan secara eksplisit
-    model = sio.load(MODEL_PATH, trusted=trusted_types)
+    Profil_Tren: str
+
+# --- Model untuk API Rekomendasi MK (App 2) ---
+class RecommendationRequest(BaseModel):
+    current_semester: int
+    courses_passed: List[str]
+
+class PrerequisiteInfo(BaseModel):
+    code: str
+    name: str
+
+class CourseRecommendation(BaseModel):
+    rank: int
+    code: str
+    name: str
+    sks: int
+    semester_plan: int
+    reason: str
+    priority_score: float
+    prerequisites: List[PrerequisiteInfo]
 
-except Exception as e:
-    raise RuntimeError(f"Gagal memuat model dari {MODEL_PATH}: {e}")
+# ======================================================================
+# 3. Variabel Global & Pemuatan Model/Data
+# ======================================================================
 
-# ==============================
-# 4. Daftar fitur yang diharapkan model
-# ==============================
+# --- Variabel Global untuk API Prediksi Risiko (App 1) ---
+ml_model = None
 MODEL_FEATURES = [
     'IPK_Terakhir', 'IPS_Terakhir', 'Total_SKS', 'IPS_Tertinggi',
     'IPS_Terendah', 'Rentang_IPS', 'Jumlah_MK_Gagal', 'Total_SKS_Gagal',
@@ -65,41 +71,211 @@ MODEL_FEATURES = [
     'IPK_Ternormalisasi_SKS', 'Tren_Menaik', 'Tren_Menurun', 'Tren_Stabil'
 ]
 
-# ==============================
-# 5. Endpoint root
-# ==============================
+# --- Variabel Global untuk API Rekomendasi MK (App 2) ---
+G = nx.DiGraph()
+course_details_map = {}
+prereq_map = {}
+coreq_map = {}
+out_degree_map = {}
+
+# --- Fungsi Pemuatan (dipanggil saat startup) ---
+
+def load_ml_model():
+    """Memuat model ML dari file .skops"""
+    global ml_model
+    MODEL_PATH = os.path.join(os.path.dirname(__file__), "model_risiko_akademik.skops")
+    print(f"Mencoba memuat model ML dari: {MODEL_PATH}")
+    try:
+        trusted_types = [
+            "numpy.ndarray", "numpy.core.multiarray.scalar",
+            "sklearn.tree._classes.DecisionTreeClassifier", "_codecs.encode",
+            "joblib.numpy_pickle.NumpyArrayWrapper", "numpy.core.multiarray._reconstruct",
+            "numpy.dtype", "sklearn.tree._tree.Tree"
+        ]
+        ml_model = sio.load(MODEL_PATH, trusted=trusted_types)
+        print("Model ML berhasil dimuat.")
+    except Exception as e:
+        print(f"ERROR: Gagal memuat model ML dari {MODEL_PATH}: {e}")
+        # Di produksi, Anda mungkin ingin ini menghentikan server
+        # raise RuntimeError(f"Gagal memuat model dari {MODEL_PATH}: {e}")
+
+def load_graph_data():
+    """Memuat dan memproses data graf kurikulum dari JSON"""
+    global G, course_details_map, prereq_map, coreq_map, out_degree_map
+    JSON_PATH = "OK_matkul_graph.json"
+    print(f"Mencoba memuat data graf dari: {JSON_PATH}")
+    try:
+        with open(JSON_PATH, "r") as f:
+            data = json.load(f)
+
+        for node in data["nodes"]:
+            course_details_map[node["code"]] = node
+            G.add_node(node["code"])
+
+        for edge in data["edges"]:
+            if edge["type"] == "prereq":
+                G.add_edge(edge["from"], edge["to"])
+                if edge["to"] not in prereq_map:
+                    prereq_map[edge["to"]] = []
+                prereq_map[edge["to"]].append(edge["from"])
+            elif edge["type"] == "coreq":
+                if edge["to"] not in coreq_map:
+                    coreq_map[edge["to"]] = []
+                coreq_map[edge["to"]].append(edge["from"])
+
+        for node_code in G.nodes():
+            out_degree_map[node_code] = G.out_degree(node_code)
+        
+        print(f"Data graf berhasil dimuat. Prereqs: {len(prereq_map)}, Coreqs: {len(coreq_map)}")
+    except FileNotFoundError:
+        print(f"ERROR: {JSON_PATH} tidak ditemukan!")
+    except Exception as e:
+        print(f"Error saat memuat graf: {e}")
+
+# --- Startup Event: Muat semua data saat server menyala ---
+@app.on_event("startup")
+def on_startup():
+    load_ml_model()
+    load_graph_data()
+
+# ======================================================================
+# 4. Helper Function (Untuk API Rekomendasi)
+# ======================================================================
+
+def get_recommendations_logic(current_semester: int, courses_passed_list: List[str]) -> List[Dict[str, Any]]:
+    """Inti dari logika rekomendasi, dengan validasi prereq dan coreq."""
+    passed_set = set(courses_passed_list)
+    all_courses_set = set(course_details_map.keys())
+    not_passed_courses = all_courses_set - passed_set
+    
+    prereq_valid_candidates = []
+
+    # Tahap 1: Cek Prasyarat (Prereq)
+    for course_code in not_passed_courses:
+        prereqs = prereq_map.get(course_code, [])
+        if all(p_code in passed_set for p_code in prereqs):
+            details = course_details_map.get(course_code)
+            if not details: continue # Lewati jika MK tidak ada di map (data anomali)
+
+            out_degree = out_degree_map.get(course_code, 0)
+            semester = details.get("semester_plan", 1)
+            priority_score = (out_degree / semester) if semester > 0 else 0
+            
+            candidate_data = details.copy()
+            candidate_data["priority_score"] = priority_score
+            prereq_valid_candidates.append(candidate_data)
+
+    # Tahap 2: Cek Ko-requisite (Coreq)
+    prereq_valid_codes = {c['code'] for c in prereq_valid_candidates}
+    final_valid_candidates = []
+    
+    for candidate in prereq_valid_candidates:
+        course_code = candidate['code']
+        coreqs = coreq_map.get(course_code, [])
+        
+        if not coreqs:
+            final_valid_candidates.append(candidate)
+            continue
+
+        is_coreq_met = True
+        for coreq_code in coreqs:
+            if (coreq_code not in passed_set) and (coreq_code not in prereq_valid_codes):
+                is_coreq_met = False
+                break
+        
+        if is_coreq_met:
+            final_valid_candidates.append(candidate)
+
+    # Tahap 3: Urutkan berdasarkan prioritas
+    catch_up_courses = [c for c in final_valid_candidates if c["semester_plan"] < current_semester]
+    current_semester_courses = [c for c in final_valid_candidates if c["semester_plan"] == current_semester]
+    future_courses = [c for c in final_valid_candidates if c["semester_plan"] > current_semester]
+
+    sorted_catch_up = sorted(catch_up_courses, key=lambda x: (x["semester_plan"], -x["priority_score"]))
+    sorted_current = sorted(current_semester_courses, key=lambda x: -x["priority_score"], reverse=True)
+    sorted_future = sorted(future_courses, key=lambda x: (x["semester_plan"], -x["priority_score"]))
+
+    final_ranked_list = sorted_catch_up + sorted_current + sorted_future
+    
+    return final_ranked_list
+
+# ======================================================================
+# 5. Endpoints API
+# ======================================================================
+
+# --- Endpoint dari App 1 (Prediksi) ---
 @app.get("/")
 def read_root():
     return {
-        "message": "API untuk Prediksi Risiko Akademik Mahasiswa",
-        "status": "ready"
+        "message": "Selamat Datang di API Layanan Akademik Mahasiswa",
+        "status": "ready",
+        "endpoints": ["/predict/", "/recommend/"]
     }
 
