Question

大家早上好。我正在尝试使用Keras和pandas来实现这个LSTM算法，以便读入csv文件。我正在使用的后端是Tensorflow。在预测训练集之前，我遇到了反转我的结果的问题。以下是我的代码

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：形状不可广播的输出操作数（67704,1）与广播形状不匹配（67704,12）

认为你们可以帮我解决这个问题？我对此非常陌生，但想要了解它，这个错误让我受苦！感谢您提供的任何帮助。

Answer 1

缩放数据时，它会以不同方式缩放12个字段。它将采用每个字段的最小值并将其转换为0到1的值。

当你制作一个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什么......你需要提供一个12个字段数据集，预测字段位于正确的位置。

尝试在有问题的行之前添加：

# 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？：）

LSTM-Keras错误：ValueError：具有形状（67704,1）的不可广播输出操作数与广播形状不匹配（67704,12）

1 个答案: