我尝试为时间序列训练神经网络。我使用了一些来自 Covid 的数据，主要目标是了解 14 天的住院人数来预测 J+1 的人数。我已经使用了一些提前停止来避免过度拟合，但几乎是两倍以上的学习停止耐心+1，并且损失和 val_loss 没有减少。我试图移动像学习率这样的超参数，但问题总是在这里。有什么猜测吗？
主要代码如下，整个代码包含数据：https ://github.com/paullaurain/prediction
import os
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from keras.models import load_model
from keras.optimizers import Adam
from sklearn.preprocessing import MinMaxScaler
# fit a model
def model_fit(data, config):
# unpack config
n_in,n_out, n_nodes, n_epochs, n_batch,p,pl = config
# prepare data
DATA = series_to_supervised(data, n_in, n_out)
X, Y = DATA[:, :-n_out], DATA[:, n_in:]
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.1)
# define model
model = Sequential()
model.add(Dense(4*n_nodes, activation= 'relu', input_dim=n_in))
model.add(Dense(2*n_nodes, activation= 'relu'))
model.add(Dense(n_nodes, activation= 'relu'))
model.add(Dense(n_out, activation= 'relu'))
model.compile(loss='mse' , optimizer='adam',metrics=['mse'])
# fit
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=p)
file='best_modelDense.hdf5'
mc = ModelCheckpoint(filepath=file, monitor='loss', mode='min', verbose=0, save_best_only=True)
history=model.fit(X_train, y_train, validation_data=(X_test,y_test), epochs=n_epochs, verbose=0,batch_size=n_batch, callbacks=[es,mc])
if pl:
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
saved_model=load_model(file)
os.remove(file)
return history.history['val_loss'][-p], saved_model
# repeat evaluation of a config
def repeat_evaluate(data,n_test, config, n_repeat,plot):
# rescale data
scaler = MinMaxScaler(feature_range=(0, 1))
scaler = scaler.fit(data)
scaled_data=scaler.transform(data)
scores=[]
for _ in range(n_repeat):
score, model= model_fit(scaled_data[:-n_test], config)
scores.append(score)
# plot the prediction id asked
if plot:
y=[]
x=[]
for i in range(n_test,0,-1):
y.append(float(model.predict(scaled_data[-14-i:-i].reshape(1,14))))
x.append(scaled_data[-i])
X=scaler.inverse_transform(x)
plt.plot(X)
Y=scaler.inverse_transform(np.array([y]))
plt.plot(Y.reshape(10,1))
plt.title('result')
plt.legend(['real', 'prdiction'], loc='upper left')
plt.show()
return scores
# summarize model performance
def summarize_scores(name, scores):
# print a summary
scores_m, score_std = mean(scores), std(scores)
print( '%s: %.3f RMSE (+/- %.3f)' % (name, scores_m, score_std))
# box and whisker plot
pyplot.boxplot(scores)
pyplot.show()
#setting variable
n_in=14
n_out=1
n_repeat=5
n_test=10
# define config n_in, n_out, n_nodes, n_epochs, n_batch, pateince, draw loss
config = [n_in, n_out, 10, 2000, 50, 200,True]
# compute scores
scores = repeat_evaluate(data,n_test, config, n_repeat, True)
print(scores)
# summarize scores
summarize_scores('mlp ', scores)
结果：
