Cover Image

The cover of the book is inspired by the fast growing generative art community in R. Generative art refers to art that in whole or in part has been created with the use of an autonomous system. Instead of creating random dynamics we rely on what is core to the book: The evolution of financial markets. Each circle corresponds to one of the twelve Fama-French industry portfolios, whereas each bar represents the average annual return between 1927 and 2022. The bar color is determined by the standard deviation of returns for each industry. The few lines of code below replicate the entire figure.

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import pandas_datareader as pdr

from datetime import datetime
from matplotlib.colors import LinearSegmentedColormap

main_colors = ["#3B9AB2", "#78B7C5", "#EBCC2A", "#E1AF00", "#F21A00"]
colormap = LinearSegmentedColormap.from_list("custom_colormap", main_colors)

industries_ff_daily_raw = pdr.DataReader(
  name="12_Industry_Portfolios_daily",
  data_source="famafrench", 
  start="1927-01-01", 
  end="2022-12-31")[0]

industries_ff_daily = (industries_ff_daily_raw
  .divide(100)
  .reset_index(names="date")
  .assign(date=lambda x: pd.to_datetime(x["date"].astype(str)))
  .rename(str.lower, axis="columns")
)

industries_long = (industries_ff_daily
  .melt(id_vars="date", var_name="name", value_name="value")
)
                          
industries_order = sorted(industries_long["name"].unique())

data_plot = (industries_long
  .assign(year=industries_long["date"].dt.to_period("Y"))
  .groupby(["year", "name"])
  .aggregate(total=("value", "mean"),
             vola=("value", "std"))
  .reset_index()
  .assign(
    vola_ntile=lambda x: pd.qcut(x["vola"], 42, labels=False)
  )
)

dpi = 300
width = 2400/dpi
height = 1800/dpi
num_cols = 4
num_rows = int(len(industries_order)/num_cols)
fig, axs = plt.subplots(
  num_rows, num_cols,
  constrained_layout=True,
  subplot_kw={"projection": "polar"},
  figsize=(width, height),
  dpi=dpi
)
axs = axs.flatten()

for i in enumerate(industries_order):

    df = data_plot.copy().query(f'name == "{i[1]}"')
    min_value = df["total"].min()
    max_value = df["total"].max()
    std_value = df["total"].std()
    df["total"] = 2*(df["total"]-min_value)/(max_value-min_value)-1

    angles = np.linspace(0, 2*np.pi, len(df), endpoint=False)
    values = df["total"].values
    width = 2*np.pi/len(values)
    offset = np.pi/2

    ax = axs[i[0]]
    ax.set_theta_offset(offset)
    ax.set_ylim(-std_value*1400, 1)
    ax.set_frame_on(False)
    ax.xaxis.grid(False)
    ax.yaxis.grid(False)
    ax.set_xticks([])
    ax.set_yticks([])

    color_values = df["vola_ntile"].values
    normalize = plt.Normalize(min(color_values), max(color_values))
    colors = colormap(normalize(color_values))

    ax.bar(
      angles, values,
      width=width, color=colors, edgecolor="white", linewidth=0.2
    )

plt.tight_layout()
plt.subplots_adjust(wspace=-0.2, hspace=-0.1)
plt.gcf().savefig(
  "images/cover-image.png", dpi = 300, pad_inches=0, transparent=False
)