07. DNN 코딩 실습

1. 패키지 로딩

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from keras.models import Sequential
from keras.layers import Dense
from keras.callbacks import EarlyStopping
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, roc_auc_score, precision_score

 

2. 하이퍼 파라미터 설정

INPUT_DIM = 13
MY_EPOCH = 100
MY_BATCH = 32
MY_SPLIT = 0.4

 

3. 데이터 로딩 및 확인

heart.xls

0.06MB

data = pd.read_excel('heart.xls')
print(data.shape)
display(data.head())
data.describe()
data.info()
# 결측치 확인
print(data.isna().sum())

 

4. 데이터 스케일링

from sklearn.preprocessing import StandardScaler

X = data.drop('target', axis=1)
y = data['target']
scaler =  StandardScaler()
scaled_data = scaler.fit_transform(X)
scaled_data = pd.DataFrame(scaled_data, columns=X.columns)
print(scaled_data.describe())

boxplot = scaled_data.boxplot(figsize=(10,7), showmeans=True)
plt.show()

 

5. 학습/평가 데이터 분할

X_train, X_test, y_train, y_test = train_test_split(scaled_data, y, test_size=MY_SPLIT, random_state=10)
X_train.shape, X_test.shape, y_train.shape, y_test.shape

X_val, X_test, y_val, y_test = train_test_split(X_test, y_test, test_size=0.5, random_state=0)
X_val.shape, X_test.shape, y_val.shape, y_test.shape

 

6. 모델 생성

# Ouput Shape (None, 1000): None-> 배치 사이즈가 정해지지 않아서 None으로 표기됨
from keras.layers import Dropout
from keras import regularizers
model = Sequential()
model.add(Dense(1000, activation='tanh', input_dim=INPUT_DIM, kernel_regularizer=regularizers.l2(0.02)))
model.add(Dense(1000, activation='tanh', kernel_regularizer=regularizers.l2(0.1)))
model.add(Dropout(rate=0.5))
model.add(Dense(1, activation='sigmoid'))
model.summary()

 

7. 모델 컴파일 및 학습

from keras.callbacks import TensorBoard
import datetime

# log_dir: 로그가 기록될 디렉토리 경로 (경로에 한글이 포함되면 안됨)
log_dir = 'c:\\Logs\\'+datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard = TensorBoard(log_dir=log_dir, histogram_freq=1)

from keras.callbacks import EarlyStopping
early_stop = EarlyStopping(monitor='val_loass', mode='min', patience=3)

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=MY_BATCH, epochs=MY_EPOCH, validation_data=(X_val, y_val),verbose=1, callbacks=[tensorboard, early_stop])
model.save('heart-disease.h5')

 

8. 예측 및 모델 평가

y_pred_prob = model.predict(X_test)
y_pred = (y_pred_prob > 0.5)
print('\n== CONFUSION MATRIX ==')
print(confusion_matrix(y_test, y_pred))

score = model.evaluate(X_test, y_test, verbose=1)#, callbacks=[tensorboard])
print('Loss:',score[0])
print('Accuracy:',score[1])

print('Precision:',precision_score(y_test, y_pred))
print('AUC:', roc_auc_score(y_test, y_pred_prob))