add weight

app.py

@@ -65,19 +65,25 @@ def calculate_distance(job_coords, user_coords):
 
 # Fungsi utama untuk persiapan dan rekomendasi pekerjaan
 def prepare_and_recommend(df, user_skills, user_location):
+    def prepare_and_recommend(df, user_skills, user_location):
+    # 1. Memastikan dataset memiliki koordinat
     if 'latitude' not in df or 'longitude' not in df:
         raise ValueError("Dataset harus memiliki kolom latitude dan longitude")
 
+    # 2. Vektorisasi skill
     all_skills = df['skills'].tolist()  # Semua skill dari dataset
     user_skills_vtr = vectorize_skills([user_skills], all_skills)  # Skill user
     job_skills_vtr = vectorize_skills(df['skills'], all_skills)  # Skill pekerjaan di dataset
 
+    # 3. Menghitung Cosine Similarity antara user dan pekerjaan
     cosine_similarities = calculate_cosine_similarity(user_skills_vtr, job_skills_vtr)
     df['cosine_similarity'] = cosine_similarities[0]
 
+    # 4. Menghitung jarak antara lokasi pekerjaan dan lokasi user
     user_coords = get_coordinates(user_location)  # Dapatkan koordinat user
     distances = []
     for _, row in df.iterrows():
+        # Pengecekan apakah koordinat pekerjaan valid
         if pd.notna(row['latitude']) and pd.notna(row['longitude']) and row['latitude'] != 0 and row['longitude'] != 0:
             job_coords = (row['latitude'], row['longitude'])
             distance = calculate_distance(job_coords, user_coords)
@@ -86,8 +92,15 @@ def prepare_and_recommend(df, user_skills, user_location):
             distances.append(float('inf'))  # Jika koordinat tidak valid, jarak tak terhingga
 
     df['distance (km)'] = distances
-    df['final score'] = df['cosine_similarity'] / (df['distance (km)'] + 1)
 
+    # 5. Normalisasi jarak
+    df['normalized_distance'] = normalize_distance(df['distance (km)'])
+
+    # 6. Menghitung skor akhir berdasarkan Cosine Similarity dan Normalisasi Jarak
+    df['final score'] = (1.5 * df['cosine_similarity']) * (1.0 * df['normalized_distance'])
+    df['final score'] = df['final score'].round(2)
+
+    # 7. Mengurutkan pekerjaan dan memilih 5 teratas berdasarkan skor akhir
     top_jobs = df.sort_values(by='final score', ascending=False).head(5)
 
     return top_jobs[['job_link', 'title', 'company', 'location', 'distance (km)', 'final score']]