stock_betas.py

get_ipython().magic('matplotlib inline')

import datetime  

import numpy as np
import pandas as pd
import seaborn as sns
import pandas_datareader.data as web

sns.set()


# https://stackoverflow.com/questions/39501277/efficient-python-pandas-stock-beta-calculation-on-many-dataframes
def roll(df, w):
    # stack df.values w-times shifted once at each stack
    roll_array = np.dstack([df.values[i:i+w, :] for i in range(len(df.index) - w + 1)]).T
    # roll_array is now a 3-D array and can be read into
    # a pandas panel object
    panel = pd.Panel(roll_array, 
                     items=df.index[w-1:],
                     major_axis=df.columns,
                     minor_axis=pd.Index(range(w), name='roll'))
    # convert to dataframe and pivot + groupby
    # is now ready for any action normally performed
    # on a groupby object
    return panel.to_frame().unstack().T.groupby(level=0)


def beta(df, market=None):
    # If the market values are not passed,
    # I'll assume they are located in a column
    # named 'Market'.  If not, this will fail.
    if market is None:
        market = df['Market']
        df = df.drop('Market', axis=1)
    X = market.values.reshape(-1, 1)
    X = np.concatenate([np.ones_like(X), X], axis=1)
    b = np.linalg.pinv(X.T.dot(X)).dot(X.T).dot(df.values)
    return pd.Series(b[1], df.columns, name=df.index[-1])

tickers = ['DAL', 'AAL', 'UAL', 'LUV', 'ALK', 'JBLU']

start = datetime.datetime(1990, 1, 1)
end = datetime.date.today()
data = web.DataReader(['0p00001g7j'] + tickers, 'morningstar', start, end)

close = data.Close.unstack().T
close.columns = ['Market'] + tickers
monthly = close.resample('1M').last()
monthly = monthly[['Market', 'AAL', 'DAL']]

# calculate beta of 36 months years
betas = roll(monthly.pct_change().dropna(), w=36).apply(beta)
# clip beta at 2
betas.clip(0, 2).plot(figsize=(12, 8), title='Beta of major airlines')