Улучшение модели LSTM для торговли акциями и ускорения выполнения кода ⇐ Python

[Anonymous]

Я работал над алгоритмом торговли акциями, используя модель LSTM. Алгоритм получает данные в реальном времени, делает прогнозы и решает, покупать или продавать акции в зависимости от прогнозируемой цены. Вот код: < /p>

Код: Выделить всё

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from keras.layers import LSTM, Dense
import time
import requests

# Define the stock symbol and your Alpha Vantage API key
symbol = 'AAPL'
api_key = 'MY_API'

# Define the initial capital
initial_capital = 10000
capital = initial_capital

# Brokerage fee per stock
brokerage_fee_per_stock = 0.02

# Minimum brokerage fee
min_brokerage_fee = 18

# SEC tax rate
sec_tax_rate = 0.0000278

# Create a dataframe to store the capital and actions over time
capital_df = pd.DataFrame(columns=['time', 'capital', 'action', 'price'])
capital_df.loc[0] = {'time': pd.Timestamp.now(), 'capital': capital, 'action': 'Initial', 'price': 0}  # Initialize with initial capital

# Define lookback period
lookback = 60

# Define the LSTM model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(lookback, 1)))
model.add(LSTM(units=50))
model.add(Dense(1))

# Compile the LSTM model
model.compile(loss='mean_squared_error', optimizer='adam')

while True:
# Fetch real-time data using Alpha Vantage API
url = f'https://www.alphavantage.co/query?function=TIME_SERIES_INTRADAY&symbol={symbol}&interval=1min&apikey={api_key}'
response = requests.get(url)
data = response.json()
current_price = float(data['Time Series (1min)'][list(data['Time Series (1min)'].keys())[0]]['4. close'])

# Preprocess the data
scaler = MinMaxScaler(feature_range=(0, 1))
price_data = np.array([current_price for _ in range(lookback)]).reshape(-1, 1)
scaled_data = scaler.fit_transform(price_data)

# Prepare inputs for the LSTM model
inputs = scaled_data.reshape(1, lookback, 1)

# Fit the LSTM model
model.fit(inputs, np.array([current_price]), epochs=1, batch_size=1, verbose=2)

# Make predictions using the trained LSTM model
predicted_price = model.predict(inputs)
predicted_price = scaler.inverse_transform(predicted_price)[0][0]

# Calculate the number of stocks to buy or sell
num_stocks = capital // current_price

# Calculate the total brokerage fee for buying and selling
total_brokerage_fee = max(brokerage_fee_per_stock * num_stocks, min_brokerage_fee) * 2

# Calculate the SEC tax
sec_tax = sec_tax_rate * predicted_price * num_stocks

# Update capital based on predicted price and record the action
if predicted_price > current_price:
capital += num_stocks * current_price - total_brokerage_fee - sec_tax
action = 'Buy'
else:
capital -= num_stocks * current_price + total_brokerage_fee + sec_tax
action = 'Sell'

# Append the current capital and action to the dataframe
new_row = {'time': pd.Timestamp.now(), 'capital': capital, 'action': action, 'price': current_price}
capital_df = pd.concat([capital_df, pd.DataFrame([new_row])], ignore_index=True)

# Plot the capital over time
plt.figure(figsize=(10, 5))
plt.plot(capital_df['time'], capital_df['capital'])
plt.title('Capital Over Time')
plt.xlabel('Time')
plt.ylabel('Capital')
plt.xticks(rotation=45)
plt.gca().xaxis.set_major_locator(plt.MaxNLocator(10))  # Show 10 ticks
plt.show()

print(f'Current earning: {capital - initial_capital}, Action: {action} at price: {current_price}')

# Wait for 1 minute
time.sleep(60)
< /code>
У меня есть несколько вопросов, касающихся этого: < /p>

  странный сюжет: < /em> сюжет Капитал со временем выглядит странно. Это буквально просто линия. Я не уверен, почему это происходит, но я считаю, что это может занять некоторую статистическую проблему. Может ли это быть из -за того, как я обновляю и планирую запланировать капитал? />  Это странный сюжет на второй минуте < /p>
Это странный сюжет на третьей минуте < /p>
Это странный сюжет На четвертой минуте 
Это странный сюжет на пятой минуте 
Это странный сюжет на шестой минуте 
Странная вещь в том, что сюжет, кажется, не следует за «правилом инвестиций». Интуитивно заговор должен начинаться с 10000, и было бы много колебаний, а не одну прямую линию.  Что кажется очень странным. Кроме того, ось X сюжета, которая представляет время, показывает ту же ярлык для всех клещей. в минуту. < /li>
 Как я могу изменить код так, чтобы этикетки оси x показали правильное время для каждого действия? < /li>
< /ol>
) < /p>

   точное время и действие: < /em> Я хочу, чтобы мой код указал точное время и точное действие (покупка/продажа), которые рассчитывает модель LSTM. Как я могу этого добиться? Минут. Тем не менее, в настоящее время это занимает более минуты. Есть ли какие -нибудь способы оптимизировать код, чтобы он работал быстрее? < /P>
< /li>
< /ol>
Помогает, вот мои пересмотренные коды: < /p>
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from keras.layers import LSTM, Dense
import time
import requests

# Define the stock symbol and your Alpha Vantage API key
symbol = 'AAPL'
api_key = 'MY_API'

# Define the initial capital
initial_capital = 10000
capital = initial_capital

# Brokerage fee per stock
brokerage_fee_per_stock = 0.02

# Minimum brokerage fee
min_brokerage_fee = 18

# SEC tax rate
sec_tax_rate = 0.0000278

# Create a dataframe to store the capital and actions over time
capital_df = pd.DataFrame(columns=['time', 'capital', 'action', 'price'])
capital_df.loc[0] = {'time': pd.Timestamp.now(), 'capital': capital, 'action': 'Initial', 'price': 0}  # Initialize with initial capital

# Define lookback period
lookback = 60

# Define the LSTM model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(lookback, 1)))
model.add(LSTM(units=50))
model.add(Dense(1))

# Compile the LSTM model
model.compile(loss='mean_squared_error', optimizer='adam')

# Create the plot before the loop
plt.figure(figsize=(10, 5))
plt.title('Capital Over Time')
plt.xlabel('Time')
plt.ylabel('Capital')
plt.xticks(rotation=45)
plt.gca().xaxis.set_major_locator(plt.MaxNLocator(10))  # Show 10 ticks
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d %H:%M'))  # Format the time up to minutes

# Initialize a flag for the first iteration and the action
first_iteration = True
action = 'Initial'

while True:
start_time = time.time()  # Start the timer

# Fetch real-time data using Alpha Vantage API
url = f'https://www.alphavantage.co/query?function=TIME_SERIES_INTRADAY&symbol={symbol}&interval=1min&apikey={api_key}'
response = requests.get(url)
data = response.json()
current_price = float(data['Time Series (1min)'][list(data['Time Series (1min)'].keys())[0]]['4.  close'])

# Preprocess the data
scaler = MinMaxScaler(feature_range=(0, 1))
price_data = np.array([current_price for _ in range(lookback)]).reshape(-1, 1)
scaled_data = scaler.fit_transform(price_data)

# Prepare inputs for the LSTM model
inputs = scaled_data.reshape(1, lookback, 1)

# Fit the LSTM model
model.fit(inputs, np.array([current_price]), epochs=1, batch_size=1, verbose=2)

# Make predictions using the trained LSTM model
predicted_price = model.predict(inputs)
predicted_price = scaler.inverse_transform(predicted_price)[0][0]

# Calculate the number of stocks to buy or sell
num_stocks = capital // current_price

# Calculate the total brokerage fee for buying and selling
total_brokerage_fee = max(brokerage_fee_per_stock * num_stocks, min_brokerage_fee) * 2

# Calculate the SEC tax
sec_tax = sec_tax_rate * predicted_price * num_stocks

# Update capital based on predicted price and record the action
if first_iteration:
first_iteration = False
elif predicted_price >  current_price:
capital += num_stocks * current_price - total_brokerage_fee - sec_tax
action = 'Buy'
else:
capital -= num_stocks * current_price + total_brokerage_fee + sec_tax
action = 'Sell'

# Append the current capital and action to the dataframe
new_row = {'time': pd.Timestamp.now(), 'capital': capital, 'action': action, 'price': current_price}
capital_df = pd.concat([capital_df, pd.DataFrame([new_row])], ignore_index=True)

# Update the plot data without creating it all again
plt.plot(capital_df['time'], capital_df['capital'])
plt.gcf().autofmt_xdate()  # Autoformat the time label for better display
plt.draw()
plt.pause(0.01)  # Pause for the plot to update

print(f'Current earning: {capital - initial_capital}, Action: {action} at price: {current_price}')

# Calculate the elapsed time and wait for the remaining time to complete 60 seconds
elapsed_time = time.time() - start_time
time.sleep(max(60 - elapsed_time, 0))
< /code>
Вот мои вопросы сейчас: < /p>

  Что может привести к удвоению капитала с начала второго минута? /> < /ol>
Я использовал еще один API от Iex Cloud и доказал, что проблема не в API: < /p>
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from keras.layers import LSTM, Dense
import time
import requests

# Define the stock symbol and your IEX Cloud API key
symbol = 'AAPL'
api_key = 'sk_98e272a5046941a2a4f7c3554bbecce1'  # replace with your own API key

# Define the initial capital
initial_capital = 10000
capital = initial_capital

# Brokerage fee per stock
brokerage_fee_per_stock = 0.02

# Minimum brokerage fee
min_brokerage_fee = 18

# SEC tax rate
sec_tax_rate = 0.0000278

# Create a dataframe to store the capital and actions over time
capital_df = pd.DataFrame(columns=['time', 'capital', 'action', 'price'])
capital_df.loc[0] = {'time': pd.Timestamp.now(), 'capital': capital, 'action': 'Initial', 'price': 0}  # Initialize with initial capital

# Define lookback period
lookback = 60

# Define the LSTM model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(lookback, 1)))
model.add(LSTM(units=50))
model.add(Dense(1))

# Compile the LSTM model
model.compile(loss='mean_squared_error', optimizer='adam')

# Create the plot before the loop
plt.figure(figsize=(10, 5))
plt.title('Capital Over Time')
plt.xlabel('Time')
plt.ylabel('Capital')
plt.xticks(rotation=45)
plt.gca().xaxis.set_major_locator(plt.MaxNLocator(10))  # Show 10 ticks
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d %H:%M'))  # Format the time up to minutes

# Initialize a flag for the first iteration and the action
first_iteration = True
action = 'Initial'

while True:
start_time = time.time()  # Start the timer
print(f'Start time: {start_time}')  # Print the start time

# Fetch real-time data using IEX Cloud API
url = f'https://cloud.iexapis.com/stable/stock/{symbol}/quote?token={api_key}'
response = requests.get(url)
data = response.json()
current_price = float(data['latestPrice'])

# Preprocess the data
scaler = MinMaxScaler(feature_range=(0, 1))
price_data = np.array([current_price for _ in range(lookback)]).reshape(-1, 1)
scaled_data = scaler.fit_transform(price_data)

# Prepare inputs for the LSTM model
inputs = scaled_data.reshape(1, lookback, 1)

# Fit the LSTM model
model.fit(inputs, np.array([current_price]), epochs=1, batch_size=1, verbose=2)

# Make predictions using the trained LSTM model
predicted_price = model.predict(inputs)
predicted_price = scaler.inverse_transform(predicted_price)[0][0]

# Calculate the number of stocks to buy or sell
num_stocks = capital // current_price

# Calculate the total brokerage fee for buying and selling
total_brokerage_fee = max(brokerage_fee_per_stock * num_stocks, min_brokerage_fee) * 2

# Calculate the SEC tax
sec_tax = sec_tax_rate * predicted_price * num_stocks

# Update capital based on predicted price and record the action
if first_iteration:
first_iteration = False
elif predicted_price >  current_price:
capital += num_stocks * current_price - total_brokerage_fee - sec_tax
action = 'Buy'
else:
capital -= num_stocks * current_price + total_brokerage_fee + sec_tax
action = 'Sell'

print(f'Action: {action}, Capital: {capital}')  # Print the action and the updated capital

# Append the current capital and action to the dataframe
new_row = {'time': pd.Timestamp.now(), 'capital': capital, 'action': action, 'price': current_price}
capital_df = pd.concat([capital_df, pd.DataFrame([new_row])], ignore_index=True)

# Update the plot data without creating it all again
plt.plot(capital_df['time'], capital_df['capital'])
plt.gcf().autofmt_xdate()  # Autoformat the time label for better display
plt.draw()
plt.pause(0.01)  # Pause for the plot to update

print(f'Current earning: {capital - initial_capital}, Action: {action} at price: {current_price}')  # Print the current earning, action, and price

# Calculate the elapsed time and wait for the remaining time to complete 60 seconds
elapsed_time = time.time() - start_time
print(f'Elapsed time: {elapsed_time}')  # Print the elapsed time
time.sleep(max(60 - elapsed_time, 0))

Любая помощь будет высоко оценена.
Спасибо!

Подробнее здесь: https://stackoverflow.com/questions/785 ... -execution