IndexError: tuple index out of range (LSTM)
IndexError: tuple index out of range (LSTM)
当我遇到 LSTM 模型的指数错误时，我正在关注一个 python 项目来粗略地预测股票价格。这是我遵循的指南，我的代码大致匹配：Prediction Tutorial。但为了便于访问，这正是我的代码：
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()
根据我遵循的教程，此代码应该可以正常工作，但每次我 运行 代码时，我都会收到此错误消息：
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
我不知道这到底是什么意思，也不知道如何解决。
LSTM 层的预期输入形状为 (batch, timesteps, features)。由于你只有一个特征，你可以按如下方式重塑你的训练序列
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], 1)
正如您已经对验证序列所做的那样。
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')
当我遇到 LSTM 模型的指数错误时，我正在关注一个 python 项目来粗略地预测股票价格。这是我遵循的指南，我的代码大致匹配：Prediction Tutorial。但为了便于访问，这正是我的代码：
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()
根据我遵循的教程，此代码应该可以正常工作，但每次我 运行 代码时，我都会收到此错误消息：
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
我不知道这到底是什么意思，也不知道如何解决。
LSTM 层的预期输入形状为 (batch, timesteps, features)。由于你只有一个特征，你可以按如下方式重塑你的训练序列
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], 1)
正如您已经对验证序列所做的那样。
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')