{"id":1152128,"date":"2025-01-13T17:21:56","date_gmt":"2025-01-13T09:21:56","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1152128.html"},"modified":"2025-01-13T17:21:59","modified_gmt":"2025-01-13T09:21:59","slug":"%e5%a6%82%e4%bd%95%e5%88%a9%e7%94%a8python%e8%af%ad%e8%a8%80%e7%82%92%e8%82%a1","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1152128.html","title":{"rendered":"\u5982\u4f55\u5229\u7528python\u8bed\u8a00\u7092\u80a1"},"content":{"rendered":"

\"\u5982\u4f55\u5229\u7528python\u8bed\u8a00\u7092\u80a1\"<\/p>\n

\u5229\u7528Python\u8bed\u8a00\u7092\u80a1\u7684\u5173\u952e\u70b9\u5305\u62ec\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406\u3001\u6280\u672f\u5206\u6790\u3001\u673a\u5668\u5b66\u4e60<\/a>\u6a21\u578b\u3001\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316<\/strong>\u3002\u5176\u4e2d\uff0c\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406\u662f\u6700\u91cd\u8981\u7684\uff0c\u56e0\u4e3a\u51c6\u786e\u548c\u53ca\u65f6\u7684\u6570\u636e\u662f\u6240\u6709\u5206\u6790\u548c\u51b3\u7b56\u7684\u57fa\u7840\u3002\u901a\u8fc7API\u63a5\u53e3\u3001\u7f51\u7edc\u722c\u866b\u7b49\u65b9\u5f0f\u83b7\u53d6\u5b9e\u65f6\u548c\u5386\u53f2\u80a1\u7968\u6570\u636e\uff0c\u7136\u540e\u8fdb\u884c\u6e05\u6d17\u548c\u5904\u7406\uff0c\u4e3a\u540e\u7eed\u7684\u6280\u672f\u5206\u6790\u548c\u673a\u5668\u5b66\u4e60\u6a21\u578b\u63d0\u4f9b\u9ad8\u8d28\u91cf\u7684\u6570\u636e\u652f\u6301\u3002<\/p>\n<\/p>\n

\n

\u4e00\u3001\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406<\/h2>\n<\/p>\n

\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406\u662f\u80a1\u7968\u4ea4\u6613\u5206\u6790\u7684\u7b2c\u4e00\u6b65\uff0cPython\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u5f0f\u6765\u83b7\u53d6\u548c\u5904\u7406\u80a1\u7968\u6570\u636e\u3002\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528API\u63a5\u53e3\u3001\u7f51\u7edc\u722c\u866b\u7b49\u3002<\/p>\n<\/p>\n

1. API\u63a5\u53e3\u83b7\u53d6\u6570\u636e<\/h3>\n<\/p>\n

\u8bb8\u591a\u91d1\u878d\u6570\u636e\u670d\u52a1\u5546\u63d0\u4f9bAPI\u63a5\u53e3\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u83b7\u53d6\u80a1\u7968\u6570\u636e\u3002\u4f8b\u5982\uff0cYahoo Finance\u3001Alpha Vantage\u3001IEX Cloud\u7b49\u3002\u4ee5Yahoo Finance\u4e3a\u4f8b\uff0c\u53ef\u4ee5\u4f7f\u7528yfinance<\/code>\u5e93\u6765\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n

import yfinance as yf<\/p>\n
\u83b7\u53d6\u82f9\u679c\u516c\u53f8\u7684\u5386\u53f2\u6570\u636e<\/strong><\/h2>\n
ticker = yf.Ticker("AAPL")<\/p>\n
data = ticker.history(period="1y")<\/p>\n
