42 lines
1.3 KiB
Python
42 lines
1.3 KiB
Python
import pandas as pd
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.preprocessing import LabelEncoder
|
|
import joblib
|
|
|
|
# Memuat data dari file Excel
|
|
data = pd.read_excel('D:/Skripsi/ekstraksi fitur/data_fitur.xlsx')
|
|
|
|
# Pisahkan fitur dan label
|
|
X = data[['Jumlah Objek', 'Eccentricity Rata-Rata', 'Metric Rata-Rata', 'Area Total', 'Perimeter Total']]
|
|
y = data['Label']
|
|
|
|
# Encode label menjadi numerik
|
|
le = LabelEncoder()
|
|
y = le.fit_transform(y)
|
|
|
|
# Bagi data menjadi subset pelatihan dan pengujian
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=9)
|
|
|
|
# Inisialisasi dan latih model Random Forest
|
|
rf_model = RandomForestClassifier(n_estimators=13, random_state=9)
|
|
rf_model.fit(X_train, y_train)
|
|
|
|
# Simpan model yang telah dilatih
|
|
model_path = 'D:/Skripsi/ekstraksi fitur/rf_model.joblib'
|
|
joblib.dump(rf_model, model_path)
|
|
print(f"Model disimpan di {model_path}")
|
|
|
|
# Prediksi kelas pada subset pengujian
|
|
y_pred = rf_model.predict(X_test)
|
|
|
|
# Evaluasi kinerja model
|
|
accuracy = accuracy_score(y_test, y_pred)
|
|
print("Accuracy:", accuracy)
|
|
|
|
# Simpan LabelEncoder
|
|
label_encoder_path = 'D:/Skripsi/ekstraksi fitur/label_encoder.joblib'
|
|
joblib.dump(le, label_encoder_path)
|
|
print(f"Label encoder disimpan di {label_encoder_path}")
|