python - LSTM-Keras 错误 : ValueError: non-broadcastable output operand with shape (67704, 1) 与广播形状不匹配 (67704,12)

Question

大家早上好。我正在尝试使用 Keras 和 pandas 来实现这个 LSTM 算法，以读取 csv 文件。我使用的后端是 Tensorflow。在预测训练集之前反转结果时，我遇到了问题。下面是我的代码

import numpy
import matplotlib.pyplot as plt
import pandas
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error


#plt.plot(dataset)
#plt.show()

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

#Load dataset
col_names = ['UserID','SysTouchTime', 'EventTime', 'ActivityTouchID', 'Pointer_count', 'PointerID',
                'ActionID', 'Touch_X', 'Touch_Y', 'Touch_Pressure', 'Contact_Size', 'Phone_Orientation']
dataframe = pandas.read_csv('touchEventsFor5Users.csv', engine='python', header=None, names = col_names, skiprows=1)
#print(dataset.head())
#print(dataset.shape)
dataset = dataframe.values
dataset = dataframe.astype('float32')
print(dataset.isnull().any())
dataset = dataset.fillna(method='ffill')
feature_cols = ['SysTouchTime', 'EventTime', 'ActivityTouchID', 'Pointer_count', 'PointerID', 'ActionID', 'Touch_X', 'Touch_Y', 'Touch_Pressure', 'Contact_Size', 'Phone_Orientation']

X = dataset[feature_cols]
y = dataset['UserID']
print(y.head())
#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),:]
print(len(train), len(test))

# 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), 0]
        dataX.append(a)
        dataY.append(dataset[i + look_back, 0])
    return numpy.array(dataX), numpy.array(dataY)

# reshape into X=t and Y=t+1
look_back = 1
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], 1, trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

#create and fit the LSTM network
model = Sequential()
model.add(LSTM(4, input_dim=look_back))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
model.fit(trainX, trainY, epochs=1, batch_size=32, verbose=2)

# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# invert predictions
import gc
gc.collect()

#####problem occurs with the following line of code#############

trainPredict = scaler.inverse_transform(trainPredict)

trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
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(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()

我得到的错误是

ValueError:形状为 (67704,1) 的不可广播输出操作数与广播形状 (67704,12) 不匹配

你们能帮我解决这个问题吗？我对此很陌生，但非常想学习它，这个错误让我很痛苦!感谢您提供的任何帮助。

Answer 1

当您缩放数据时，它将以不同的方式缩放 12 个字段。它将获取每个字段的 minmax 并将其转换为 0 到 1 的值。

当你进行 invert_transform 时，它对函数没有任何意义，因为你只给它一个字段，它不知道如何处理它，它的最小值和最大值是多少......你需要提供一个12 个字段的数据集，这个预测字段位于正确的位置。

尝试在有问题的行之前添加此内容:

# create empty table with 12 fields
trainPredict_dataset_like = np.zeros(shape=(len(train_predict), 12) )
# put the predicted values in the right field
trainPredict_dataset_like[:,0] = trainPredict[:,0]
# inverse transform and then select the right field
trainPredict = scaler.inverse_transform(trainPredict_dataset_like)[:,0]

这有帮助吗？ :)