print(data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7f51\u7edc\u722c\u866b<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u4e00\u4e9b\u6ca1\u6709API\u63a5\u53e3\u7684\u6570\u636e\u6765\u6e90\uff0c\u53ef\u4ee5\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6765\u83b7\u53d6\u6570\u636e\u3002\u5e38\u7528\u7684\u5e93\u6709BeautifulSoup<\/code>\u548cSelenium<\/code>\u3002\u4f8b\u5982\uff0c\u4f7f\u7528BeautifulSoup<\/code>\u4ece\u67d0\u4e2a\u8d22\u7ecf\u7f51\u7ad9\u83b7\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
url = 'https:\/\/finance.yahoo.com\/quote\/AAPL\/history'<\/p>\n
response = requests.get(url)<\/p>\n
soup = BeautifulSoup(response.text, 'html.parser')<\/p>\n
\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u83b7\u53d6\u80a1\u7968\u6570\u636e<\/strong><\/h2>\n
\u5177\u4f53\u89e3\u6790\u65b9\u5f0f\u6839\u636e\u7f51\u9875\u7ed3\u6784\u800c\u5b9a<\/strong><\/h2>\n
<\/code><\/pre>\n<\/p>\n
3. \u6570\u636e\u6e05\u6d17\u4e0e\u5904\u7406<\/h3>\n<\/p>\n
\u83b7\u53d6\u6570\u636e\u540e\uff0c\u901a\u5e38\u9700\u8981\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u4e0e\u5904\u7406\u3002\u5305\u62ec\u5904\u7406\u7f3a\u5931\u503c\u3001\u6570\u636e\u683c\u5f0f\u8f6c\u6362\u7b49\u3002\u4f7f\u7528pandas<\/code>\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884c\u8fd9\u4e9b\u64cd\u4f5c\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u5904\u7406\u7f3a\u5931\u503c<\/strong><\/h2>\n
data = data.dropna()<\/p>\n
\u6570\u636e\u683c\u5f0f\u8f6c\u6362<\/strong><\/h2>\n
data['Date'] = pd.to_datetime(data['Date'])<\/p>\n
data.set_index('Date', inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u6280\u672f\u5206\u6790<\/h2>\n<\/p>\n
\u6280\u672f\u5206\u6790\u662f\u901a\u8fc7\u7814\u7a76\u80a1\u7968\u4ef7\u683c\u548c\u4ea4\u6613\u91cf\u7684\u5386\u53f2\u6570\u636e\u6765\u9884\u6d4b\u672a\u6765\u4ef7\u683c\u8d70\u52bf\u3002Python\u4e2d\u6709\u8bb8\u591a\u5e93\u53ef\u4ee5\u5e2e\u52a9\u8fdb\u884c\u6280\u672f\u5206\u6790\uff0c\u4f8b\u5982TA-Lib<\/code>\u3001pandas-ta<\/code>\u7b49\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528TA-Lib\u8fdb\u884c\u6280\u672f\u5206\u6790<\/h3>\n<\/p>\n
TA-Lib<\/code>\u662f\u4e00\u4e2a\u5e38\u7528\u7684\u6280\u672f\u5206\u6790\u5e93\uff0c\u63d0\u4f9b\u4e86\u5927\u91cf\u7684\u6280\u672f\u6307\u6807\uff0c\u4f8b\u5982\u79fb\u52a8\u5e73\u5747\u7ebf\uff08MA\uff09\u3001\u76f8\u5bf9\u5f3a\u5f31\u6307\u6570\uff08RSI\uff09\u7b49\u3002<\/p>\n<\/p>\n
import talib<\/p>\n
\u8ba1\u7b97\u79fb\u52a8\u5e73\u5747\u7ebf<\/strong><\/h2>\n
data['MA20'] = talib.SMA(data['Close'], timeperiod=20)<\/p>\n
\u8ba1\u7b97\u76f8\u5bf9\u5f3a\u5f31\u6307\u6570<\/strong><\/h2>\n
data['RSI'] = talib.RSI(data['Close'], timeperiod=14)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528pandas-ta\u8fdb\u884c\u6280\u672f\u5206\u6790<\/h3>\n<\/p>\n
pandas-ta<\/code>\u662f\u53e6\u4e00\u4e2a\u6280\u672f\u5206\u6790\u5e93\uff0c\u4e0epandas<\/code>\u96c6\u6210\u826f\u597d\uff0c\u4f7f\u7528\u8d77\u6765\u975e\u5e38\u65b9\u4fbf\u3002<\/p>\n<\/p>\n
import pandas_ta as ta<\/p>\n
\u8ba1\u7b97\u79fb\u52a8\u5e73\u5747\u7ebf<\/strong><\/h2>\n
