def _naive_risk(self, returns, cov, rm="MV", rf=0):
assets = returns.columns.tolist()
n = len(assets)
if rm == "equal":
weight = np.ones((n, 1)) * 1 / n
else:
inv_risk = np.zeros((n, 1))
for i in assets:
k = assets.index(i)
w = np.zeros((n, 1))
w[k, 0] = 1
w = pd.DataFrame(w, columns=["weights"], index=assets)
if rm == "vol":
risk = rk.Sharpe_Risk(w,
cov=cov,
returns=returns,
rm="MV",
rf=rf,
alpha=self.alpha)
else:
risk = rk.Sharpe_Risk(w,
cov=cov,
returns=returns,
rm=rm,
rf=rf,
alpha=self.alpha)
inv_risk[k, 0] = risk
if rm == "MV":
inv_risk = 1 / np.power(inv_risk, 2)
else:
inv_risk = 1 / inv_risk
weight = inv_risk * (1 / np.sum(inv_risk))
weight = weight.reshape(-1, 1)
return weight
def _hierarchical_recursive_bisection(self,
Z,
rm="MV",
rf=0,
linkage="ward",
model="HERC"):
# Transform linkage to tree and reverse order
root, nodes = hr.to_tree(Z, rd=True)
nodes = nodes[::-1]
weight = pd.Series(1, index=self.cov.index) # Set initial weights to 1
clusters_inds = hr.fcluster(Z, self.k, criterion="maxclust")
clusters = {
i: []
for i in range(min(clusters_inds),
max(clusters_inds) + 1)
}
for i, v in enumerate(clusters_inds):
clusters[v].append(i)
# Loop through k clusters
for i in nodes[:self.k - 1]:
if i.is_leaf() == False: # skip leaf-nodes
left = i.get_left().pre_order(
) # lambda i: i.id) # get left cluster
right = i.get_right().pre_order(
) # lambda i: i.id) # get right cluster
left_set = set(left)
right_set = set(right)
left_risk = 0
right_risk = 0
# Allocate weight to clusters
if rm == "equal":
w_1 = 0.5
else:
for j in clusters.keys():
if set(clusters[j]).issubset(left_set):
# Left cluster
left_cov = self.cov.iloc[clusters[j], clusters[j]]
left_returns = self.returns.iloc[:, clusters[j]]
left_weight = self._naive_risk(left_returns,
left_cov,
rm=rm,
rf=rf)
if rm == "vol":
left_risk_ = rk.Sharpe_Risk(
left_weight,
cov=left_cov,
returns=left_returns,
rm="MV",
rf=rf,
alpha=self.alpha,
)
else:
left_risk_ = rk.Sharpe_Risk(
left_weight,
cov=left_cov,
returns=left_returns,
rm=rm,
rf=rf,
alpha=self.alpha,
)
if rm == "MV":
left_risk_ = np.power(left_risk_, 2)
left_risk += left_risk_
if set(clusters[j]).issubset(right_set):
# Right cluster
right_cov = self.cov.iloc[clusters[j], clusters[j]]
right_returns = self.returns.iloc[:, clusters[j]]
right_weight = self._naive_risk(right_returns,
right_cov,
rm=rm,
rf=rf)
if rm == "vol":
right_risk_ = rk.Sharpe_Risk(
right_weight,
cov=right_cov,
returns=right_returns,
rm="MV",
rf=rf,
alpha=self.alpha,
)
else:
right_risk_ = rk.Sharpe_Risk(
right_weight,
cov=right_cov,
returns=right_returns,
rm=rm,
rf=rf,
alpha=self.alpha,
)
if rm == "MV":
right_risk_ = np.power(right_risk_, 2)
right_risk += right_risk_
w_1 = 1 - left_risk / (left_risk + right_risk)
weight[left] *= w_1 # weight 1
weight[right] *= 1 - w_1 # weight 2
# Get constituents of k clusters
clustered_assets = pd.Series(hr.cut_tree(Z,
n_clusters=self.k).flatten(),
index=self.cov.index)
# Multiply within-cluster weight with inter-cluster weight
for i in range(self.k):
cluster = clustered_assets.loc[clustered_assets == i]
cluster_cov = self.cov.loc[cluster.index, cluster.index]
cluster_returns = self.returns.loc[:, cluster.index]
if model == "HERC":
cluster_weights = pd.Series(
self._naive_risk(cluster_returns,
cluster_cov,
rm=rm,
rf=rf).flatten(),
index=cluster_cov.index,
)
elif model == "HERC2":
cluster_weights = pd.Series(
self._naive_risk(cluster_returns,
cluster_cov,
rm="equal",
rf=rf).flatten(),
