Spaces:
Sleeping
Sleeping
Upload 13 files
Browse files- .gitattributes +3 -0
- Dataset/english_jobs.csv +3 -0
- Dataset/jobs.csv +3 -0
- Dockerfile +15 -0
- Siamese/pca_siamese_final.pkl +3 -0
- Siamese/recommender_model_final.keras +3 -0
- Siamese/vectorizer_siamese_final.pkl +3 -0
- main.py +209 -0
- models/best_model.h5 +3 -0
- models/mlb.pkl +3 -0
- models/model_prediksi_kategori.pkl +3 -0
- models/tfidf_category.pkl +3 -0
- models/tfidf_text.pkl +3 -0
- requirements.txt +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Dataset/english_jobs.csv filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Dataset/jobs.csv filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Siamese/recommender_model_final.keras filter=lfs diff=lfs merge=lfs -text
|
Dataset/english_jobs.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8139533582da83eb2f64ebbf23bc3466fd3606052dc14a5456930add0fc30697
|
| 3 |
+
size 357837231
|
Dataset/jobs.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cb8539466e17e0bceb2222ea642f39587af43bf944701900a59926c69df82c8
|
| 3 |
+
size 178426678
|
Dockerfile
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Gunakan Python versi 3.10
|
| 2 |
+
FROM python:3.10
|
| 3 |
+
|
| 4 |
+
# Atur folder kerja di dalam server
|
| 5 |
+
WORKDIR /code
|
| 6 |
+
|
| 7 |
+
# Salin file requirements dan install library
|
| 8 |
+
COPY ./requirements.txt /code/requirements.txt
|
| 9 |
+
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
| 10 |
+
|
| 11 |
+
# Salin semua file model dan kodemu ke dalam server
|
| 12 |
+
COPY . .
|
| 13 |
+
|
| 14 |
+
# Beri tahu server untuk menjalankan FastAPI di port 7860 (Syarat wajib Hugging Face)
|
| 15 |
+
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
Siamese/pca_siamese_final.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad9ea8fdfc4621c9591d5cd40294d9c95be4e75f67b16f4a6b416f6cc8fc39b1
|
| 3 |
+
size 8484599
|
Siamese/recommender_model_final.keras
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc1a2ae42d8d295ff9326c9454d1d44d4feb8ab8ebb5561067129079eff9d9ed
|
| 3 |
+
size 2098114
|
Siamese/vectorizer_siamese_final.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c7cae7e75eb04cd8733d6dd0d42578eded7121059247c7750a18611f6d6ab05
|
| 3 |
+
size 78255
|
main.py
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI, UploadFile, File
|
| 2 |
+
from deep_translator import GoogleTranslator
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import numpy as np
|
| 5 |
+
import pickle
|
| 6 |
+
import tensorflow as tf
|
| 7 |
+
import PyPDF2
|
| 8 |
+
import io
|
| 9 |
+
import urllib.parse
|
| 10 |
+
import os
|
| 11 |
+
|
| 12 |
+
original_dense_init = tf.keras.layers.Dense.__init__
|
| 13 |
+
|
| 14 |
+
def safe_dense_init(self, *args, **kwargs):
|
| 15 |
+
kwargs.pop('quantization_config', None)
|
| 16 |
+
original_dense_init(self, *args, **kwargs)
|
| 17 |
+
|
| 18 |
+
tf.keras.layers.Dense.__init__ = safe_dense_init
|
| 19 |
+
|
| 20 |
+
app = FastAPI(title="NextStep AI API")
|
| 21 |
+
|
| 22 |
+
@app.get("/")
|
| 23 |
+
async def root():
|
| 24 |
+
return {"message": "Selamat datang di NextStep AI API! Silakan akses /docs untuk dokumentasi."}
|
| 25 |
+
|
| 26 |
+
print(" Memuat Dataset & Model...")