data['MA20'] = data['Close'].ta.sma(length=20)<\/p>\n
\u8ba1\u7b97\u76f8\u5bf9\u5f3a\u5f31\u6307\u6570<\/strong><\/h2>\n
data['RSI'] = data['Close'].ta.rsi(length=14)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u673a\u5668\u5b66\u4e60\u6a21\u578b<\/h2>\n<\/p>\n
\u9664\u4e86\u6280\u672f\u5206\u6790\uff0c\u673a\u5668\u5b66\u4e60\u6a21\u578b\u5728\u80a1\u7968\u9884\u6d4b\u4e2d\u4e5f\u6709\u5e7f\u6cdb\u5e94\u7528\u3002\u5e38\u89c1\u7684\u673a\u5668\u5b66\u4e60\u6a21\u578b\u5305\u62ec\u7ebf\u6027\u56de\u5f52\u3001\u51b3\u7b56\u6811\u3001\u968f\u673a\u68ee\u6797\u3001\u652f\u6301\u5411\u91cf\u673a\uff08SVM\uff09\u7b49\u3002<\/p>\n<\/p>\n
1. \u6570\u636e\u9884\u5904\u7406<\/h3>\n<\/p>\n
\u5728\u8bad\u7ec3\u673a\u5668\u5b66\u4e60\u6a21\u578b\u4e4b\u524d\uff0c\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u9884\u5904\u7406\uff0c\u5305\u62ec\u7279\u5f81\u5de5\u7a0b\u3001\u6570\u636e\u6807\u51c6\u5316\u7b49\u3002<\/p>\n<\/p>\n
from sklearn.model_selection import trAI<\/a>n_test_split<\/p>\n
from sklearn.preprocessing import StandardScaler<\/p>\n
\u7279\u5f81\u5de5\u7a0b<\/strong><\/h2>\n
features = data[['Open', 'High', 'Low', 'Close', 'Volume', 'MA20', 'RSI']]<\/p>\n
target = data['Close'].shift(-1)<\/p>\n
\u6570\u636e\u5206\u5272<\/strong><\/h2>\n
X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)<\/p>\n
\u6570\u636e\u6807\u51c6\u5316<\/strong><\/h2>\n
scaler = StandardScaler()<\/p>\n
X_train = scaler.fit_transform(X_train)<\/p>\n
X_test = scaler.transform(X_test)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bad\u7ec3\u673a\u5668\u5b66\u4e60\u6a21\u578b<\/h3>\n<\/p>\n
\u4ee5\u7ebf\u6027\u56de\u5f52\u4e3a\u4f8b\uff0c\u4f7f\u7528scikit-learn<\/code>\u5e93\u8bad\u7ec3\u6a21\u578b\u5e76\u8fdb\u884c\u9884\u6d4b\u3002<\/p>\n<\/p>\n
from sklearn.linear_model import LinearRegression<\/p>\n
from sklearn.metrics import mean_squared_error<\/p>\n
\u8bad\u7ec3\u7ebf\u6027\u56de\u5f52\u6a21\u578b<\/strong><\/h2>\n
model = LinearRegression()<\/p>\n
model.fit(X_train, y_train)<\/p>\n
\u8fdb\u884c\u9884\u6d4b<\/strong><\/h2>\n
predictions = model.predict(X_test)<\/p>\n
\u8bc4\u4f30\u6a21\u578b<\/strong><\/h2>\n
mse = mean_squared_error(y_test, predictions)<\/p>\n
print(f'Mean Squared Error: {mse}')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u6df1\u5ea6\u5b66\u4e60\u6a21\u578b<\/h3>\n<\/p>\n
\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u5728\u5904\u7406\u9ad8\u7ef4\u5ea6\u3001\u975e\u7ebf\u6027\u6570\u636e\u4e0a\u6709\u5f88\u5927\u4f18\u52bf\u3002\u53ef\u4ee5\u4f7f\u7528TensorFlow<\/code>\u6216PyTorch<\/code>\u6765\u6784\u5efa\u548c\u8bad\u7ec3\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u3002<\/p>\n<\/p>\n
import tensorflow as tf<\/p>\n
from tensorflow.keras.models import Sequential<\/p>\n
from tensorflow.keras.layers import Dense, LSTM<\/p>\n
\u6784\u5efaLSTM\u6a21\u578b<\/strong><\/h2>\n
