Python-for-data-移动窗口函数

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

close_px_all = pd.read_csv("./examples/stock_px_2.csv"
                           ,parse_dates=True  # 解析时间
                           ,index_col=0)

close_px = close_px_all[["AAPL","MSFT","XOM"]]
close_px = close_px.resample("B").ffill()
close_px

close_px.AAPL.plot()

# 图形更加地平滑：根据250日滑动窗口分组，而不是直接分组
close_px.AAPL.rolling(250).mean().plot()

appl_std250 = close_px.AAPL.rolling(250,min_periods=10).std()
appl_std250[5:12]

2003-01-09         NaN
2003-01-10         NaN
2003-01-13         NaN
2003-01-14         NaN
2003-01-15    0.077496
2003-01-16    0.074760
2003-01-17    0.112368
Freq: B, Name: AAPL, dtype: float64

# 滚动窗口函数需要窗口中所有的值必须是非NaN值
# 如果存在缺失值，时间序列的起始位置的数据必须是少于窗口区间的
appl_std250.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x11ee210d0>

close_px.rolling(60).mean().plot(logy=True)

## rolling算子接收固定大小的时间偏置字符串
close_px.rolling("20D").mean()

# 调用扩展均值算子
expanding_mean = appl_std250.expanding().mean()
expanding_mean

2003-01-02          NaN
2003-01-03          NaN
2003-01-06          NaN
2003-01-07          NaN
2003-01-08          NaN
                ...
2011-10-10    18.521201
2011-10-11    18.524272
2011-10-12    18.527385
2011-10-13    18.530554
2011-10-14    18.533823
Freq: B, Name: AAPL, Length: 2292, dtype: float64

# 将苹果公司的股票价格的60日均线和span=60的EW移动均线进行比较
appl_px = close_px.AAPL["2006":"2007"]
ma60 = appl_px.rolling(30,min_periods=20).mean()

ewma60 = appl_px.ewm(span=30).mean()

ma60.plot(style="k--",label="Simple MA")

ewma60.plot(style="k-",label="EWMA")

close_px_all[:5]

spx_px = close_px_all["SPX"]  # 选择某列的数据
spx_rets = spx_px.pct_change()  # 计算该列的百分比变化

returns = close_px.pct_change()  # 计算整个数据的百分比变化

# 调用rolling后，corr聚合函数可以根据spx_rets计算滚动相关性

# 计算returns和spx_rets的相关性
corr = returns.AAPL.rolling(125,min_periods=100).corr(spx_rets)
corr.plot()

corr = returns.rolling(125,min_periods=100).corr(spx_rets)
corr.plot()

# 定值的百分位数:scipy.stats.percentileofscore
from scipy.stats import percentileofscore

score_at_2percent = lambda x: percentileofscore(x,0.02)
result = returns.AAPL.rolling(250).apply(score_at_2percent)

result.plot()