|
| 27 |
+
|
| 28 |
+
# ==================== LOAD DATASET ====================
|
| 29 |
+
df_job = pd.read_csv('Dataset/english_jobs.csv')
|
| 30 |
+
|
| 31 |
+
# Tambahan pengaman: mencetak kolom untuk melihat isi dataset aslimu
|
| 32 |
+
print("-> Kolom di english_jobs.csv:", df_job.columns.tolist())
|
| 33 |
+
|
| 34 |
+
try:
|
| 35 |
+
if os.path.exists('Dataset/jobs.csv'):
|
| 36 |
+
df_metadata = pd.read_csv('Dataset/jobs.csv')
|
| 37 |
+
|
| 38 |
+
# Hapus duplikat agar data tidak berlipat ganda, lalu ambil 3 kolom penting
|
| 39 |
+
df_metadata_clean = df_metadata.drop_duplicates(subset=['title'])[['title', 'company', 'url']]
|
| 40 |
+
|
| 41 |
+
# GABUNGKAN HANYA BERDASARKAN NAMA POSISI (Karena company_name tidak ada)
|
| 42 |
+
df_job = pd.merge(
|
| 43 |
+
left=df_job,
|
| 44 |
+
right=df_metadata_clean,
|
| 45 |
+
left_on='raw_job_title',
|
| 46 |
+
right_on='title',
|
| 47 |
+
how='left'
|
| 48 |
+
)
|
| 49 |
+
print("-> Sukses! Berhasil menggabungkan dataset dengan jobs.csv!")
|
| 50 |
+
except Exception as e:
|
| 51 |
+
print(f"-> Peringatan: Gagal menggabungkan jobs.csv: {e}")
|
| 52 |
+
|
| 53 |
+
df_job = df_job.dropna(subset=['extracted_skills', 'job_category'])
|
| 54 |
+
# ======================================================
|
| 55 |
+
|
| 56 |
+
# LOAD MODEL KLASIFIKASI
|
| 57 |
+
with open('models/tfidf_text.pkl', 'rb') as f:
|
| 58 |
+
tfidf_text = pickle.load(f)
|
| 59 |
+
|
| 60 |
+
with open('models/mlb.pkl', 'rb') as f:
|
| 61 |
+
mlb = pickle.load(f)
|
| 62 |
+
|
| 63 |
+
model_klasifikasi = tf.keras.models.load_model('models/best_model.h5')
|
| 64 |
+
|
| 65 |
+
with open('models/model_prediksi_kategori.pkl', 'rb') as f:
|
| 66 |
+
model_kategori = pickle.load(f)
|
| 67 |
+
|
| 68 |
+
# LOAD MODEL SIAMESE
|
| 69 |
+
class CosineSimilarityLayer(tf.keras.layers.Layer):
|
| 70 |
+
def __init__(self, **kwargs):
|
| 71 |
+
super(CosineSimilarityLayer, self).__init__(**kwargs)
|
| 72 |
+
def call(self, inputs):
|
| 73 |
+
cv_vec, job_vec = inputs
|
| 74 |
+
cv_norm = tf.nn.l2_normalize(cv_vec, axis=-1)
|
| 75 |
+
job_norm = tf.nn.l2_normalize(job_vec, axis=-1)
|
| 76 |
+
return tf.reduce_sum(cv_norm * job_norm, axis=-1, keepdims=True)
|
| 77 |
+
|
| 78 |
+
with open('Siamese/vectorizer_siamese_final.pkl', 'rb') as f:
|
| 79 |
+
vectorizer_siamese = pickle.load(f)
|
| 80 |
+
with open('Siamese/pca_siamese_final.pkl', 'rb') as f:
|
| 81 |
+
pca_siamese = pickle.load(f)
|
| 82 |
+
|
| 83 |
+
recommender_model = tf.keras.models.load_model(
|
| 84 |
+
'Siamese/recommender_model_final.keras',
|
| 85 |
+
custom_objects={'CosineSimilarityLayer': CosineSimilarityLayer}
|
| 86 |
+
)
|
| 87 |
+
print("Semua Model Berhasil Dimuat!")
|
| 88 |
+
|
| 89 |
+
# HELPER FUNCTIONS
|
| 90 |
+
def ekstrak_teks_pdf(file_bytes):
|
| 91 |
+
teks_lengkap = ""
|
| 92 |
+
reader = PyPDF2.PdfReader(io.BytesIO(file_bytes))
|
| 93 |
+
for page in reader.pages:
|
| 94 |
+
teks_lengkap += page.extract_text() + " "
|
| 95 |
+
return teks_lengkap
|
| 96 |
+
|
| 97 |
+
def terjemahkan_cv(teks):
|
| 98 |
+
try:
|
| 99 |
+
if len(teks) > 4900:
|
| 100 |
+
teks = teks[:4900]
|
| 101 |
+
return GoogleTranslator(source='auto', target='en').translate(teks)
|
| 102 |
+
except Exception as e:
|
| 103 |
+
print(f"Translasi Gagal (Internet down/limit): {e}")
|
| 104 |
+
return teks
|
| 105 |
+
|
| 106 |
+
def cari_skill_gap(teks_cv, syarat_skill):
|
| 107 |
+
clean_syarat = str(syarat_skill).replace('[','').replace(']','').replace("'", "").split(',')
|
| 108 |
+
gap = [skill.strip() for skill in clean_syarat if skill.strip().lower() not in teks_cv.lower()]
|
| 109 |
+
return [g for g in gap if g]
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
# ENDPOINT API
|
| 113 |
+
@app.post("/api/predict-cv")
|
| 114 |
+
async def predict_cv(file: UploadFile = File(...)):
|
| 115 |
+
try:
|
| 116 |
+
file_bytes = await file.read()
|
| 117 |
+
teks_cv = ekstrak_teks_pdf(file_bytes)
|
| 118 |
+
|
| 119 |
+
vektor_cv_ai = tfidf_text.transform([teks_cv]).toarray()
|
| 120 |
+
vektor_dummy = np.zeros((1, 50))
|
| 121 |
+
vektor_input_klasifikasi = [vektor_cv_ai, vektor_dummy]
|
| 122 |
+
|
| 123 |
+
raw_pred = model_klasifikasi.predict(vektor_input_klasifikasi, verbose=0)
|
| 124 |
+
if isinstance(raw_pred, list):
|
| 125 |
+
raw_pred = raw_pred[0]
|
| 126 |
+
|
| 127 |
+
prediksi_prob = np.array(raw_pred).flatten()
|
| 128 |
+
y_pred_binary = (prediksi_prob > 0.50).astype(int)
|
| 129 |
+
skills_pelamar = mlb.inverse_transform(y_pred_binary.reshape(1, -1))[0]
|
| 130 |
+
|
| 131 |
+
kategori_prediksi = model_kategori.predict(vektor_cv_ai)[0]
|
| 132 |
+
df_filtered = df_job[df_job['job_category'] == kategori_prediksi]
|
| 133 |
+
|
| 134 |
+
if df_filtered.empty:
|
| 135 |
+
df_filtered = df_job
|
| 136 |
+
|
| 137 |
+
df_sample = df_filtered.sample(min(100, len(df_filtered)))
|
| 138 |
+
|
| 139 |
+
array_mentah = vectorizer_siamese.transform([teks_cv]).toarray()
|
| 140 |
+
vektor_input_siamese = pca_siamese.transform(array_mentah)
|
| 141 |
+
|
| 142 |
+
hasil_rekomendasi = []
|
| 143 |
+
for index, row in df_sample.iterrows():
|
| 144 |
+
teks_job = str(row['extracted_skills'])
|
| 145 |
+
array_job = vectorizer_siamese.transform([teks_job]).toarray()
|
| 146 |
+
vektor_job = pca_siamese.transform(array_job)
|
| 147 |
+
|
| 148 |
+
skor_ai = recommender_model.predict([vektor_input_siamese, vektor_job], verbose=0)[0][0]
|
| 149 |
+
persentase = round(float(((skor_ai + 1) / 2) * 100), 2)
|
| 150 |
+
|
| 151 |
+
posisi_loker = row.get('raw_job_title', f"Lowongan {index}")
|
| 152 |
+
|
| 153 |
+
# --- LOGIKA PENGAMBILAN PERUSAHAAN YANG LEBIH KETAT ---
|
| 154 |
+
perusahaan_loker = row.get('company') # Mencoba ambil dari jobs.csv
|
| 155 |
+
|
| 156 |
+