model = Sequential()<\/p>\n
model.add(LSTM(50, return_sequences=True, input_shape=(X_train.shape[1], 1)))<\/p>\n
model.add(LSTM(50, return_sequences=False))<\/p>\n
model.add(Dense(25))<\/p>\n
model.add(Dense(1))<\/p>\n
\u7f16\u8bd1\u6a21\u578b<\/strong><\/h2>\n
model.compile(optimizer='adam', loss='mean_squared_error')<\/p>\n
\u8bad\u7ec3\u6a21\u578b<\/strong><\/h2>\n
model.fit(X_train, y_train, batch_size=1, epochs=1)<\/p>\n
\u8fdb\u884c\u9884\u6d4b<\/strong><\/h2>\n
predictions = model.predict(X_test)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316<\/h2>\n<\/p>\n
\u5728\u5b8c\u6210\u6570\u636e\u5206\u6790\u548c\u6a21\u578b\u8bad\u7ec3\u540e\uff0c\u53ef\u4ee5\u5c06\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316\uff0c\u4ee5\u4fbf\u5b9e\u65f6\u8fdb\u884c\u4ea4\u6613\u3002Python\u63d0\u4f9b\u4e86\u8bb8\u591a\u5e93\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\uff0c\u4f8b\u5982ccxt<\/code>\u3001alpaca-trade-api<\/code>\u7b49\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528ccxt\u8fdb\u884c\u4ea4\u6613<\/h3>\n<\/p>\n
ccxt<\/code>\u662f\u4e00\u4e2a\u652f\u6301\u591a\u4e2a\u4ea4\u6613\u6240\u7684\u52a0\u5bc6\u8d27\u5e01\u4ea4\u6613\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884c\u5b9e\u65f6\u4ea4\u6613\u3002<\/p>\n<\/p>\n
import ccxt<\/p>\n
\u914d\u7f6e\u4ea4\u6613\u6240\u548cAPI\u5bc6\u94a5<\/strong><\/h2>\n
exchange = ccxt.binance({<\/p>\n
    'apiKey': 'YOUR_API_KEY',<\/p>\n
    'secret': 'YOUR_API_SECRET',<\/p>\n
})<\/p>\n
\u83b7\u53d6\u8d26\u6237\u4f59\u989d<\/strong><\/h2>\n
balance = exchange.fetch_balance()<\/p>\n
print(balance)<\/p>\n
\u4e0b\u5355\u4e70\u5165<\/strong><\/h2>\n
order = exchange.create_market_buy_order('BTC\/USDT', 0.01)<\/p>\n
print(order)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528alpaca-trade-api\u8fdb\u884c\u4ea4\u6613<\/h3>\n<\/p>\n
alpaca-trade-api<\/code>\u662f\u4e00\u4e2a\u4e13\u95e8\u7528\u4e8e\u80a1\u7968\u4ea4\u6613\u7684\u5e93\uff0c\u652f\u6301\u5b9e\u65f6\u4ea4\u6613\u548c\u7b56\u7565\u81ea\u52a8\u5316\u3002<\/p>\n<\/p>\n
import alpaca_trade_api as tradeapi<\/p>\n
\u914d\u7f6eAPI\u5bc6\u94a5<\/strong><\/h2>\n
api = tradeapi.REST('APCA-API-KEY-ID', 'APCA-API-SECRET-KEY', base_url='https:\/\/paper-api.alpaca.markets')<\/p>\n
\u83b7\u53d6\u8d26\u6237\u4fe1\u606f<\/strong><\/h2>\n
account = api.get_account()<\/p>\n
print(account)<\/p>\n
\u4e0b\u5355\u4e70\u5165<\/strong><\/h2>\n
order = api.submit_order(<\/p>\n
    symbol='AAPL',<\/p>\n
    qty=1,<\/p>\n
    side='buy',<\/p>\n
    type='market',<\/p>\n
    time_in_force='gtc',<\/p>\n
)<\/p>\n
print(order)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u81ea\u52a8\u5316\u4ea4\u6613\u7b56\u7565<\/h3>\n<\/p>\n
