Spaces:
Sleeping
Sleeping
| import re, os | |
| import pandas as pd | |
| import joblib, json | |
| import numpy as np | |
| from pathlib import Path | |
| from sentence_transformers import SentenceTransformer | |
| from kaggle.api.kaggle_api_extended import KaggleApi | |
| os.environ["KAGGLE_USERNAME"] = os.getenv("KAGGLE_USERNAME", "") | |
| os.environ["KAGGLE_KEY"] = os.getenv("KAGGLE_KEY", "") | |
| # Verify if variables exist | |
| if not os.environ["KAGGLE_USERNAME"] or not os.environ["KAGGLE_KEY"]: | |
| raise ValueError("KAGGLE_USERNAME or KAGGLE_KEY not set in environment!") | |
| api = KaggleApi() | |
| api.authenticate() | |
| MODEL_PATH = "model.pkl" | |
| if not os.path.exists(MODEL_PATH): | |
| api.dataset_download_file("myfaizal/model", file_name="model.pkl", path=".", unzip=True) | |
| bert_model = SentenceTransformer('all-MiniLM-L6-v2') | |
| def CarPricePrediction(car_names, car_prices, car_sold): | |
| # inisialisasi | |
| p_scaler = joblib.load('modeling/results/price_norm.pkl') | |
| eop_scaler = joblib.load('modeling/results/eop_norm.pkl') | |
| model = joblib.load(MODEL_PATH) | |
| pattern = re.compile(r"^Rp\.?\s?\d{1,3}(\.\d{3})+$") | |
| name_pattern = re.compile(r"^(19[8-9][0-9]|20[0-2][0-9]|2025)\s+\w+(\s+\w+)+$", re.IGNORECASE) | |
| names = car_names.strip() | |
| prices = car_prices.strip() | |
| car_sold = int(car_sold) | |
| if not pattern.match(prices): | |
| return 'Harga harus berformat rupiah misal: Rp. 2.000.000 atau Rp 2.000.000' | |
| if not name_pattern.match(names): | |
| return 'Nama mobil harus berformat: <tahun> Mistubishi Pajero' | |
| test = { | |
| 'car_names': [names], | |
| 'car_prices': [prices] | |
| } | |
| test_df = pd.DataFrame(test) | |
| # feature engineering | |
| test_df['year'] = test_df['car_names'].str.extract(r'(\b\d{4}\b)').astype(int) | |
| if car_sold < test_df['year'].tolist()[0]: | |
| return "Tidak bisa tahun penjualan kurang dari tahun pembelian" | |
| test_df['car_names_clean'] = test_df['car_names'].str.replace(r'^\d{4}\s+', '', regex=True).str.split(r' - ').str[0].str.strip() | |
| test_df['estimated_original_price'] = test_df['car_prices'].str.replace(r'\D', '', regex=True).apply(lambda x: int(x) if x else None) | |
| test_df['ages'] = test_df['year'].apply(lambda x: car_sold - int(x)) | |
| test_df['eop_norm'] = eop_scaler.transform(test_df[['estimated_original_price']]) | |
| car_names_embeddings = bert_model.encode(test_df['car_names_clean'].tolist(), show_progress_bar=True) | |
| car_names_df = pd.DataFrame(car_names_embeddings, columns=[f'bert_{i}' for i in range(car_names_embeddings.shape[1])]) | |
| test_input = pd.concat([car_names_df, test_df[['eop_norm', 'ages']].reset_index(drop=True)], axis=1) | |
| test_result = model.predict(test_input) | |
| test_result = p_scaler.inverse_transform(np.array(test_result).reshape(-1, 1)) | |
| test_result = test_result.flatten() | |
| test_result_str = [f"Rp. {format(round(n), ',').replace(',', '.')}" for n in test_result] | |
| test_df['deprecate_percentage'] = ((test_df['estimated_original_price'] - round(test_result[0])) / test_df['estimated_original_price']) | |
| return f""" | |
| Informasi penjualan: | |
| - {car_names} | |
| - Harga pembelian: {car_prices} | |
| - Harga penjualan: {test_result_str[0]} | |
| - Tahun penjualan: {car_sold} | |
| - Depresiasi sebesar: {round(test_df['deprecate_percentage'].tolist()[0]*100)}% | |
| """ |