python - 如何使用 python 使用回归模型将预测值转换为 NaN 输入值

Question

假设我有四个输入，并且我想预测第一个输入值的下一个 2 小时值当我尝试预测值时，第一个输入列包含 NaN。

我试图跳过 NaN 值，我试图将早期的预测值转移到该输入列中。但它对我不起作用。

[ 120   30  40  50 
  110   20  10  20
  NaN   12  30  30
  120   50  60  70
  NaN   10  28  40]  inputs to the model

我期望的输出 训练模型时

[ 120   30  40  50 = pred1 
  110   20  10  20 = pred2
  pred2 12  30  30 = pred3
  120   50  60  70 = pred4
  pred4 10  28  40 = pred5 ]

现在，当训练模型时，NaN 值被删除，早期的预测值应该移动到该 NaN 值位置。 我为此编写了代码，但它对我不起作用。这是我的代码:

model.reset_states()
pred= model.predict(x_test_n) 
pred_count=pred[0]
forecasts=[]
next_pred=[]
for col in range(len(x_test_n)-1):
print('Prediction %s: ' % str(pred))
next_pred_res = np.reshape(next_pred, (next_pred.shape[1], 1, next_pred.shape[0]))
# make predictions
forecastPredict = model.predict(next_pred_res, batch_size=1)
forecastPredictInv = scaler.inverse_transform(forecastPredict)
forecasts.append(forecastPredictInv)
next_pred = next_pred[1:]
next_pred = np.concatenate([next_pred, forecastPredict])

pred_count += 1

谁能帮我解决这个错误吗？我只想用 NaN 值移动早期的预测值。

Answer 1

您可以迭代每一行，获取预测并填充 nan。如下所示，即

prev_preds = 0
preds = []

# For each row of the dataframe get the predictions. 
for _,row in df.iterrows(): 
   # Fill the missing values with previous prediction, initially it will be zero.  
   row = row.fillna(prev_preds)
   # Now get the prediction and store it in an array
   preds.append(model.predict([row.values]))
   # Update the previous prediction to new prediction by accessing last element of the predictions array. 
   prev_preds = preds[-1]

# Assign the predictions to a new column in dataframe
df['predictions'] = preds