add radius

app.py

@@ -71,44 +71,48 @@ def normalize_distance(distances):
     normalized = 1 / (1 + np.log1p(distances))  # log1p untuk menangani log(1 + distance)
     return normalized
 
-# Fungsi utama untuk persiapan dan rekomendasi pekerjaan
-def prepare_and_recommend(df, user_skills, user_location):
+# Menambahkan radius sebagai parameter
+def prepare_and_recommend(df, user_skills, user_location, radius_km):
     # 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
+    all_skills = df['skills'].tolist()
+    user_skills_vtr = vectorize_skills([user_skills], all_skills)
+    job_skills_vtr = vectorize_skills(df['skills'], all_skills)
 
     # 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
+    user_coords = get_coordinates(user_location)
     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:
+        if pd.notna(row['latitude']) and pd.notna(row['longitude']):
             job_coords = (row['latitude'], row['longitude'])
             distance = calculate_distance(job_coords, user_coords)
             distances.append(distance)
         else:
-            distances.append(float('inf'))  # Jika koordinat tidak valid, jarak tak terhingga
-
+            distances.append(float('inf'))
     df['distance (km)'] = distances
 
-    # 5. Normalisasi jarak
-    df['normalized_distance'] = normalize_distance(df['distance (km)'])
+    # 5. Filter pekerjaan berdasarkan radius
+    df = df[df['distance (km)'] <= radius_km]
+
+    # 6. Normalisasi jarak
+    if not df.empty:
+        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. Menghitung skor akhir
+        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)
+        # 8. Mengurutkan pekerjaan dan memilih 5 teratas berdasarkan skor akhir
+        top_jobs = df.sort_values(by='final score', ascending=False).head(5)
+    else:
+        top_jobs = pd.DataFrame()  # Kembalikan DataFrame kosong jika tidak ada pekerjaan dalam radius
 
     return top_jobs[['job_link', 'title', 'company', 'location', 'distance (km)', 'final score']]
 
@@ -118,10 +122,11 @@ st.write('Enter your skills and location to get job recommendations.')
 
 user_skills = st.text_input('Enter your skills (comma-separated):')
 user_location = st.text_input('Enter your location:')
+radius_km = st.number_input('Enter your preferred radius (in km):', min_value=1, value=10)
 
 if st.button('Get Recommendations'):
     if user_skills and user_location:
-        recommended_jobs = prepare_and_recommend(sample_data, user_skills, user_location)
+        recommended_jobs = prepare_and_recommend(sample_data, user_skills, user_location, radius_km)
         if recommended_jobs.empty:
             st.warning('Tidak ditemukan pekerjaan yang sesuai dengan keterampilan dan lokasi Anda.')
         elif recommended_jobs['final score'].max() < 0.02: