"""
Models.py - Modul Model Klasifikasi dan Vektorisasi TF-IDF
Proyek Tugas Akhir: Analisis Sentimen Komentar Berbasis TF-IDF & Logistic Regression

Modul ini menangani:
1. Pemuatan pre-trained TF-IDF Vectorizer dan model Logistic Regression
2. Transformasi teks bersih ke vektor TF-IDF
3. Perhitungan skor probabilitas dan decision value
4. Ekstraksi fitur n-gram dominan berserta bobot koefisiennya
"""

import os
import time
import warnings
import joblib
from typing import Dict, Any

warnings.filterwarnings("ignore")

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
MODEL_PATH = os.path.join(BASE_DIR, "model_logistic_regression.pkl")
TFIDF_PATH = os.path.join(BASE_DIR, "tfidf_vectorizer.pkl")

# Memuat model dan vectorizer saat modul diimpor
model = joblib.load(MODEL_PATH)
tfidf = joblib.load(TFIDF_PATH)


def predict_sentiment(teks_bersih: str) -> Dict[str, Any]:
    """
    Melakukan inferensi klasifikasi sentimen berdasarkan teks yang telah diproses:
    - X = tfidf.transform([teks_bersih])
    - Prediksi label: POSITIF / NEGATIF
    - Probabilitas Sigmoid untuk tiap kelas
    - Nilai Decision Function (z = w*x + b)
    - Ekstraksi kontribusi bobot fitur dominan
    """
    start_time = time.time()
    if not teks_bersih or not teks_bersih.strip():
        return {
            "success": True,
            "sentimen": "GAGAL DIANALISIS",
            "preprocessing": "",
            "probabilitas": {
                "negatif": 0.0,
                "positif": 0.0
            },
            "keyakinan": 0.0,
            "decision_value": 0.0,
            "fitur_dominan": [],
            "elapsed_ms": 0.5,
            "keterangan": "Hasil preprocessing kosong (tidak dapat dianalisis)."
        }

    # Transformasi TF-IDF
    X = tfidf.transform([teks_bersih])

    # Ekstraksi Fitur N-Gram Dominan
    feature_names = tfidf.get_feature_names_out()
    non_zero_indices = X.nonzero()[1]
    has_features = len(non_zero_indices) > 0
    elapsed_ms = round((time.time() - start_time) * 1000, 1)

    # Bila fitur kata tidak ditemukan pada TF-IDF, jangan gunakan bias model
    if not has_features:
        return {
            "success": True,
            "sentimen": "FITUR TIDAK DITEMUKAN",
            "preprocessing": teks_bersih,
            "probabilitas": {
                "negatif": 0.0,
                "positif": 0.0
            },
            "keyakinan": 0.0,
            "decision_value": 0.0,
            "fitur_dominan": [],
            "fitur_ditemukan": False,
            "keterangan": "Fitur tidak ditemukan",
            "elapsed_ms": max(1.0, elapsed_ms)
        }

    # Prediksi Label dan Probabilitas hanya bila fitur kata ditemukan
    hasil_prediksi = model.predict(X)[0]
    proba = model.predict_proba(X)[0]
    prob_negatif = float(proba[0])
    prob_positif = float(proba[1])
    decision_val = float(model.decision_function(X)[0])

    features_info = []
    for idx in non_zero_indices:
        token = feature_names[idx]
        val = float(X[0, idx])
        weight = float(model.coef_[0, idx])
        features_info.append({
            "token": token,
            "tfidf": round(val, 4),
            "weight": round(weight, 4)
        })

    # Urutkan berdasarkan nilai absolut kontribusi fitur
    features_info.sort(key=lambda item: abs(item['weight'] * item['tfidf']), reverse=True)
    top_features = features_info[:8]
    keyakinan = (prob_negatif if hasil_prediksi == 'NEGATIF' else prob_positif) * 100

    return {
        "success": True,
        "sentimen": str(hasil_prediksi),
        "preprocessing": teks_bersih,
        "probabilitas": {
            "negatif": round(prob_negatif, 4),
            "positif": round(prob_positif, 4)
        },
        "keyakinan": round(keyakinan, 1),
        "decision_value": round(decision_val, 4),
        "fitur_dominan": top_features,
        "fitur_ditemukan": True,
        "keterangan": "Fitur berhasil diekstraksi",
        "elapsed_ms": max(1.0, elapsed_ms)
    }


if __name__ == "__main__":
    test_clean = "sok cantik banget"
    hasil = predict_sentiment(test_clean)
    print("Hasil Prediksi:", hasil)