\u5c06\u6570\u636e\u83b7\u53d6\u3001\u5206\u6790\u3001\u6a21\u578b\u9884\u6d4b\u548c\u4ea4\u6613\u6267\u884c\u6574\u5408\u5728\u4e00\u8d77\uff0c\u5b9e\u73b0\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316\u3002\u4f8b\u5982\uff0c\u6bcf\u5929\u5b9a\u65f6\u83b7\u53d6\u6570\u636e\u3001\u8fdb\u884c\u9884\u6d4b\u5e76\u4e0b\u5355\u4ea4\u6613\u3002<\/p>\n<\/p>\n
import schedule<\/p>\n
import time<\/p>\n
def execute_trade():<\/p>\n
    # \u83b7\u53d6\u6570\u636e<\/p>\n
    data = get_stock_data('AAPL')<\/p>\n
    # \u6570\u636e\u9884\u5904\u7406<\/p>\n
    features, target = preprocess_data(data)<\/p>\n
    # \u8fdb\u884c\u9884\u6d4b<\/p>\n
    prediction = model.predict(features)<\/p>\n
    # \u6839\u636e\u9884\u6d4b\u7ed3\u679c\u4e0b\u5355\u4ea4\u6613<\/p>\n
    if prediction > data['Close'].iloc[-1]:<\/p>\n
        order = api.submit_order(<\/p>\n
            symbol='AAPL',<\/p>\n
            qty=1,<\/p>\n
            side='buy',<\/p>\n
            type='market',<\/p>\n
            time_in_force='gtc',<\/p>\n
        )<\/p>\n
        print(order)<\/p>\n
\u5b9a\u65f6\u6267\u884c\u4ea4\u6613\u7b56\u7565<\/strong><\/h2>\n
schedule.every().day.at("09:30").do(execute_trade)<\/p>\n
while True:<\/p>\n
    schedule.run_pending()<\/p>\n
    time.sleep(1)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u98ce\u9669\u7ba1\u7406\u4e0e\u56de\u6d4b<\/h2>\n<\/p>\n
\u5728\u5b9e\u9645\u4ea4\u6613\u4e2d\uff0c\u98ce\u9669\u7ba1\u7406\u548c\u7b56\u7565\u56de\u6d4b\u662f\u975e\u5e38\u91cd\u8981\u7684\u73af\u8282\u3002\u901a\u8fc7\u56de\u6d4b\uff0c\u53ef\u4ee5\u8bc4\u4f30\u7b56\u7565\u7684\u5386\u53f2\u8868\u73b0\uff0c\u53d1\u73b0\u6f5c\u5728\u95ee\u9898\uff0c\u4f18\u5316\u7b56\u7565\u3002\u540c\u65f6\uff0c\u98ce\u9669\u7ba1\u7406\u53ef\u4ee5\u5e2e\u52a9\u63a7\u5236\u635f\u5931\uff0c\u4fdd\u62a4\u8d44\u91d1\u5b89\u5168\u3002<\/p>\n<\/p>\n
1. \u7b56\u7565\u56de\u6d4b<\/h3>\n<\/p>\n
\u4f7f\u7528backtrader<\/code>\u5e93\u8fdb\u884c\u7b56\u7565\u56de\u6d4b\uff0c\u53ef\u4ee5\u6a21\u62df\u7b56\u7565\u5728\u5386\u53f2\u6570\u636e\u4e0a\u7684\u8868\u73b0\uff0c\u8bc4\u4f30\u5176\u6536\u76ca\u548c\u98ce\u9669\u3002<\/p>\n<\/p>\n
import backtrader as bt<\/p>\n
class TestStrategy(bt.Strategy):<\/p>\n
    def __init__(self):<\/p>\n
        self.sma = bt.indicators.SimpleMovingAverage(self.data.close, period=20)<\/p>\n
    def next(self):<\/p>\n
        if self.data.close > self.sma:<\/p>\n
            self.buy()<\/p>\n
        elif self.data.close < self.sma:<\/p>\n
            self.sell()<\/p>\n
\u521b\u5efa\u56de\u6d4b\u5b9e\u4f8b<\/strong><\/h2>\n
cerebro = bt.Cerebro()<\/p>\n
cerebro.addstrategy(TestStrategy)<\/p>\n
\u52a0\u8f7d\u6570\u636e<\/strong><\/h2>\n
data = bt.feeds.PandasData(dataname=data)<\/p>\n
cerebro.adddata(data)<\/p>\n
\u8fd0\u884c\u56de\u6d4b<\/strong><\/h2>\n
cerebro.run()<\/p>\n
cerebro.plot()<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u98ce\u9669\u7ba1\u7406<\/h3>\n<\/p>\n
