<p>这是我的最后一个代码,它包含了所有的列</p>
<pre><code>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()
</code></pre>
<p>到目前为止,它在我所有的csv列上都运行得很好,我还删除了许多行(重塑、MinMAxScaler转换),但仍然无法正确地可视化我的最终数据(使用实际值),它显示的是非常小的值或严格的行。<br/>
该数据集的返回序列和测试分数分别为0.03和0.05</p>