运行以下代码时出现错误（'DataFrame' 对象没有属性 'as_matrix'）

Question

基本 LSTM 模型导入 keras 库

import math
import pandas as pd
import numpy as np
from IPython.display import display

from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential
from keras.metrics import mean_squared_error
from sklearn.model_selection import StratifiedKFold

import lstm, time #helper libraries

import visualize as vs
import stock_data as sd
import LinearRegressionModel

stocks = pd.read_csv('E:/DBSOM DATA\FOM_Sem 2/Analyses of S&U Data/Project work/Stock-Price-Prediction-master/google_preprocessed.csv')
stocks_data = stocks.drop(['Item'], axis =1)

display(stocks_data.head())

拆分训练和测试数据集并展开 lstm 模型的训练和测试数据

    X_train, X_test,y_train, y_test = sd.train_test_split_lstm(stocks_data, 5)

    unroll_length = 50
    X_train = sd.unroll(X_train, unroll_length)
    X_test = sd.unroll(X_test, unroll_length)
    y_train = y_train[-X_train.shape[0]:]
    y_test = y_test[-X_test.shape[0]:]

    print("x_train", X_train.shape)
    print("y_train", y_train.shape)
    print("x_test", X_test.shape)
    print("y_test", y_test.shape)

功能定义

将数据集拆分为长短期记忆模型的训练和测试特征

def train_test_split_lstm(stocks, prediction_time=1, test_data_size=450, unroll_length=50):  

# training data
test_data_cut = test_data_size + unroll_length + 1
x_train = stocks[0:-prediction_time - test_data_cut].values
y_train = stocks[prediction_time:-test_data_cut]['Close'].values

# test data
x_test = stocks[0 - test_data_cut:-prediction_time].values
y_test = stocks[prediction_time - test_data_cut:]['Close'].values
return x_train, x_test, y_train, y_test

使用不同的窗口进行测试和训练，以防止数据中的信息泄漏

def unroll(data, sequence_length=24):
result = []
for index in range(len(data) - sequence_length):
    result.append(data[index: index + sequence_length])
return np.asarray(result)

错误

AttributeError                            Traceback (most recent call last)
<ipython-input-52-59aa6ad29ad5> in <module>
----> 1 X_train, X_test,y_train, y_test = sd.train_test_split_lstm(stocks_data, 5)
  2 
  3 unroll_length = 50
  4 X_train = sd.unroll(X_train, unroll_length)
  5 X_test = sd.unroll(X_test, unroll_length)

~\Stock Price Prediction\stock_data.py in train_test_split_lstm(stocks, prediction_time, test_data_size, unroll_length)
 77     test_data_cut = test_data_size + unroll_length + 1
 78 
 ---> 79     x_train = stocks[0:-prediction_time - test_data_cut].to_numpy()
 80     y_train = stocks[prediction_time:-test_data_cut]['Close'].to_numpy()
 81 

~\anaconda3\envs\tensorflow\lib\site-packages\pandas\core\generic.py in __getattr__(self, name)
5128             if 
self._info_axis._can_hold_identifiers_and_holds_name(name):
5129                 return self[name]
-> 5130             return object.__getattribute__(self, name)
5131 
5132     def __setattr__(self, name: str, value) -> None:

AttributeError: 'DataFrame' object has no attribute 'as_matrix'

Answer 1

我错误地导入了这个 sklearn.preprocessing.StandardScaler。 删除这行代码后，一切顺利