Create app.py

app.py

@@ -0,0 +1,129 @@
+import pandas as pd
+import streamlit as st
+from geopy.geocoders import Nominatim
+from geopy.distance import geodesic
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import logging
+import warnings
+import time
+
+# Menyembunyikan pesan peringatan dari urllib3
+logging.getLogger("urllib3").setLevel(logging.CRITICAL)
+warnings.filterwarnings("ignore", category=UserWarning, module="urllib3")
+
+# Inisialisasi geolocator untuk geocoding
+geolocator = Nominatim(user_agent="job_recommendation_system")
+
+# Fungsi untuk mendapatkan koordinat lokasi
+def get_coordinates(location):
+    geolocator = Nominatim(user_agent="job_recommendation_system")
+
+    # Format lokasi
+    location = location.replace("-", ",")  # Ganti tanda hubung dengan koma
+
+    # Tangani nama lokasi dengan "Metropolitan Area" atau "Region"
+    if "Metropolitan Area" in location or "Region" in location:
+        city_name = location.split(" ")[0]  # Ambil nama kota utama
+        location = city_name
+
+    # Coba cari lokasi
+    location_obj = geolocator.geocode(location)
+    if location_obj:
+        return location_obj.latitude, location_obj.longitude
+
+    # Jika tidak ditemukan, coba nama kota atau negara
+    print(f"Koordinat untuk {location} tidak ditemukan. Mencoba alternatif.")
+    city_or_area = location.split(',')[0].strip()  # Ambil nama kota pertama
+    location_obj = geolocator.geocode(city_or_area)
+
+    if not location_obj:
+        country = location.split(',')[-1].strip()  # Ambil nama negara terakhir
+        location_obj = geolocator.geocode(country)
+
+    # Jika tetap gagal, coba retry
+    retry_count = 0
+    while not location_obj and retry_count < 5:
+        print(f"Mencoba ulang untuk lokasi {location}...")
+        time.sleep(2)  # Delay
+        location_obj = geolocator.geocode(location)
+        retry_count += 1
+
+    # Return koordinat jika ditemukan
+    if location_obj:
+        return location_obj.latitude, location_obj.longitude
+    else:
+        print(f"Koordinat untuk {location} atau alternatif tidak dapat ditemukan.")
+        return None, None
+
+# Load the dataset
+sample_data = pd.read_csv('job_data_with_coordinates.csv')
+
+# 1. Vektorisasi skill menggunakan CountVectorizer
+def vectorize_skills(skills, all_skills):
+    vectorizer = CountVectorizer()
+    vectorizer.fit(all_skills)
+    skills_vector = vectorizer.transform(skills)
+    return skills_vector
+
+# 2. Menghitung Cosine Similarity
+def calculate_cosine_similarity(user_skills_tfidf, job_skills_tfidf):
+    return cosine_similarity(user_skills_tfidf, job_skills_tfidf)
+
+# 3. Menghitung jarak lokasi
+def calculate_distance(job_coords, user_coords):
+    try:
+        return geodesic(job_coords, user_coords).km
+    except ValueError:  # Menangani kasus koordinat yang tidak valid
+        return float('inf')
+
+# 4. Fungsi utama untuk persiapan dan rekomendasi pekerjaan
+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)
+            distances.append(distance)
+        else:
+            distances.append(float('inf'))  # Jika koordinat tidak valid, jarak tak terhingga
+
+    df['distance (km)'] = distances
+
+    # 5. Menghitung skor akhir berdasarkan Cosine Similarity dan Jarak
+    df['final score'] = df['cosine_similarity'] / (df['distance (km)'] + 1)
+
+    # 6. 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']]
+
+# Streamlit app
+st.title('Job Recommendation System')
+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:')
+
+if st.button('Get Recommendations'):
+    if user_skills and user_location:
+        recommended_jobs = prepare_and_recommend(sample_data, user_skills, user_location)
+        st.dataframe(recommended_jobs)
+    else:
+        st.warning('Please enter your skills and location.')