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

# 输入是一DataFrame，每一列是一支股票在每一日的价格
def find_cointegrated_pairs(dataframe):
    # 得到DataFrame长度
    n = dataframe.shape[1]
    # 初始化p值矩阵
    pvalue_matrix = np.ones((n, n))
    # 抽取列的名称
    keys = dataframe.keys()
    # 初始化强协整组
    pairs = []
    # 对于每一个i
    for i in range(n):
        # 对于大于i的j
        for j in range(i+1, n):
            # 获取相应的两只股票的价格Series
            stock1 = dataframe[keys[i]]
            stock2 = dataframe[keys[j]]
            # 分析它们的协整关系
            result = sm.tsa.stattools.coint(stock1, stock2)
            # 取出并记录p值
            pvalue = result[1]
            pvalue_matrix[i, j] = pvalue
            # 如果p值小于0.05
            if pvalue < 0.05:
                # 记录股票对和相应的p值
                pairs.append((keys[i], keys[j], pvalue))
    # 返回结果
    return pvalue_matrix, pairs

# 伊利、招行
stock_list = ['600887.XSHG','600036.XSHG','601988.XSHG']
prices_df = get_price(stock_list, start_date="2017-01-01", end_date="2018-01-01", frequency="daily", fields=["close"])["close"]
pvalues, pairs = find_cointegrated_pairs(prices_df)
sns.heatmap(1-pvalues, xticklabels=stock_list, yticklabels=stock_list, cmap='RdYlGn_r', mask = (pvalues == 1))
print pvalues

stock_df1 = prices_df["600887.XSHG"]
stock_df2 = prices_df["600036.XSHG"]
plot(stock_df1); plot(stock_df2)
plt.xlabel("Time"); plt.ylabel("Price")
plt.legend(["600887.XSHG", "600036.XSHG"],loc='best')

stock_df1 = prices_df["601988.XSHG"]
stock_df2 = prices_df["600036.XSHG"]
plot(stock_df1); plot(stock_df2)
plt.xlabel("Time"); plt.ylabel("Price")
plt.legend(["601988.XSHG", "600036.XSHG"],loc='best')