# Jika masih kosong, baru pakai Perusahaan Mitra
|
| 157 |
+
if pd.isna(perusahaan_loker) or str(perusahaan_loker).strip() == "":
|
| 158 |
+
perusahaan_loker = "Perusahaan Mitra"
|
| 159 |
+
|
| 160 |
+
# --- LOGIKA LINK APPLY JOB YANG LEBIH KETAT ---
|
| 161 |
+
link_asli = row.get('url')
|
| 162 |
+
|
| 163 |
+
if pd.isna(link_asli) or str(link_asli).strip() == "":
|
| 164 |
+
if perusahaan_loker == "Perusahaan Mitra":
|
| 165 |
+
kata_kunci = str(posisi_loker)
|
| 166 |
+
else:
|
| 167 |
+
kata_kunci = f"{posisi_loker} {perusahaan_loker}"
|
| 168 |
+
|
| 169 |
+
link_lamaran = f"https://www.linkedin.com/jobs/search/?keywords={urllib.parse.quote(kata_kunci)}"
|
| 170 |
+
else:
|
| 171 |
+
link_lamaran = str(link_asli)
|
| 172 |
+
|
| 173 |
+
hasil_rekomendasi.append({
|
| 174 |
+
"posisi": posisi_loker if pd.notna(posisi_loker) else f"Lowongan {index}",
|
| 175 |
+
"perusahaan": perusahaan_loker,
|
| 176 |
+
"industri": kategori_prediksi,
|
| 177 |
+
"skor_match": persentase,
|
| 178 |
+
"syarat_skill": teks_job,
|
| 179 |
+
"link_lamaran": link_lamaran
|
| 180 |
+
})
|
| 181 |
+
|
| 182 |
+
hasil_rekomendasi = sorted(hasil_rekomendasi, key=lambda x: x['skor_match'], reverse=True)[:3]
|
| 183 |
+
|
| 184 |
+
final_rekomendasi = []
|
| 185 |
+
for loker in hasil_rekomendasi:
|
| 186 |
+
gap = cari_skill_gap(teks_cv, loker['syarat_skill'])
|
| 187 |
+
loker['saran_belajar'] = gap[:5]
|
| 188 |
+
|
| 189 |
+
link_belajar = []
|
| 190 |
+
for skill in gap[:5]:
|
| 191 |
+
url_belajar = f"https://www.coursera.org/search?query={urllib.parse.quote(skill)}"
|
| 192 |
+
link_belajar.append(url_belajar)
|
| 193 |
+
|
| 194 |
+
loker['link_belajar'] = link_belajar
|
| 195 |
+
|
| 196 |
+
del loker['syarat_skill']
|
| 197 |
+
final_rekomendasi.append(loker)
|
| 198 |
+
|
| 199 |
+
return {
|
| 200 |
+
"status": "success",
|
| 201 |
+
"data_pelamar": {
|
| 202 |
+
"skill_terdeteksi": list(skills_pelamar)
|
| 203 |
+
},
|
| 204 |
+
"rekomendasi_utama_bidang": kategori_prediksi,
|
| 205 |
+
"top_3_loker": final_rekomendasi
|
| 206 |
+
}
|
| 207 |
+
|
| 208 |
+
except Exception as e:
|
| 209 |
+
return {"status": "error", "message": f"Terjadi kesalahan pada server: {str(e)}"}
|
models/best_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b7ccd35752adee2f193cee9eb725d6ae761c8d2bb855afc8369e191ea2f5a29
|
| 3 |
+
size 4941812
|
models/mlb.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783b20d004a441d70f04b0a1317a2dd2f00acf822a1b0542a654daed649575dc
|
| 3 |
+
size 1040
|
models/model_prediksi_kategori.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:995f0da91f238d8c6c5aae9791aec0f921821d9e8dbe03ec86e4410ffcd26938
|
| 3 |
+
size 482247
|
models/tfidf_category.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da10fa1c60ba1782f6391004ff2d713c497e5fde8bfe3d0a603bbdadc61f8eb5
|
| 3 |
+
size 2696
|
models/tfidf_text.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fe0e8597506237294c81e0e7abd4fc8bc2b4c8bfc2ff223e59bb7e1f4053674
|
| 3 |
+
size 112941
|
requirements.txt
ADDED
|
Binary file (210 Bytes). View file
|
|
|