IndexError：元組索引超出范圍（LSTM）

當我遇到 LSTM 模型的指數錯誤時，我正在關注一個 Python 專案來粗略地預測股票的價格。這是我遵循的指南，我的代碼大致匹配：Prediction Tutorial。但為了便于訪問，這正是我的代碼：

import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import LSTM, Dropout, Dense
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
from matplotlib.pylab import rcParams
rcParams['figure.figsize'] = 20, 10

df = pd.read_csv('HistoricalData_Apple.csv')
df = df[['Date', 'Close/Last']]
df = df.replace({'\$':''}, regex=True)
df = df.astype({"Close/Last": float})
df["Date"] = pd.to_datetime(df.Date, format="%m/%d/%Y")
df.index = df['Date']

df = df.sort_index(ascending=True, axis=0)
data = pd.DataFrame(index=range(0, len(df)), columns=['Date', 'Close/Last'])

for i in range(0, len(data)):
    data["Date"][i] = df['Date'][i]
    data["Close/Last"][i] = df["Close/Last"][i]

scaler = MinMaxScaler(feature_range=(0, 1))

data.index = data.Date
data.drop("Date", axis=1, inplace=True)

final_data = data.values
train_data = final_data[0:200, :]
valid_data = final_data[200:, :]

scaler = MinMaxScaler(feature_range=(0, 1))

scaled_data = scaler.fit_transform(final_data)
x_train_data, y_train_data = [], []
for i in range(60, len(train_data)):
    x_train_data.append(scaled_data[i-60:i, 0])
    y_train_data.append(scaled_data[i, 0])

lstm_model = Sequential()
lstm_model.add(LSTM(units=50, return_sequences=True, input_shape= 
(np.shape(x_train_data)[1], 1)))
lstm_model.add(LSTM(units=50))
lstm_model.add(Dense(1))

model_data = data[len(data)-len(valid_data)-60:].values
model_data = model_data.reshape(-1, 1)
model_data = scaler.transform(model_data)

lstm_model.compile(loss='mean_squared_error', optimizer='adam')
lstm_model.fit(x_train_data, y_train_data, epochs=1, batch_size=1, verbose=2)
X_test=[]
for i in range(60, model_data.shape[0]):
    X_test.append(model_data[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 = lstm_model.predict(X_test)
predicted_stock_price = scaler.inverse_transform(predicted_stock_price)

train_data = data[:200]
valid_data = data[200:]
valid_data['Predictions'] = predicted_stock_price
plt.plot(train_data["Close"])
plt.plot(valid_data[['Close', "Predictions"]])
plt.show()

此代碼應該根據我所關注的教程作業，但每次運行代碼時，我都會收到此錯誤訊息：

2021-11-08 14:57:34.659018: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 

Traceback (most recent call last): File "C:/Users/ME/AppData/Roaming/JetBrains/PyCharmCE2021.2/scratches/scratch_1.py", line 42, in <module> lstm_model.add(LSTM(units=50, return_sequences=True, input_shape=(np.shape(x_train_data)[1], 1))) IndexError: tuple index out of range

我不知道這究竟是什么意思或如何解決它。

uj5u.com熱心網友回復：

LSTM 層的預期輸入形狀是(batch, timesteps, features)。由于您只有一個特征，因此您可以按如下方式重塑訓練序列

x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], 1)

正如您已經為驗證序列所做的那樣。

import pandas as pd
import numpy as np
import yfinance as yf
from keras.models import Sequential
from keras.layers import LSTM, Dense
from sklearn.preprocessing import MinMaxScaler
pd.options.mode.chained_assignment = None

# download the data
df = yf.download(tickers=['AAPL'], period='10y')

# split the data
train_data = df[['Close']].iloc[: - 200, :]
valid_data = df[['Close']].iloc[- 200:, :]

# scale the data
scaler = MinMaxScaler(feature_range=(0, 1))
scaler.fit(train_data)

train_data = scaler.transform(train_data)
valid_data = scaler.transform(valid_data)

# extract the training sequences
x_train, y_train = [], []

for i in range(60, train_data.shape[0]):
    x_train.append(train_data[i - 60: i, 0])
    y_train.append(train_data[i, 0])

x_train = np.array(x_train)
y_train = np.array(y_train)

# extract the validation sequences
x_valid = []

for i in range(60, valid_data.shape[0]):
    x_valid.append(valid_data[i - 60: i, 0])

x_valid = np.array(x_valid)

# reshape the sequences
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], 1)
x_valid = x_valid.reshape(x_valid.shape[0], x_valid.shape[1], 1)

# train the model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=x_train.shape[1:]))
model.add(LSTM(units=50))
model.add(Dense(1))

model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(x_train, y_train, epochs=50, batch_size=128, verbose=1)

# generate the model predictions
y_pred = model.predict(x_valid)
y_pred = scaler.inverse_transform(y_pred)
y_pred = y_pred.flatten()

# plot the model predictions
df.rename(columns={'Close': 'Actual'}, inplace=True)
df['Predicted'] = np.nan
df['Predicted'].iloc[- y_pred.shape[0]:] = y_pred
df[['Actual', 'Predicted']].plot(title='AAPL')

標籤：Python 张量流 机器学习 凯拉斯 lstm

上一篇：通過ReLU激活過度擬合小資料集

下一篇：如何在py腳本的azuredevopspipline中呼叫repo路徑