基金净值与龙头股收盘价 数据的相关性分析:
diff_corr.py
# coding: utf-8
import os, sys
from datetime import datetime
import matplotlib.pyplot as plt
import pandas as pd
# 512070,易方达沪深300非银ETF基金
df = pd.read_csv('512070.csv', index_col='date')
df1 = df[['jz']]
print(df1.head())
# 600030,中信证券,为了与基金净值比较,收盘价/10
df = pd.read_csv('600030.csv', index_col='date')
df2 = df[['close']].apply(lambda x:x/10)
print(df2.head())
# pandas DataFrame 连接表
df3 = pd.merge(df1, df2, left_index=True, right_index=True, how='inner')
#df3 = df1.join(df2, how='inner')
print(df3.head())
df3.index = pd.to_datetime(df3.index)
# 每一年数据的相关性分析
print("2017Y:\n", df3[ df3.index.year==2017 ].corr()['jz'])
print("2018Y:\n", df3[ df3.index.year==2018 ].corr()['jz'])
print("2019Y:\n", df3[ df3.index.year==2019 ].corr()['jz'])
print("all:\n", df3.corr()['jz'])
运行 python diff_corr.py
df3.head() 数据格式
jz close
date
2017-04-11 1.6716 1.5546
2017-04-12 1.6761 1.5642
2017-04-13 1.6695 1.5565
计算结果:
2017Y: 0.946346
2018Y: 0.887191
2019Y: 0.855296
all: 0.849909
结论是:相关性是逐年减弱
奇怪,我直接看“基金净值与龙头股收盘价比较图”的直觉:相关性是逐年加强。
Why ? 哪里错了 ?基金净值与龙头股收盘价比较图