index=cluster_cov.index,
)
weight.loc[cluster_weights.index] *= cluster_weights
return weight
def _recursive_bisection(self, sort_order, rm="MV", rf=0):
weight = pd.Series(1, index=sort_order) # set initial weights to 1
items = [sort_order]
while len(items) > 0: # loop while weights is under 100%
items = [
i[j:k] for i in items for j, k in (
(0, len(i) // 2),
(len(i) // 2, len(i)),
) # get cluster indi
if len(i) > 1
]
# allocate weight to left and right cluster
for i in range(0, len(items), 2):
left_cluster = items[i]
right_cluster = items[i + 1]
# Left cluster
left_cov = self.cov.iloc[left_cluster, left_cluster]
left_returns = self.returns.iloc[:, left_cluster]
left_weight = self._naive_risk(left_returns,
left_cov,
rm=rm,
rf=rf)
if rm == "vol":
left_risk = rk.Sharpe_Risk(
left_weight,
cov=left_cov,
returns=left_returns,
rm="MV",
rf=rf,
alpha=self.alpha,
)
else:
left_risk = rk.Sharpe_Risk(
left_weight,
cov=left_cov,
returns=left_returns,
rm=rm,
rf=rf,
alpha=self.alpha,
)
if rm == "MV":
left_risk = np.power(left_risk, 2)
# Right cluster
right_cov = self.cov.iloc[right_cluster, right_cluster]
right_returns = self.returns.iloc[:, right_cluster]
right_weight = self._naive_risk(right_returns,
right_cov,
rm=rm,
rf=rf)
if rm == "vol":
right_risk = rk.Sharpe_Risk(
right_weight,
cov=right_cov,
returns=right_returns,
rm="MV",
rf=rf,
alpha=self.alpha,
)
else:
right_risk = rk.Sharpe_Risk(
right_weight,
cov=right_cov,
returns=right_returns,
rm=rm,
rf=rf,
alpha=self.alpha,
)
if rm == "MV":
right_risk = np.power(right_risk, 2)
# Allocate weight to clusters
alpha = 1 - left_risk / (left_risk + right_risk)
weight[left_cluster] *= alpha # weight 1
weight[right_cluster] *= 1 - alpha # weight 2
weight.index = self.asset_order
return weight
def plot_frontier(
w_frontier,
mu,
cov=None,
returns=None,
rm="MV",
rf=0,
alpha=0.05,
cmap="viridis",
w=None,
label="Portfolio",
marker="*",
s=16,
c="r",
height=6,
width=10,
t_factor=252,
ax=None,
):
r"""
Creates a plot of the efficient frontier for a risk measure specified by
the user.
Parameters
----------
w_frontier : DataFrame
Portfolio weights of some points in the efficient frontier.
mu : DataFrame of shape (1, n_assets)
Vector of expected returns, where n_assets is the number of assets.
cov : DataFrame of shape (n_features, n_features)
Covariance matrix, where n_features is the number of features.
returns : DataFrame of shape (n_samples, n_features)
Features matrix, where n_samples is the number of samples and
n_features is the number of features.
rm : str, optional
The risk measure used to estimate the frontier.
The default is 'MV'. Posible values are:
- 'MV': Standard Deviation.
- 'MAD': Mean Absolute Deviation.
- 'MSV': Semi Standard Deviation.
- 'FLPM': First Lower Partial Moment (Omega Ratio).
- 'SLPM': Second Lower Partial Moment (Sortino Ratio).
- 'CVaR': Conditional Value at Risk.
- 'EVaR': Conditional Value at Risk.
- 'WR': Worst Realization (Minimax)
- 'MDD': Maximum Drawdown of uncompounded returns (Calmar Ratio).
- 'ADD': Average Drawdown of uncompounded returns.
- 'DaR': Drawdown at Risk of uncompounded returns.
- 'CDaR': Conditional Drawdown at Risk of uncompounded returns.
- 'UCI': Ulcer Index of uncompounded returns.
rf : float, optional
Risk free rate or minimum aceptable return. The default is 0.
alpha : float, optional
Significante level of VaR, CVaR, EVaR, DaR and CDaR.
The default is 0.05.
cmap : cmap, optional
Colorscale, represente the risk adjusted return ratio.
The default is 'viridis'.
w : DataFrame of shape (n_assets, 1), optional
A portfolio specified by the user. The default is None.
label : str, optional
Name of portfolio that appear on plot legend.
The default is 'Portfolio'.
marker : str, optional
Marker of w. The default is "*".
s : float, optional
Size of marker. The default is 16.
c : str, optional
Color of marker. The default is 'r'.
height : float, optional
Height of the image in inches. The default is 6.
width : float, optional
Width of the image in inches. The default is 10.
t_factor : float, optional
Factor used to annualize expected return and expected risks for
risk measures based on returns (not drawdowns). The default is 252.
.. math::
\begin{align}
\text{Annualized Return} & = \text{Return} \, \times \, \text{t_factor} \\
\text{Annualized Risk} & = \text{Risk} \, \times \, \sqrt{\text{t_factor}}
\end{align}
ax : matplotlib axis, optional
If provided, plot on this axis. The default is None.
Raises
------
ValueError
When the value cannot be calculated.
Returns
-------
ax : matplotlib Axes
Returns the Axes object with the plot for further tweaking.
Example
-------
::
label = 'Max Risk Adjusted Return Portfolio'
mu = port.mu
cov = port.cov
returns = port.returns
ax = plf.plot_frontier(w_frontier=ws, mu=mu, cov=cov, returns=returns,
rm=rm, rf=0, alpha=0.05, cmap='viridis', w=w1,
label=label, marker='*', s=16, c='r',
height=6, width=10, t_factor=252, ax=None)
.. image:: images/MSV_Frontier.png
"""
if not isinstance(w_frontier, pd.DataFrame):
raise ValueError("w_frontier must be a DataFrame")
if not isinstance(mu, pd.DataFrame):
raise ValueError("mu must be a DataFrame")
if not isinstance(cov, pd.DataFrame):
raise ValueError("cov must be a DataFrame")
if not isinstance(returns, pd.DataFrame):
raise ValueError("returns must be a DataFrame")
if returns.shape[1] != w_frontier.shape[0]:
a1 = str(returns.shape)
a2 = str(w_frontier.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
if w is not None:
if not isinstance(w, pd.DataFrame):
raise ValueError("w must be a DataFrame")
if w.shape[1] > 1 and w.shape[0] == 0:
w = w.T
elif w.shape[1] > 1 and w.shape[0] > 0:
raise ValueError("w must be a column DataFrame")
if returns.shape[1] != w.shape[0]:
a1 = str(returns.shape)
a2 = str(w.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
if ax is None:
ax = plt.gca()
fig = plt.gcf()
fig.set_figwidth(width)
fig.set_figheight(height)
mu_ = np.array(mu, ndmin=2)
ax.set_ylabel("Expected Return")
item = rmeasures.index(rm)
x_label = rm_names[item] + " (" + rm + ")"
ax.set_xlabel("Expected Risk - " + x_label)
title = "Efficient Frontier Mean - " + x_label
ax.set_title(title)
X1 = []
Y1 = []
Z1 = []
for i in range(w_frontier.shape[1]):
weights = np.array(w_frontier.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(weights,
cov=cov,
returns=returns,
rm=rm,
rf=rf,
alpha=alpha)
ret = mu_ @ weights
ret = ret.item() * t_factor
if rm not in ["MDD", "ADD", "CDaR", "UCI"]:
risk = risk * t_factor**0.5
ratio = (ret - rf) / risk
X1.append(risk)
Y1.append(ret)
Z1.append(ratio)
ax1 = ax.scatter(X1, Y1, c=Z1, cmap=cmap)
if w is not None:
X2 = []
Y2 = []
for i in range(w.shape[1]):
weights = np.array(w.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(weights,
cov=cov,
returns=returns,
rm=rm,
rf=rf,
alpha=alpha)
ret = mu_ @ weights
ret = ret.item() * t_factor
if rm not in ["MDD", "ADD", "CDaR", "UCI"]:
risk = risk * t_factor**0.5
ratio = (ret - rf) / risk
X2.append(risk)
Y2.append(ret)
ax.scatter(X2, Y2, marker=marker, s=s**2, c=c, label=label)
ax.legend(loc="upper left")
xmin = np.min(X1) - np.abs(np.max(X1) - np.min(X1)) * 0.1
xmax = np.max(X1) + np.abs(np.max(X1) - np.min(X1)) * 0.1
ymin = np.min(Y1) - np.abs(np.max(Y1) - np.min(Y1)) * 0.1
ymax = np.max(Y1) + np.abs(np.max(Y1) - np.min(Y1)) * 0.1
ax.set_ylim(ymin, ymax)
ax.set_xlim(xmin, xmax)
ax.xaxis.set_major_locator(plt.AutoLocator())
ax.set_yticklabels(["{:.4%}".format(x) for x in ax.get_yticks()])
ax.set_xticklabels(["{:.4%}".format(x) for x in ax.get_xticks()])
ax.tick_params(axis="y", direction="in")
ax.tick_params(axis="x", direction="in")
ax.grid(linestyle=":")
colorbar = ax.figure.colorbar(ax1)
colorbar.set_label("Risk Adjusted Return Ratio")
fig = plt.gcf()
fig.tight_layout()
return ax
def plot_frontier(
w_frontier,
mu,
cov=None,
returns=None,
rm="MV",
rf=0,
alpha=0.01,
cmap="viridis",
w=None,
label="Portfolio",
marker="*",
s=16,
c="r",
height=6,
width=10,
ax=None,
):
"""
Creates a plot of the efficient frontier for a risk measure specified by
the user.
