如何在测试训练好的 LSTM 模型后预测实际的未来值？
How to predict actual future values after testing the trained LSTM model?
我通过将数据集拆分为训练和测试来训练我的股票价格预测模型。
我还通过比较有效数据和预测数据来测试预测，模型运行良好。
但我想预测 实际 未来值。
我需要在下面的代码中更改什么？
如何预测到 实际 未来的特定日期？
代码（在 Jupyter Notebook 中）：
（对于 运行 代码，请在您拥有的类似 csv 文件中尝试，或使用命令 pip install nsepy 安装 nsepy python 库）
# imports
import pandas as pd # data processing
import numpy as np # linear algebra
import matplotlib.pyplot as plt # plotting
from datetime import date # date
from nsepy import get_history # NSE historical data
from keras.models import Sequential # neural network
from keras.layers import LSTM, Dropout, Dense # LSTM layer
from sklearn.preprocessing import MinMaxScaler # scaling
nseCode = 'TCS'
stockTitle = 'Tata Consultancy Services'
# API call
apiData = get_history(symbol = nseCode, start = date(2017,1,1), end = date(2021,12,19))
data = apiData # copy the dataframe (not necessary)
# remove columns you don't need
del data['Symbol']
del data['Series']
del data['Prev Close']
del data['Volume']
del data['Turnover']
del data['Trades']
del data['Deliverable Volume']
del data['%Deliverble']
# store the data in a csv file
data.to_csv('infy2.csv')
# Read the csv file
data = pd.read_csv('infy2.csv')
# convert the date column to datetime; if you read data from csv, do this. Otherwise, no need if you read data from API
data['Date'] = pd.to_datetime(data['Date'], format = '%Y-%m-%d')
data.index = data['Date']
# plot
plt.xlabel('Date')
plt.ylabel('Close Price (Rs.)')
data['Close'].plot(legend = True, figsize = (10,6), title = stockTitle, grid = True, color = 'blue')
# Sort data into Date and Close columns
data2 = data.sort_index(ascending = True, axis = 0)
newData = pd.DataFrame(index = range(0,len(data2)), columns = ['Date', 'Close'])
for i in range(0, len(data2)): # only if you read data from csv
newData['Date'][i] = data2['Date'][i]
newData['Close'][i] = data2['Close'][I]
# Calculate the row number to split the dataset into train and test
split = len(newData) - 100
# normalize the new dataset
scaler = MinMaxScaler(feature_range = (0, 1))
finalData = newData.values
trainData = finalData[0:split, :]
validData = finalData[split:, :]
newData.index = newData.Date
newData.drop('Date', axis = 1, inplace = True)
scaler = MinMaxScaler(feature_range = (0, 1))
scaledData = scaler.fit_transform(newData)
xTrainData, yTrainData = [], []
for i in range(60, len(trainData)): # data-flair has used 60 instead of 30
xTrainData.append(scaledData[i-60:i, 0])
yTrainData.append(scaledData[i, 0])
xTrainData, yTrainData = np.array(xTrainData), np.array(yTrainData)
xTrainData = np.reshape(xTrainData, (xTrainData.shape[0], xTrainData.shape[1], 1))
# build and train the LSTM model
lstmModel = Sequential()
lstmModel.add(LSTM(units = 50, return_sequences = True, input_shape = (xTrainData.shape[1], 1)))
lstmModel.add(LSTM(units = 50))
lstmModel.add(Dense(units = 1))
inputsData = newData[len(newData) - len(validData) - 60:].values
inputsData = inputsData.reshape(-1,1)
inputsData = scaler.transform(inputsData)
lstmModel.compile(loss = 'mean_squared_error', optimizer = 'adam')
lstmModel.fit(xTrainData, yTrainData, epochs = 1, batch_size = 1, verbose = 2)
# Take a sample of a dataset to make predictions
xTestData = []
for i in range(60, inputsData.shape[0]):
xTestData.append(inputsData[i-60:i, 0])
xTestData = np.array(xTestData)
xTestData = np.reshape(xTestData, (xTestData.shape[0], xTestData.shape[1], 1))
predictedClosingPrice = lstmModel.predict(xTestData)
predictedClosingPrice = scaler.inverse_transform(predictedClosingPrice)
# visualize the results
trainData = newData[:split]
validData = newData[split:]
validData['Predictions'] = predictedClosingPrice
plt.xlabel('Date')
plt.ylabel('Close Price (Rs.)')