\u98ce\u9669\u7ba1\u7406\u7b56\u7565\u5305\u62ec\u8bbe\u7f6e\u6b62\u635f\u70b9\u3001\u4ed3\u4f4d\u7ba1\u7406\u7b49\u3002\u4f8b\u5982\uff0c\u8bbe\u7f6e\u4e00\u4e2a\u56fa\u5b9a\u7684\u6b62\u635f\u70b9\uff0c\u5f53\u4ef7\u683c\u4e0b\u8dcc\u8d85\u8fc7\u4e00\u5b9a\u5e45\u5ea6\u65f6\u81ea\u52a8\u5356\u51fa\u3002<\/p>\n<\/p>\n
class RiskManagementStrategy(bt.Strategy):<\/p>\n
    params = (<\/p>\n
        ('stop_loss', 0.05),  # \u6b62\u635f\u70b9<\/p>\n
    )<\/p>\n
    def __init__(self):<\/p>\n
        self.order = None<\/p>\n
    def next(self):<\/p>\n
        if self.order:<\/p>\n
            return<\/p>\n
        if self.data.close > self.data.close[-1]:<\/p>\n
            self.order = self.buy()<\/p>\n
        elif self.data.close < self.data.close[-1] * (1 - self.params.stop_loss):<\/p>\n
            self.order = self.sell()<\/p>\n
\u521b\u5efa\u56de\u6d4b\u5b9e\u4f8b<\/strong><\/h2>\n
cerebro = bt.Cerebro()<\/p>\n
cerebro.addstrategy(RiskManagementStrategy)<\/p>\n
\u52a0\u8f7d\u6570\u636e<\/strong><\/h2>\n
data = bt.feeds.PandasData(dataname=data)<\/p>\n
cerebro.adddata(data)<\/p>\n
\u8fd0\u884c\u56de\u6d4b<\/strong><\/h2>\n
cerebro.run()<\/p>\n
cerebro.plot()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h2>\n<\/p>\n
\u5229\u7528Python\u8bed\u8a00\u7092\u80a1\u6d89\u53ca\u591a\u4e2a\u65b9\u9762\uff0c\u5305\u62ec\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406\u3001\u6280\u672f\u5206\u6790\u3001\u673a\u5668\u5b66\u4e60\u6a21\u578b\u3001\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316\u3001\u98ce\u9669\u7ba1\u7406\u4e0e\u56de\u6d4b\u7b49\u3002\u901a\u8fc7\u5408\u7406\u5730\u5e94\u7528\u8fd9\u4e9b\u6280\u672f\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6295\u8d44\u8005\u505a\u51fa\u66f4\u4e3a\u79d1\u5b66\u3001\u7406\u6027\u7684\u6295\u8d44\u51b3\u7b56\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u867d\u7136\u6280\u672f\u548c\u6a21\u578b\u53ef\u4ee5\u63d0\u4f9b\u4e00\u5b9a\u7684\u6307\u5bfc\uff0c\u4f46\u5e02\u573a\u5177\u6709\u4e0d\u786e\u5b9a\u6027\uff0c\u4efb\u4f55\u7b56\u7565\u90fd\u4e0d\u80fd\u4fdd\u8bc1\u767e\u5206\u4e4b\u767e\u7684\u6210\u529f\u3002\u56e0\u6b64\uff0c\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\uff0c\u6295\u8d44\u8005\u5e94\u7ed3\u5408\u81ea\u8eab\u7684\u7ecf\u9a8c\u548c\u98ce\u9669\u504f\u597d\uff0c\u8c28\u614e\u51b3\u7b56\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5f00\u59cb\u4f7f\u7528Python\u8fdb\u884c\u80a1\u7968\u4ea4\u6613\uff1f<\/strong>
\u8981\u5f00\u59cb\u4f7f\u7528Python\u8fdb\u884c\u80a1\u7968\u4ea4\u6613\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u76f8\u5173\u7684\u5e93\uff0c\u5982pandas\u3001numpy\u548cmatplotlib\u7b49\uff0c\u8fd9\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u4f60\u5904\u7406\u6570\u636e\u548c\u8fdb\u884c\u5206\u6790\u3002\u6b64\u5916\uff0c\u9009\u62e9\u4e00\u4e2a\u5408\u9002\u7684\u80a1\u7968\u5e02\u573a\u6570\u636e\u63a5\u53e3\u662f\u5173\u952e\uff0c\u4f8b\u5982Yahoo Finance\u6216Alpha Vantage\uff0c\u4ee5\u4fbf\u83b7\u53d6\u5b9e\u65f6\u7684\u80a1\u7968\u6570\u636e\u3002\u638c\u63e1\u57fa\u672c\u7684\u7f16\u7a0b\u6280\u80fd\u548c\u91d1\u878d\u77e5\u8bc6\u5c06\u5927\u5927\u63d0\u5347\u4f60\u7684\u4ea4\u6613\u7b56\u7565\u5f00\u53d1\u80fd\u529b\u3002<\/p>\n
