分類問題的時候用交叉熵損失函數會更有效

# 分類問題的時候用交叉熵損失函數會更有效
# binary_crossentropy 來計算二元交叉熵
import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv('credit-a.csv', header=None)
# 數據15列是標籤
# print(data.head())
# print(data.iloc[:, -1].value_counts())
x = data.iloc[:, :-1]
aa = data.iloc[:, -1]
y = data.iloc[:, -1].replace(-1, 0)

# 定義模型
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(4, input_shape=(15,), activation='relu'))
model.add(tf.keras.layers.Dense(4, activation='relu'))  # 隱藏層
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
# print(model.summary())

# 編譯
model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['acc'])  # 正確率
# 訓練過程
history = model.fit(x, y, epochs=100)
# print(history.history.keys())   ['loss','acc']
# plt.plot(history.epoch,history.history.get('loss'))
plt.plot(history.epoch,history.history.get('acc'))
plt.show()