import pandas as pd
hs300file = "/data/hs300.txt"
hs300etffile = "/hs300etf.txt"

hs300df = pd.read_csv(hs300file)
hs300etfdf = pd.read_csv(hs300etffile)

# 筛选列
hs300df = hs300df[["time","close"]]
hs300etfdf = hs300etfdf[["time","close"]]

# 重命名列
hs300df.columns=["time","hs300"]
hs300etfdf.columns=["time","hs300etf"]
# 根据时间字段 合并 join 
df = pd.merge(hs300df,hs300etfdf,how='inner',on='time')

# 除以第一个值  方便进行对比 
df["hs300_1"] = df["hs300"] / df["hs300"][0]
# 除以第一个值  方便进行对比
df["hs300etf_1"] = df["hs300etf"] / df["hs300etf"][0]

# 偏差值
df["dif"] = df["hs300_1"] - df["hs300etf_1"]
# 画图
df[["hs300_1","hs300etf_1"]].plot()

df[["dif"]].plot()

# 根据时间过滤 
df[df["time"]>="2022-08-25"][["hs300_1","hs300etf_1"]].plot()
df[df["time"]>="2022-08-25"][["dif"]].plot()

df.head()

df.tail()