使用 keras 输入形状的 LSTM 多对一预测答案

【问题标题】：LSTM many to one prediction using keras input shape使用 keras 输入形状的 LSTM 多对一预测
【发布时间】：2017-12-30 02:50:30
【问题描述】：

最初，我有一个包含 6 列的 csv 文件：日期、用电量和 4 个其他对消耗有影响的气候特征（例如温度、湿度等）

到目前为止，我只能在消费列上运行我的 LSTM，它给了我非常准确的结果，但我需要为我的 LSTM 提供其他功能。我尝试根据之前的 cmets here 修改 python 代码，但仍然出现 reshape 错误。

这是我修改后的代码：

import numpy
import matplotlib.pyplot as plt
import pandas
import math

from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error


# convert an array of values into a dataset matrix

def create_dataset(dataset, look_back=1):
  dataX, dataY = [], []
  for i in range(len(dataset) - look_back - 1):
    a = dataset[i:(i + look_back), :]
    dataX.append(a)
    dataY.append(dataset[i + look_back, 2])
  return numpy.array(dataX), numpy.array(dataY)


  # fix random seed for reproducibility
numpy.random.seed(7)


# load the dataset
dataframe = pandas.read_csv('out_meteo.csv', engine='python') 
dataset = dataframe.values

# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

# split into train and test sets
train_size = int(len(dataset) * 0.67) 
test_size = len(dataset) - train_size
train, test = dataset[0:train_size, :], dataset[train_size:len(dataset), :]

# reshape into X=t and Y=t+1
look_back = 3
trainX, trainY = create_dataset(train, look_back)  
testX, testY = create_dataset(test, look_back)

# reshape input to be  [samples, time steps, features]
trainX = numpy.reshape(trainX, (trainX.shape[0], look_back, 3))
testX = numpy.reshape(testX, (testX.shape[0],look_back, 3))

# create and fit the LSTM network

model = Sequential()
model.add(LSTM(4, input_shape=(look_back,3)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
history= model.fit(trainX, trainY,validation_split=0.33, nb_epoch=5, batch_size=32)



# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# Get something which has as many features as dataset
trainPredict_extended = numpy.zeros((len(trainPredict),3))
# Put the predictions there
trainPredict_extended[:,2] = trainPredict
# Inverse transform it and select the 3rd column.
trainPredict = scaler.inverse_transform(trainPredict_extended)[:,2]

print(trainPredict)
# Get something which has as many features as dataset
testPredict_extended = numpy.zeros((len(testPredict),3))
# Put the predictions there
testPredict_extended[:,2] = testPredict[:,0]
# Inverse transform it and select the 3rd column.
testPredict = scaler.inverse_transform(testPredict_extended)[:,2]   


trainY_extended = numpy.zeros((len(trainY),3))
trainY_extended[:,2]=trainY
trainY=scaler.inverse_transform(trainY_extended)[:,2]


testY_extended = numpy.zeros((len(testY),3))
testY_extended[:,2]=testY
testY=scaler.inverse_transform(testY_extended)[:,2]


# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY, trainPredict))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY, testPredict))
print('Test Score: %.2f RMSE' % (testScore))

# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, 2] = trainPredict

# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, 2] = testPredict

 # plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()

我得到的错误如下

Traceback (most recent call last):
  File "desp.py", line 48, in <module>
    trainX = numpy.reshape(trainX, (trainX.shape[0], look_back, 3))
  File "/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py",  line 232, in reshape
    return _wrapfunc(a, 'reshape', newshape, order=order)
  File "/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py",  line 57, in _wrapfunc
    return getattr(obj, method)(*args, **kwds)
ValueError: cannot reshape array of size 35226 into shape (1957,3,3)

请注意，我还是个新手，reshape 的概念对我来说还是有点模糊。

【问题讨论】：

这就是答案：无法将大小为 35226 的数组重塑为形状 (1957,3,3)
但是好吧，请给我看看 trainX 和 testX 的形状。
trainX.shape= (1957, 3, 6) testX.shape= (963, 3, 6)
你看到问题了吗？你有一个形状为 (1957, 3, 6) 的张量，它等于 1957 * 3 * 6 = 35226。你想将你的张量重塑为一个新的形状 (1957,3,3) = 17613。所以，问题是您的新尺寸不合适。作为一种解决方法，我建议删除所有重塑功能。并将输入形状更改为 (look_back, 6)

标签： python numpy neural-network keras lstm

【解决方案1】：

作为对您的问题的回答，我建议检查 python / numpy 中的多维列表/数组。

另外，这里是一个关于 Keras 中张量形状的解释链接

https://github.com/fchollet/keras/issues/2045

【讨论】：

【解决方案2】：

这是我的最终代码，包含所有列

import numpy
import matplotlib.pyplot as plt
import pandas
import math

from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back=1):
   dataX, dataY = [], []
   for i in range(len(dataset) - look_back - 1):
     a = dataset[i:(i + look_back), :]
     dataX.append(a)
     dataY.append(dataset[i + look_back, 2])
   return numpy.array(dataX), numpy.array(dataY)


 # fix random seed for reproducibility
numpy.random.seed(7)

#load the dataset
dataframe = pandas.read_csv('out_meteo.csv', engine='python') 
dataset = dataframe.values

# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

# split into train and test sets
train_size = int(len(dataset) * 0.7) 
test_size = len(dataset) - train_size
train, test = dataset[0:train_size, :], dataset[train_size:len(dataset), :]

# reshape into X=t and Y=t+1
look_back = 3
trainX, trainY = create_dataset(train, look_back)  
testX, testY = create_dataset(test, look_back)


# create and fit the LSTM network

model = Sequential()
model.add(LSTM(20, input_shape=(look_back,6)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
history= model.fit(trainX, trainY,validation_split=0.33, nb_epoch=15, batch_size=15)

# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

print(trainPredict)

# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY, trainPredict))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY, testPredict))
print('Test Score: %.2f RMSE' % (testScore))

# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict

# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict

 # plot baseline and predictions
plt.plot((dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()

到目前为止，它在我的所有 csv 列上都运行良好，我还删除了许多行（reshape、MinMAxScaler 转换）但仍然无法正确可视化我的最终数据（使用实际值），它显示的值非常小或严格线。
该数据集的返回训练和测试分数分别为 0.03 和 0.05

【讨论】：

【解决方案3】：

在绘图之前，尝试做

testPredict = scaler.inverse_transform(testPredict)

【讨论】：