Python\u53ef\u4ee5\u5e2e\u52a9\u6211\u5206\u6790\u54ea\u4e9b\u80a1\u7968\u6307\u6807\uff1f<\/strong>
\u4f7f\u7528Python\uff0c\u4f60\u53ef\u4ee5\u5206\u6790\u591a\u79cd\u80a1\u7968\u6307\u6807\uff0c\u5305\u62ec\u79fb\u52a8\u5e73\u5747\u7ebf\u3001\u76f8\u5bf9\u5f3a\u5f31\u6307\u6570\uff08RSI\uff09\u3001\u5e03\u6797\u5e26\u7b49\u3002\u8fd9\u4e9b\u6307\u6807\u80fd\u591f\u5e2e\u52a9\u4f60\u8bc6\u522b\u5e02\u573a\u8d8b\u52bf\u548c\u4e70\u5356\u673a\u4f1a\u3002\u6b64\u5916\uff0c\u5229\u7528Python\u7684\u673a\u5668\u5b66\u4e60\u5e93\uff0c\u5982scikit-learn\uff0c\u4f60\u8fd8\u53ef\u4ee5\u6784\u5efa\u9884\u6d4b\u6a21\u578b\uff0c\u6839\u636e\u5386\u53f2\u6570\u636e\u9884\u6d4b\u672a\u6765\u7684\u80a1\u7968\u4ef7\u683c\u6ce2\u52a8\u3002<\/p>\n
\u5982\u4f55\u5229\u7528Python\u5b9e\u73b0\u81ea\u52a8\u5316\u4ea4\u6613\uff1f<\/strong>
\u81ea\u52a8\u5316\u4ea4\u6613\u53ef\u4ee5\u901a\u8fc7\u7f16\u5199\u7a0b\u5e8f\u6765\u5b9e\u73b0\uff0c\u6839\u636e\u8bbe\u5b9a\u7684\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u4e70\u5165\u6216\u5356\u51fa\u80a1\u7968\u3002\u4f7f\u7528\u50cfQuantConnect\u6216Backtrader\u8fd9\u6837\u7684\u6846\u67b6\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u56de\u6d4b\u4f60\u7684\u7b56\u7565\u5e76\u5728\u771f\u5b9e\u5e02\u573a\u4e2d\u6267\u884c\u3002\u786e\u4fdd\u5728\u7f16\u5199\u81ea\u52a8\u5316\u4ea4\u6613\u4ee3\u7801\u65f6\uff0c\u8003\u8651\u98ce\u9669\u7ba1\u7406\u7b56\u7565\u548c\u6b62\u635f\u673a\u5236\uff0c\u4ee5\u964d\u4f4e\u6f5c\u5728\u7684\u6295\u8d44\u98ce\u9669\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5229\u7528Python\u8bed\u8a00\u7092\u80a1\u7684\u5173\u952e\u70b9\u5305\u62ec\u6570\u636e\u83b7\u53d6\u4e0e\u5904\u7406\u3001\u6280\u672f\u5206\u6790\u3001\u673a\u5668\u5b66\u4e60\u6a21\u578b\u3001\u4ea4\u6613\u7b56\u7565\u81ea\u52a8\u5316\u3002\u5176\u4e2d\uff0c\u6570\u636e\u83b7\u53d6\u4e0e\u5904 […]","protected":false},"author":3,"featured_media":1152134,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1152128"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1152128"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1152128\/revisions"}],"predecessor-version":[{"id":1152138,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1152128\/revisions\/1152138"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1152134"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1152128"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1152128"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1152128"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}