如何循环通过各种训练和测试拆分

Question

我使用 TimeSeriesSplit() 创建了各种训练和测试拆分。我的数据框有 377 个观察值，包含 6 个输入变量和 1 个目标变量。

我使用以下代码将我的数据框拆分为训练和测试：

#train set 
i=0
for X_train, X_test in tscv.split(data):
    i=i+1
    print ("No of observations under train%s=%s"%(i,len(X_train)))
    print ("No of observations under test%s=%s" % (i, len(X_test)))

X_train1, X_test1 = data[:67, :-1],  data[67:129,:-1]
X_train2, X_test2 = data[:129,:-1], data[129:191,:-1]
X_train3, X_test3 = data[:191,:-1], data[191:253,:-1]
X_train4, X_test4 = data[:253,:-1], data[253:315,:-1]
X_train5, X_test5 = data[:315,:-1], data[315:377,:-1]

#test set
i=0
for y_train, y_test in tscv.split(data):
    i=i+1
    print ("No of observations under train%s=%s"%(i,len(y_train)))
    print ("No of observations under test%s=%s" % (i, len(y_test)))

y_train1, y_test1 = data[:67, -1], data[67:129 ,-1]
y_train2, y_test2 = data[:129,-1], data[129:191,-1]
y_train3, y_test3 = data[:191,-1], data[191:253,-1]
y_train4, y_test4 = data[:253,-1], data[253:315,-1]
y_train5, y_test5 = data[:315,-1], data[315:377,-1]

所以我总共有 5 个拆分。我想通过这些拆分训练我的 lstm 模型，但我不确定我能做到最好。这是我的 lstm 的代码：

# split into input and outputs
train_X, train_y = X_train, y_train
test_X, test_y = X_test, y_test

#reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,LSTM, Flatten
import matplotlib.pyplot as pyplot
# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
history = model.fit(train_X, train_y, epochs=700
                    , batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)

# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()

#predictions
y_lstm = model.predict(test_X)

#metrics for test set
mse_lstm = mean_squared_error(y_test, y_lstm)
rmse_lstm = np.sqrt(mse_lstm)
r2_lstm = r2_score(y_test, y_lstm)
mae_lstm = mean_absolute_error(y_test, y_lstm)

#train metics
train     = model.predict(X_t_reshaped)
msetrain  = mean_squared_error(y_train, train)
rmsetrain = np.sqrt(msetrain)
r2train   = r2_score(y_train, train)

如何使用上述代码循环遍历所有不同的拆分并将结果存储在列表或数据框中？

我还想绘制如下图所示的预测结果

这是基于@Ashraful 答案的图表

Answer 1

用这个替换你的最后一个代码块，

from sklearn.metrics import  mean_squared_error
from sklearn.metrics import *
import numpy as np
import csv  

Round = 3      # define the number of digits after decimal point you want 

fields = ['Fold_No', 'mse_lstm', 'rmse_lstm', 'r2_lstm','mae_lstm']  
csvfile = open('Summary.csv', 'w') 
csvwriter = csv.writer(csvfile)  
csvwriter.writerow(fields) 


for fold in range(1,6):
    print(f'Running fold {fold}')
    # split into input and outputs
    train_X, train_y = eval(f'X_train{fold}'),eval(f'y_train{fold}')
    test_X, test_y = eval(f'X_test{fold}'),eval(f'y_test{fold}')
    print(train_X.shape)



    #reshape input to be 3D [samples, timesteps, features]
    train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
    test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))

    from tensorflow.keras.models import Sequential
    from tensorflow.keras.layers import Dense,LSTM, Flatten
    import matplotlib.pyplot as pyplot
    # design network
    model = Sequential()
    model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
    model.add(Dense(1))
    model.compile(loss='mae', optimizer='adam')
    history = model.fit(train_X, train_y, epochs=2
                        , batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)

    # plot history
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='test')
    pyplot.legend()
    pyplot.show()

    #predictions
    train_output =  model.predict(train_X)
    y_lstm = model.predict(test_X)

    pyplot.plot(train_output, label='Training output')
    pyplot.plot(train_y, label='Obesrved Training Target')
    # pyplot.plot(train_y, label='Training value')
    pyplot.plot(test_y, label='Obesrved Predic. Target')
    pyplot.plot(y_lstm, label='Predicted Output')
    pyplot.legend(loc='upper right')
    # pyplot.legend()
    pyplot.show()
    
    #metrics for test set
    mse_lstm = mean_squared_error(y_test1, y_lstm)
    rmse_lstm = np.sqrt(mse_lstm)
    r2_lstm = r2_score(y_test1, y_lstm)
    mae_lstm = mean_absolute_error(y_test1, y_lstm)

    csvwriter.writerow([f'Fold_{fold}',round(mse_lstm,Round), round(rmse_lstm,Round), round(r2_lstm,Round),round(mae_lstm,Round)]) 


csvfile.close()

#read stored CSV file
summary= pd.read_csv('Summary.csv')

print(summary)

另外，我在 colab 文件中的实现，你可以找到 here。