配对交易代码

配对交易（Pair Trading）代码的实现方式有很多种，下面提供其中一种实现方式的示例代码，仅供参考：

import numpy as np
import pandas as pd
import statsmodels.api as sm

# 读取数据
df = pd.read_csv('data.csv')
df.set_index('Date', inplace=True)

# 计算两只股票的对数收益率
df['Log_Return1'] = np.log(df['Stock1']/df['Stock1'].shift(1))
df['Log_Return2'] = np.log(df['Stock2']/df['Stock2'].shift(1))

# 计算两只股票的协整关系
X = df['Log_Return1']
Y = df['Log_Return2']
X = sm.add_constant(X)
result = sm.OLS(Y,X).fit()
beta = result.params[1]

# 计算配对交易信号
df['Spread'] = df['Stock2'] - beta * df['Stock1']
df['Spread_MA'] = df['Spread'].rolling(window=10).mean()
df['zScore'] = (df['Spread'] - df['Spread_MA']) / np.std(df['Spread'] - df['Spread_MA'])

df['Long_Entry'] = df['zScore'] < -1
df['Long_Exit'] = df['zScore'] > -0.5

df['Short_Entry'] = df['zScore'] > 1
df['Short_Exit'] = df['zScore'] < 0.5

# 计算交易信号
df['Position_1'] = np.where(df['Long_Entry'], 1, 0)
df['Position_1'] = np.where(df['Long_Exit'], 0, df['Position_1'])

df['Position_2'] = np.where(df['Short_Entry'], -beta, 0)
df['Position_2'] = np.where(df['Short_Exit'], 0, df['Position_2'])

df['Position'] = df['Position_1'] + df['Position_2']
df['Position'] = df['Position'].shift(1).fillna(0)

# 计算收益率
df['Strategy_Return'] = df['Position'] * (df['Log_Return1'] + beta * df['Log_Return2'])
df['Cumulative_Return'] = df['Strategy_Return'].cumsum()

# 绘制图形
import matplotlib.pyplot as plt
fig = plt.figure(figsize=(16,8))
ax1 = fig.add_subplot(111, ylabel='Cumulative Return')
df['Cumulative_Return'].plot(ax=ax1, color='blue', lw=2.)
plt.show()

需要注意的是，这只是一个简单的示例代码，实际的配对交易策略需要根据具体情况进行调整和优化。