algorithm - Efficient Python Pandas Stock Beta Calculation on Many Dataframes

Question

I have many (4000+) CSVs of stock data (Date, Open, High, Low, Close) which I import into individual Pandas dataframes to perform analysis. I am new to python and want to calculate a rolling 12month beta for each stock, I found a post to calculate rolling beta (Python pandas calculate rolling stock beta using rolling apply to groupby object in vectorized fashion) however when used in my code below takes over 2.5 hours! Considering I can run the exact same calculations in SQL tables in under 3 minutes this is too slow.

How can I improve the performance of my below code to match that of SQL? I understand Pandas/python has that capability. My current method loops over each row which I know slows performance but I am unaware of any aggregate way to perform a rolling window beta calculation on a dataframe.

Note: the first 2 steps of loading the CSVs into individual dataframes and calculating daily returns only takes ~20seconds. All my CSV dataframes are stored in the dictionary called 'FilesLoaded' with names such as 'XAO'.

Your help would be much appreciated! Thank you :)

import pandas as pd, numpy as np
import datetime
import ntpath
pd.set_option('precision',10)  #Set the Decimal Point precision to DISPLAY
start_time=datetime.datetime.now()

MarketIndex = 'XAO'
period = 250
MinBetaPeriod = period
# ***********************************************************************************************
# CALC RETURNS 
# ***********************************************************************************************
for File in FilesLoaded:
    FilesLoaded[File]['Return'] = FilesLoaded[File]['Close'].pct_change()
# ***********************************************************************************************
# CALC BETA
# ***********************************************************************************************
def calc_beta(df):
    np_array = df.values
    m = np_array[:,0] # market returns are column zero from numpy array
    s = np_array[:,1] # stock returns are column one from numpy array
    covariance = np.cov(s,m) # Calculate covariance between stock and market
    beta = covariance[0,1]/covariance[1,1]
    return beta

#Build Custom "Rolling_Apply" function
def rolling_apply(df, period, func, min_periods=None):
    if min_periods is None:
        min_periods = period
    result = pd.Series(np.nan, index=df.index)
    for i in range(1, len(df)+1):
        sub_df = df.iloc[max(i-period, 0):i,:]
        if len(sub_df) >= min_periods:  
            idx = sub_df.index[-1]
            result[idx] = func(sub_df)
    return result

#Create empty BETA dataframe with same index as RETURNS dataframe
df_join = pd.DataFrame(index=FilesLoaded[MarketIndex].index)    
df_join['market'] = FilesLoaded[MarketIndex]['Return']
df_join['stock'] = np.nan

for File in FilesLoaded:
    df_join['stock'].update(FilesLoaded[File]['Return'])
    df_join  = df_join.replace(np.inf, np.nan) #get rid of infinite values "inf" (SQL won't take "Inf")
    df_join  = df_join.replace(-np.inf, np.nan)#get rid of infinite values "inf" (SQL won't take "Inf")
    df_join  = df_join.fillna(0) #get rid of the NaNs in the return data
    FilesLoaded[File]['Beta'] = rolling_apply(df_join[['market','stock']], period, calc_beta, min_periods = MinBetaPeriod)

# ***********************************************************************************************
# CLEAN-UP
# ***********************************************************************************************
print('Run-time: {0}'.format(datetime.datetime.now() - start_time))

Answer 1

Generate Random Stock Data
20 Years of Monthly Data for 4,000 Stocks

dates = pd.date_range('1995-12-31', periods=480, freq='M', name='Date')
stoks = pd.Index(['s{:04d}'.format(i) for i in range(4000)])
df = pd.DataFrame(np.random.rand(480, 4000), dates, stoks)

---

df.iloc[:5, :5]

---

Roll Function
Returns groupby object ready to apply custom functions
See Source

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)

---

Beta Function
Use closed form solution of OLS regression
Assume column 0 is market
See Source

def beta(df):
    # first column is the market
    X = df.values[:, [0]]
    # prepend a column of ones for the intercept
    X = np.concatenate([np.ones_like(X), X], axis=1)
    # matrix algebra
    b = np.linalg.pinv(X.T.dot(X)).dot(X.T).dot(df.values[:, 1:])
    return pd.Series(b[1], df.columns[1:], name='Beta')

---

Demonstration

rdf = roll(df, 12)
betas = rdf.apply(beta)

---

Timing

---

Validation
Compare calculations with OP

def calc_beta(df):
    np_array = df.values
    m = np_array[:,0] # market returns are column zero from numpy array
    s = np_array[:,1] # stock returns are column one from numpy array
    covariance = np.cov(s,m) # Calculate covariance between stock and market
    beta = covariance[0,1]/covariance[1,1]
    return beta

---

print(calc_beta(df.iloc[:12, :2]))

-0.311757542437

---

print(beta(df.iloc[:12, :2]))

s0001   -0.311758
Name: Beta, dtype: float64

---

Note the first cell
Is the same value as validated calculations above

betas = rdf.apply(beta)
betas.iloc[:5, :5]

---

Response to comment
Full working example with simulated multiple dataframes

num_sec_dfs = 4000

cols = ['Open', 'High', 'Low', 'Close']
dfs = {'s{:04d}'.format(i): pd.DataFrame(np.random.rand(480, 4), dates, cols) for i in range(num_sec_dfs)}

market = pd.Series(np.random.rand(480), dates, name='Market')

df = pd.concat([market] + [dfs[k].Close.rename(k) for k in dfs.keys()], axis=1).sort_index(1)

betas = roll(df.pct_change().dropna(), 12).apply(beta)

for c, col in betas.iteritems():
    dfs[c]['Beta'] = col

dfs['s0001'].head(20)