[220928 ABC] 피마족 인디언 당뇨병 발병 유무 예측(정규화 추가 ver)

문제 정의 : 피마족 인디언 당뇨병 발병 유무를 예측하는 이진 분류 문제 (당뇨병 1, 정상 0)

데이터 준비하기

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

import tensorflow as tf
from keras.models import Sequential
from keras.layers ipmort Dense

# 랜덤 시드 고정
np.random.seed(5)

dataset = pd.read_csv('/content/diabetes/csv')
dataset.head()

dataset.info()

데이터 분리하기

dataset.columns

X = dataset[['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',
       'BMI', 'DiabetesPedigreeFunction', 'Age']]
y = dataset['Outcome']

from sklearn import preprocessiong

# 정규화하기
X = preprocessing.StandardScaler().fit(X).transform(X)

# train:test => 80:20 -> 614:154
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=777)

X_train.shape

모델 구성하기

model = Sequential()
model.add(Dense(32, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid))

model.summary()

tf.keras.utils.plot_model(model, show_shape=True, show_layer_names=True, 
                         rankdir='TB', expand_nested=False, dpi=100)

모델 설정하기

model.compile(loss='binary_crossentropy', optimize='adam', metric=['accuracy'])

모델 학습하기

history = model.fit(X_train, y_train, epochs=100, batch_size=128)

학습 결과

import matplotlib.pyplot as plt

his_dict = history.history
loss = his_dict['loss']

epochs = range(1, len(loss)+1)
fig = plt.figure(figsize = (10, 5))

# 훈련 및 검증 손실 그리기
ax1 = fig.add_subplot(1, 2, 1)
ax1.plot(epochs, loss, color = 'orange', label = 'train_loss')
ax1.set_title('train loss')
ax1.set_xlabel('epochs')
ax1.set_ylabel('loss')
ax1.legend()

acc = his_dict['accuracy']

# 훈련 및 검증 정확도 그리기
ax2 = fig.add_subplot(1, 2, 2)
ax2.plot(epochs, acc, color = 'blue', label = 'train_accuracy')
ax2.set_title('train accuracy')
ax2.set_xlabel('epochs')
ax2.set_ylabel('accuracy')
ax2.legend()

plt.show()

모델 평가하기

scores = model.evaluate(X_test, y_test)
print('%s : %.2f%%' %(model.metrics_names[1], scores[1]*100))

print(model.metrics_names[0], scores[0])

scores = model.evaluate(X_train, y_train)
print('%s: %.2f%%' %(model.metrics_names[1], scores[1]*100))