尝试使用 SPY 数据训练简单 LSTM 后出错

Question

我认为这些错误与我的数据格式或我的代码与数据集交互的方式有关，但无论如何我都不是开发人员，所以我不太确定这是怎么回事。

/Users/kylehammerberg/PycharmProjects/LSTM1P/matplottest.py:54: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (这是一个列表或元组的列表或元组或具有不同长度或形状的 ndarray ) 已弃用。如果您打算这样做，则必须在创建 ndarray 时指定 'dtype=object' X_test = np.array(X_test) 回溯（最近一次通话最后）： 文件“/Users/kylehammerberg/PycharmProjects/LSTM1P/matplottest.py”，第 55 行，在 X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1)) IndexError: 元组索引超出范围

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import keras

url = 'https://raw.githubusercontent.com/khammerberg53/MLPROJ1/main/SP500.csv'
dataset_train = pd.read_csv(url)
training_set = dataset_train.iloc[:, 1:2].values

dataset_train.head()
print(dataset_train.head())

from sklearn.preprocessing import MinMaxScaler
sc = MinMaxScaler(feature_range=(0,1))
training_set_scaled = sc.fit_transform(training_set)

X_train = []
y_train = []
for i in range(60, 2000):
    X_train.append(training_set_scaled[i-60:i, 0])
    y_train.append(training_set_scaled[i, 0])
X_train, y_train = np.array(X_train), np.array(y_train)
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dropout
from keras.layers import Dense

model = Sequential()
model.add(LSTM(units=50,return_sequences=True,input_shape=(X_train.shape[1], 1)))
model.add(Dropout(0.2))
model.add(LSTM(units=50,return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50,return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=1))
model.compile(optimizer='adam',loss='mean_squared_error')
model.fit(X_train,y_train,epochs=100,batch_size=32)

url = 'https://raw.githubusercontent.com/khammerberg53/MLPROJ1/main/SP500%20test%20setcsv.csv'
dataset_test = pd.read_csv(url)
real_stock_price = dataset_test.iloc[:, 1:2].values

dataset_total = pd.concat((dataset_train['Value'], dataset_test['Value']), axis = 0)
inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values
inputs = inputs.reshape(-1,1)
inputs = sc.transform(inputs)
X_test = []
for i in range(3, 100):
    X_test.append(inputs[i-60:i, 0])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
predicted_stock_price = model.predict(X_test)
predicted_stock_price = sc.inverse_transform(predicted_stock_price)

plt.plot(real_stock_price, color = 'black', label = 'TATA Stock Price')
plt.plot(predicted_stock_price, color = 'green', label = 'Predicted TATA Stock Price')
plt.title('TATA Stock Price Prediction')
plt.xlabel('Time')
plt.ylabel('TATA Stock Price')
plt.legend()
plt.show()

print(plt.show())

Answer 1

如果您按照自己的方式定义X_test，则范围不能从 3 到 100。如果您将代码更改为：

inputs = inputs.reshape(-1,1)
inputs = sc.transform(inputs)
X_test = []
for i in range(60, 161):
    X_test.append(inputs[i-60:i, 0])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))

其余代码将产生（我只用了 2 个 epoch，可能会解释预测不是您所期望的）：

使用 20 个 epoch，你会得到：