-# ==============================
-# 6. Endpoint untuk prediksi
-# ==============================
 @app.post("/predict/")
 def predict_risk(student_data: StudentFeatures):
-    # Konversi input ke DataFrame
+    if ml_model is None:
+        raise HTTPException(status_code=503, detail="Model ML belum siap. Silakan coba lagi nanti.")
+
     data = student_data.dict()
     input_df = pd.DataFrame([data])
-
-    # One-hot encoding kolom kategorikal
     input_encoded = pd.get_dummies(input_df, columns=['Profil_Tren'], prefix='Tren')
-
-    # Pastikan semua kolom model tersedia
     input_encoded = input_encoded.reindex(columns=MODEL_FEATURES, fill_value=False)
+    
+    try:
+        prediction = ml_model.predict(input_encoded)
+        prediction_proba = ml_model.predict_proba(input_encoded)
+        classes = ml_model.classes_
+        probabilities = dict(zip(classes, prediction_proba[0]))
+        
+        return {
+            "prediction": prediction[0],
+            "probabilities": probabilities
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Terjadi kesalahan saat prediksi: {e}")
 
-    # Prediksi
-    prediction = model.predict(input_encoded)
-    prediction_proba = model.predict_proba(input_encoded)
+# --- Endpoint dari App 2 (Rekomendasi) ---
+@app.post("/recommend/", response_model=List[CourseRecommendation])
+async def recommend_courses(request: RecommendationRequest):
+    if not course_details_map:
+        raise HTTPException(status_code=503, detail="Data kurikulum belum siap. Silakan coba lagi nanti.")
 
-    # Ambil hasil probabilitas per kelas
-    classes = model.classes_
-    probabilities = dict(zip(classes, prediction_proba[0]))
+    ranked_candidates = get_recommendations_logic(request.current_semester, request.courses_passed)
+    top_3_candidates = ranked_candidates[:3]
+    
+    response_output = []
+    for i, course in enumerate(top_3_candidates):
+        rank = i + 1
+        
+        reason = "Rekomendasi semester ini"
+        if course["semester_plan"] < request.current_semester:
+            reason = f"Mata kuliah tertinggal (Smt {course['semester_plan']})"
+        elif course["semester_plan"] > request.current_semester:
+            reason = f"Akselerasi (Smt {course['semester_plan']})"
 
-    # Return hasil dalam format JSON
-    return {
-        "prediction": prediction[0],
-        "probabilities": probabilities
-    }
+        prereq_codes = prereq_map.get(course["code"], [])
+        prereq_details_list = []
+        for p_code in prereq_codes:
+            if p_code in course_details_map:
+                prereq_details_list.append(
+                    PrerequisiteInfo(
+                        code=p_code,
+                        name=course_details_map[p_code]["name"]
+                    )
+                )
+
+        response_output.append(
+            CourseRecommendation(
+                rank=rank,
+                code=course["code"],
+                name=course["name"],
+                sks=course["sks"],
+                semester_plan=course["semester_plan"],
+                reason=reason,
+                priority_score=course["priority_score"],
+                prerequisites=prereq_details_list
+            )
+        )
+        
+    return response_output