File size: 3,002 Bytes
0630ed4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | # train_emotion.py
import pandas as pd
import re
import joblib
import os
from datasets import load_dataset
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
# ==========================================
# 🔧 KONFIGURASI
# ==========================================
MODEL_OUTPUT = 'api/data/model_emotion.pkl'
# ==========================================
print("🔍 Mengunduh dataset GoEmotions...")
try:
dataset = load_dataset("google-research-datasets/go_emotions", "simplified", split="train")
df = pd.DataFrame(dataset)
labels_list = dataset.features['labels'].feature.names
def get_first_label(label_ids):
if len(label_ids) > 0:
return labels_list[label_ids[0]]
return "neutral"
df['emotion_label'] = df['labels'].apply(get_first_label)
X = df['text']
y = df['emotion_label']
print(f"✅ Data siap: {len(df)} baris.")
except Exception as e:
print(f"❌ Error: {e}")
exit()
# --- CLEANING DATA ---
def clean_text(text):
text = str(text).lower()
text = re.sub(r'http\S+', '', text)
text = re.sub(r'[^a-zA-Z\s]', '', text)
text = re.sub(r'\s+', ' ', text).strip()
return text
print("🧹 Membersihkan data emosi...")
X = X.apply(clean_text)
# --- TRAINING ---
print("🚀 Melatih Model Emosi (Logistic Regression Fixed)...")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
pipeline = Pipeline([
('tfidf', TfidfVectorizer(
max_features=12000, # Fitur banyak biar detail
stop_words='english',
ngram_range=(1, 2), # Baca kata per kata & frasa
sublinear_tf=True # [TRICK] Scaling logaritmik (Penting!)
)),
('clf', LogisticRegression(
max_iter=1000,
solver='lbfgs', # Ganti ke lbfgs biar aman dari error multiclass
C=1.2 # Agak agresif dikit (di atas 1.0) biar akurasi naik
))
])
pipeline.fit(X_train, y_train)
# --- EVALUASI ---
print("📊 Menghitung Metrik Evaluasi...")
predictions = pipeline.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
precision, recall, f1, _ = precision_recall_fscore_support(y_test, predictions, average='weighted', zero_division=0)
print("\n" + "="*40)
print(" HASIL EVALUASI MODEL EMOSI (FINAL)")
print("="*40)
print(f"{'Metrik':<15} | {'Skor':<10}")
print("-" * 30)
print(f"{'Akurasi':<15} | {accuracy:.3f} ({accuracy*100:.1f}%)")
print(f"{'Precision':<15} | {precision:.3f}")
print(f"{'Recall':<15} | {recall:.3f}")
print(f"{'F1-Score':<15} | {f1:.3f}")
print("="*40 + "\n")
os.makedirs(os.path.dirname(MODEL_OUTPUT), exist_ok=True)
joblib.dump(pipeline, MODEL_OUTPUT)
print(f"💾 SUKSES! Model Emosi disimpan di: {MODEL_OUTPUT}") |