trainData['Close'].plot(legend = True, color = 'blue', label = 'Train Data')
validData['Close'].plot(legend = True, color = 'green', label = 'Valid Data')
validData['Predictions'].plot(legend = True, figsize = (12,7), grid = True, color = 'orange', label = 'Predicted Data', title = stockTitle)
下面是如何为您的模型实施 this approach 的示例：
import pandas as pd
import numpy as np
from datetime import date
from nsepy import get_history
from keras.models import Sequential
from keras.layers import LSTM, Dense
from sklearn.preprocessing import MinMaxScaler
pd.options.mode.chained_assignment = None
# load the data
stock_ticker = 'TCS'
stock_name = 'Tata Consultancy Services'
train_start = date(2017, 1, 1)
train_end = date.today()
data = get_history(symbol=stock_ticker, start=train_start, end=train_end)
data.index = pd.DatetimeIndex(data.index)
data = data[['Close']]
# scale the data
scaler = MinMaxScaler(feature_range=(0, 1)).fit(data)
z = scaler.transform(data)
# extract the input sequences and target values
window_size = 60
x, y = [], []
for i in range(window_size, len(z)):
x.append(z[i - window_size: i])
y.append(z[i])
x, y = np.array(x), np.array(y)
# build and train the model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=x.shape[1:]))
model.add(LSTM(units=50))
model.add(Dense(units=1))
model.compile(loss='mse', optimizer='adam')
model.fit(x, y, epochs=100, batch_size=128, verbose=1)
# generate the multi-step forecasts
def multi_step_forecasts(n_past, n_future):
x_past = x[- n_past - 1:, :, :][:1] # last observed input sequence
y_past = y[- n_past - 1] # last observed target value
y_future = [] # predicted target values
for i in range(n_past + n_future):
# feed the last forecast back to the model as an input
x_past = np.append(x_past[:, 1:, :], y_past.reshape(1, 1, 1), axis=1)
# generate the next forecast
y_past = model.predict(x_past)
# save the forecast
y_future.append(y_past.flatten()[0])
# transform the forecasts back to the original scale
y_future = scaler.inverse_transform(np.array(y_future).reshape(-1, 1)).flatten()
# add the forecasts to the data frame
df_past = data.rename(columns={'Close': 'Actual'}).copy()
df_future = pd.DataFrame(
index=pd.bdate_range(start=data.index[- n_past - 1] + pd.Timedelta(days=1), periods=n_past + n_future),
columns=['Forecast'],
data=y_future
)
return df_past.join(df_future, how='outer')
# forecast the next 30 days
df1 = multi_step_forecasts(n_past=0, n_future=30)
df1.plot(title=stock_name)
# forecast the last 20 days and the next 30 days
df2 = multi_step_forecasts(n_past=20, n_future=30)
df2.plot(title=stock_name)
我通过将数据集拆分为训练和测试来训练我的股票价格预测模型。 我还通过比较有效数据和预测数据来测试预测，模型运行良好。 但我想预测 实际 未来值。
我需要在下面的代码中更改什么？
如何预测到 实际 未来的特定日期？
代码（在 Jupyter Notebook 中）：
（对于 运行 代码，请在您拥有的类似 csv 文件中尝试，或使用命令 pip install nsepy 安装 nsepy python 库）
# imports
import pandas as pd # data processing
import numpy as np # linear algebra
import matplotlib.pyplot as plt # plotting
from datetime import date # date
from nsepy import get_history # NSE historical data
from keras.models import Sequential # neural network
from keras.layers import LSTM, Dropout, Dense # LSTM layer
from sklearn.preprocessing import MinMaxScaler # scaling
nseCode = 'TCS'
stockTitle = 'Tata Consultancy Services'
# API call
apiData = get_history(symbol = nseCode, start = date(2017,1,1), end = date(2021,12,19))
data = apiData # copy the dataframe (not necessary)
# remove columns you don't need
del data['Symbol']
del data['Series']
del data['Prev Close']
del data['Volume']
del data['Turnover']
del data['Trades']
del data['Deliverable Volume']
del data['%Deliverble']
# store the data in a csv file
data.to_csv('infy2.csv')
# Read the csv file
data = pd.read_csv('infy2.csv')
# convert the date column to datetime; if you read data from csv, do this. Otherwise, no need if you read data from API
data['Date'] = pd.to_datetime(data['Date'], format = '%Y-%m-%d')
data.index = data['Date']
# plot
plt.xlabel('Date')
plt.ylabel('Close Price (Rs.)')
