ValueError：操作数无法与形状一起广播 (1,108) (3,) (1,108)

Question

import pandas as pd
import numpy as np
from numpy import array
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense
from sklearn.preprocessing import MinMaxScaler

# split a multivariate sequence into samples
def split_sequences(sequences, n_steps, n_test):
    X, y = list(), list()

    for i in range(0,len(sequences),100):
        # find the end of this pattern
        end_ix = i + n_steps
        # check if we are beyond the dataset
        if i!=0 and end_ix > len(sequences):
            break

        sequences[i:end_ix,0]=np.insert(np.diff(sequences[i:end_ix,0]),0,0)
        # gather input and output parts of the pattern
        seq_x, seq_y = sequences[i:end_ix-n_test], sequences[end_ix-n_test:end_ix]

        X.append(seq_x)
        y.append(seq_y)
    return array(X), array(y)

df = pd.read_csv('time-series-19-covid-combined.csv')
df = df.drop(['Lat','Long'], axis = 1)
df.columns = ['day','country', 'territory','confirmed','recovered','deaths']

data=df[df.country.isin(['Australia','Costa Rica','Greece','Hungary','Israel'])][['confirmed','recovered','deaths']]

is_brazil =  (df['country']=='Brazil')

data2=df[(is_brazil)][['confirmed','recovered','deaths']]
date=df[(is_brazil)][['day','confirmed']]
date.day = pd.to_datetime(date.day,format='%Y%m%d', errors='ignore')
date.set_index('day', inplace=True)

n_features = data.shape[1] # this is number of parallel inputs
n_timesteps = date.shape[0] # this is number of timesteps
n_test = int(n_timesteps*0.25)

X, Y = split_sequences(data.values, n_timesteps, n_test)

#normalization#####################################################
alld=np.concatenate((X,Y),1)
alld=alld.reshape(alld.shape[0]*alld.shape[1],alld.shape[2])



scaler = MinMaxScaler()
scaler.fit(alld)
X=[scaler.transform(x) for x in X]
y=[scaler.transform(y) for y in Y]

X=np.array(X)
y=np.array(y)[:,:,0]

# define model
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_timesteps - n_test, n_features)))
model.add(Dense(y.shape[1]))
model.compile(optimizer='adam', loss='mse')

# fit model
model.fit(X, y, epochs=200, verbose=1)

# evaluation

data2x=data2
truth = data2

data2x.values[0:len(data2x),0]=np.insert(np.diff(data2x.values[0:len(data2x),0]),0,0)
data2x=scaler.transform(data2x)

X_test = np.expand_dims(data2x, axis=0)

yhat = model.predict(X_test[:,-n_timesteps + n_test:,:], verbose=0)

print (data2x[-n_timesteps + n_test:,0], yhat)

actual_predictions = scaler.inverse_transform(np.tile(yhat, (1, 1, 3))[0])[:,0]

大小和值：

X: float-64 (16,108,3) 数组

X_test: float-64 (1,144,3) 数组

Y: float-64 (16,36,3) 数组

alld: float-64 (2304,3) 数组

数据：数据框 (1728,3)

data2: 数据框 (144,3)

data2x：float-64 (144,3) 数组

日期：数据框 (144,1)

df: 数据框 (38448,6)

is_brazil: 系列 (38448,)

n_features：3（整数）

n_test: 36 (int)

n_timesteps: 144 (int)

真相：数据框 (144,3)

y: float-64 (16,36) 数组

yhat: float-32 (1,36) 数组

我打算在我的项目中做的是使用来自特定国家/地区的确诊病例、康复患者和死亡人数的数据来训练 LSTM，并尝试预测另一个国家/地区的病例数。例如：使用来自澳大利亚、哥斯达黎加、希腊、匈牙利和以色列的数据训练 LSTM，并尝试预测巴西的病例数。

找到原始代码here 并尝试使用 Keras 对其进行编码，但是在上面的最后一行代码中，当我尝试反向规范化时，我遇到了错误：ValueError:operands could not be broadcast连同形状 (1,108) (3,) (1,108)

我不知道可以做些什么来解决这个问题。在其他线程中搜索，但没有成功。任何解决方案将不胜感激。

最好的问候，

海高。

Answer 1

解决了。

我之前添加了一条缺失的重塑线：

lstm_out=lstm_out.reshape(1,144,1).cpu().data.numpy()