portfolio.py

# Databricks notebook source
import numpy as np
import pandas as pd
import yfinance as yf
import warnings

warnings.filterwarnings("ignore")
#pd.options.display.float_format = '{:.4%}'.format

# Date range
start = '2007-01-01'
end = '2021-12-31'

# Tickers of assets
assets = ['XLB', 'XLV', 'XLC', 'XLK', 'XLF', 'XLP', 'XLI', 'XLU',
          'XLY', 'XLRE', 'XLE'
         ]
assets.sort()

# Downloading data
data = yf.download(assets, start = start, end = end)
data = data.loc[:,('Adj Close', slice(None))]
data.columns = assets

# COMMAND ----------

# Calculating returns

Y = data[assets].pct_change().dropna()

display(Y.head())

# COMMAND ----------

import riskfolio as rp

# Plotting Assets Clusters

ax = rp.plot_dendrogram(returns=Y,
                        codependence='pearson',
                        linkage='single',
                        k=None,
                        max_k=10,
                        leaf_order=True,
                        ax=None)

# COMMAND ----------

# Building the portfolio object
port = rp.HCPortfolio(returns=Y)

# Estimate optimal portfolio:

model='HRP' # Could be HRP or HERC
codependence = 'pearson' # Correlation matrix used to group assets in clusters
rm = 'MV' # Risk measure used, this time will be variance
rf = 0 # Risk free rate
linkage = 'single' # Linkage method used to build clusters
max_k = 10 # Max number of clusters used in two difference gap statistic, only for HERC model
leaf_order = True # Consider optimal order of leafs in dendrogram

w = port.optimization(model=model,
                      codependence=codependence,
                      rm=rm,
                      rf=rf,
                      linkage=linkage,
                      max_k=max_k,
                      leaf_order=leaf_order)

display(w.T)

# COMMAND ----------

# Plotting the composition of the portfolio

ax = rp.plot_pie(w=w,
                 title='HRP Naive Risk Parity',
                 others=0.05,
                 nrow=25,
                 cmap="tab20",
                 height=8,
                 width=10,
                 ax=None)

# COMMAND ----------

# Plotting the risk contribution per asset

mu = Y.mean()
cov = Y.cov() # Covariance matrix
returns = Y # Returns of the assets

ax = rp.plot_risk_con(w=w,
                      cov=cov,
                      returns=returns,
                      rm=rm,
                      rf=0,
                      alpha=0.05,
                      color="tab:blue",
                      height=6,
                      width=10,
                      t_factor=252,
                      ax=None)

# COMMAND ----------

# Risk Measures available:
#
# 'vol': Standard Deviation.
# 'MV': Variance.
# 'MAD': Mean Absolute Deviation.
# 'GMD': Gini Mean Difference.
# 'MSV': Semi Standard Deviation.
# 'FLPM': First Lower Partial Moment (Omega Ratio).
# 'SLPM': Second Lower Partial Moment (Sortino Ratio).
# 'VaR': Conditional Value at Risk.
# 'CVaR': Conditional Value at Risk.
# 'TG': Tail Gini.
# 'EVaR': Entropic Value at Risk.
# 'WR': Worst Realization (Minimax).
# 'RG': Range of returns.
# 'CVRG': CVaR Range of returns.
# 'TGRG': Tail Gini Range of returns.
# 'MDD': Maximum Drawdown of uncompounded cumulative returns (Calmar Ratio).
# 'ADD': Average Drawdown of uncompounded cumulative returns.
# 'DaR': Drawdown at Risk of uncompounded cumulative returns.
# 'CDaR': Conditional Drawdown at Risk of uncompounded cumulative returns.
# 'EDaR': Entropic Drawdown at Risk of uncompounded cumulative returns.
# 'UCI': Ulcer Index of uncompounded cumulative returns.
# 'MDD_Rel': Maximum Drawdown of compounded cumulative returns (Calmar Ratio).
# 'ADD_Rel': Average Drawdown of compounded cumulative returns.
# 'DaR_Rel': Drawdown at Risk of compounded cumulative returns.
# 'CDaR_Rel': Conditional Drawdown at Risk of compounded cumulative returns.
# 'EDaR_Rel': Entropic Drawdown at Risk of compounded cumulative returns.
# 'UCI_Rel': Ulcer Index of compounded cumulative returns.

rms = ['vol', 'MV', 'MAD', 'GMD', 'MSV', 'FLPM', 'SLPM', 'VaR',
       'CVaR', 'TG', 'EVaR', 'WR', 'RG', 'CVRG', 'TGRG', 'MDD', 
       'ADD', 'DaR', 'CDaR', 'EDaR', 'UCI', 'MDD_Rel',
       'ADD_Rel', 'DaR_Rel', 'CDaR_Rel', 'EDaR_Rel', 'UCI_Rel']

w_s = pd.DataFrame([])

for i in rms:
    w = port.optimization(model=model,
                          codependence=codependence,
                          rm=i,
                          rf=rf,
                          linkage=linkage,
                          max_k=max_k,
                          leaf_order=leaf_order)

    w_s = pd.concat([w_s, w], axis=1)
    
w_s.columns = rms

# COMMAND ----------

w_s.style.format("{:.2%}").background_gradient(cmap='YlGn')

# COMMAND ----------

import matplotlib.pyplot as plt

# Plotting a comparison of assets weights for each portfolio

fig = plt.gcf()
fig.set_figwidth(16)
fig.set_figheight(8)
ax = fig.subplots(nrows=1, ncols=1)

w_s.plot(kind='bar', width=0.8, ax=ax)