data['Close'].plot(legend = True, figsize = (10,6), title = stockTitle, grid = True, color = 'blue')
# Sort data into Date and Close columns
data2 = data.sort_index(ascending = True, axis = 0)
newData = pd.DataFrame(index = range(0,len(data2)), columns = ['Date', 'Close'])
for i in range(0, len(data2)): # only if you read data from csv
newData['Date'][i] = data2['Date'][i]
newData['Close'][i] = data2['Close'][I]
# Calculate the row number to split the dataset into train and test
split = len(newData) - 100
# normalize the new dataset
scaler = MinMaxScaler(feature_range = (0, 1))
finalData = newData.values
trainData = finalData[0:split, :]
validData = finalData[split:, :]
newData.index = newData.Date
newData.drop('Date', axis = 1, inplace = True)
scaler = MinMaxScaler(feature_range = (0, 1))
scaledData = scaler.fit_transform(newData)
xTrainData, yTrainData = [], []
for i in range(60, len(trainData)): # data-flair has used 60 instead of 30
xTrainData.append(scaledData[i-60:i, 0])
yTrainData.append(scaledData[i, 0])
xTrainData, yTrainData = np.array(xTrainData), np.array(yTrainData)
xTrainData = np.reshape(xTrainData, (xTrainData.shape[0], xTrainData.shape[1], 1))
# build and train the LSTM model
lstmModel = Sequential()
lstmModel.add(LSTM(units = 50, return_sequences = True, input_shape = (xTrainData.shape[1], 1)))
lstmModel.add(LSTM(units = 50))
lstmModel.add(Dense(units = 1))
inputsData = newData[len(newData) - len(validData) - 60:].values
inputsData = inputsData.reshape(-1,1)
inputsData = scaler.transform(inputsData)
lstmModel.compile(loss = 'mean_squared_error', optimizer = 'adam')
lstmModel.fit(xTrainData, yTrainData, epochs = 1, batch_size = 1, verbose = 2)
# Take a sample of a dataset to make predictions
xTestData = []
for i in range(60, inputsData.shape[0]):
xTestData.append(inputsData[i-60:i, 0])
xTestData = np.array(xTestData)
xTestData = np.reshape(xTestData, (xTestData.shape[0], xTestData.shape[1], 1))
predictedClosingPrice = lstmModel.predict(xTestData)
predictedClosingPrice = scaler.inverse_transform(predictedClosingPrice)
# visualize the results
trainData = newData[:split]
validData = newData[split:]
validData['Predictions'] = predictedClosingPrice
plt.xlabel('Date')
plt.ylabel('Close Price (Rs.)')
trainData['Close'].plot(legend = True, color = 'blue', label = 'Train Data')
validData['Close'].plot(legend = True, color = 'green', label = 'Valid Data')
validData['Predictions'].plot(legend = True, figsize = (12,7), grid = True, color = 'orange', label = 'Predicted Data', title = stockTitle)
下面是如何为您的模型实施 this approach 的示例：
import pandas as pd
import numpy as np
from datetime import date
from nsepy import get_history
from keras.models import Sequential
from keras.layers import LSTM, Dense
from sklearn.preprocessing import MinMaxScaler
pd.options.mode.chained_assignment = None
# load the data
stock_ticker = 'TCS'
stock_name = 'Tata Consultancy Services'
train_start = date(2017, 1, 1)
train_end = date.today()
data = get_history(symbol=stock_ticker, start=train_start, end=train_end)
data.index = pd.DatetimeIndex(data.index)
data = data[['Close']]
# scale the data
scaler = MinMaxScaler(feature_range=(0, 1)).fit(data)
z = scaler.transform(data)
# extract the input sequences and target values
window_size = 60
x, y = [], []
for i in range(window_size, len(z)):
x.append(z[i - window_size: i])
y.append(z[i])
x, y = np.array(x), np.array(y)
# build and train the model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=x.shape[1:]))
model.add(LSTM(units=50))
model.add(Dense(units=1))
model.compile(loss='mse', optimizer='adam')
model.fit(x, y, epochs=100, batch_size=128, verbose=1)
# generate the multi-step forecasts
def multi_step_forecasts(n_past, n_future):
x_past = x[- n_past - 1:, :, :][:1] # last observed input sequence
y_past = y[- n_past - 1] # last observed target value
y_future = [] # predicted target values
for i in range(n_past + n_future):
# feed the last forecast back to the model as an input
x_past = np.append(x_past[:, 1:, :], y_past.reshape(1, 1, 1), axis=1)
# generate the next forecast
y_past = model.predict(x_past)
# save the forecast
y_future.append(y_past.flatten()[0])
# transform the forecasts back to the original scale
y_future = scaler.inverse_transform(np.array(y_future).reshape(-1, 1)).flatten()
# add the forecasts to the data frame
df_past = data.rename(columns={'Close': 'Actual'}).copy()
df_future = pd.DataFrame(
index=pd.bdate_range(start=data.index[- n_past - 1] + pd.Timedelta(days=1), periods=n_past + n_future),
columns=['Forecast'],
data=y_future
)
return df_past.join(df_future, how='outer')
# forecast the next 30 days
df1 = multi_step_forecasts(n_past=0, n_future=30)
df1.plot(title=stock_name)
# forecast the last 20 days and the next 30 days
df2 = multi_step_forecasts(n_past=20, n_future=30)
df2.plot(title=stock_name)