Parameters
----------
w_frontier : DataFrame
Portfolio weights of some points in the efficient frontier.
mu : DataFrame of shape (1, n_assets)
Vector of expected returns, where n_assets is the number of assets.
cov : DataFrame of shape (n_features, n_features)
Covariance matrix, where n_features is the number of features.
returns : DataFrame of shape (n_samples, n_features)
Features matrix, where n_samples is the number of samples and
n_features is the number of features.
rm : str, optional
Risk measure used to create the frontier. The default is 'MV'.
rf : float, optional
Risk free rate or minimum aceptable return. The default is 0.
alpha : float, optional
Significante level of VaR, CVaR and CDaR. The default is 0.01.
cmap : cmap, optional
Colorscale, represente the risk adjusted return ratio.
The default is 'viridis'.
w : DataFrame, optional
A portfolio specified by the user. The default is None.
label : str, optional
Name of portfolio that appear on plot legend.
The default is 'Portfolio'.
marker : str, optional
Marker of w_. The default is '*'.
s : float, optional
Size of marker. The default is 16.
c : str, optional
Color of marker. The default is 'r'.
height : float, optional
Height of the image in inches. The default is 6.
width : float, optional
Width of the image in inches. The default is 10.
ax : matplotlib axis, optional
If provided, plot on this axis. The default is None.
Raises
------
ValueError
When the value cannot be calculated.
Returns
-------
ax : matplotlib Axes
Returns the Axes object with the plot for further tweaking.
Example
-------
::
label = 'Max Risk Adjusted Return Portfolio'
mu = port.mu
cov = port.cov
returns = port.returns
ax = plf.plot_frontier(w_frontier=ws, mu=mu, cov=cov, returns=returns,
rm=rm, rf=0, alpha=0.01, cmap='viridis', w=w1,
label='Portfolio', marker='*', s=16, c='r',
height=6, width=10, ax=None)
.. image:: images/MSV_Frontier.png
"""
if not isinstance(w_frontier, pd.DataFrame):
raise ValueError("w_frontier must be a DataFrame")
if not isinstance(mu, pd.DataFrame):
raise ValueError("mu must be a DataFrame")
if not isinstance(cov, pd.DataFrame):
raise ValueError("cov must be a DataFrame")
if not isinstance(returns, pd.DataFrame):
raise ValueError("returns must be a DataFrame")
if returns.shape[1] != w_frontier.shape[0]:
a1 = str(returns.shape)
a2 = str(w_frontier.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
if w is not None:
if not isinstance(w, pd.DataFrame):
raise ValueError("w must be a DataFrame")
if w.shape[1] > 1 and w.shape[0] == 0:
w = w.T
elif w.shape[1] > 1 and w.shape[0] > 0:
raise ValueError("w must be a column DataFrame")
if returns.shape[1] != w.shape[0]:
a1 = str(returns.shape)
a2 = str(w.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
if ax is None:
ax = plt.gca()
fig = plt.gcf()
fig.set_figwidth(width)
fig.set_figheight(height)
mu_ = np.array(mu, ndmin=2)
ax.set_ylabel("Expected Return")
item = rmeasures.index(rm)
x_label = rm_names[item] + " (" + rm + ")"
ax.set_xlabel("Expected Risk - " + x_label)
title = "Efficient Frontier Mean - " + x_label
ax.set_title(title)
X1 = []
Y1 = []
Z1 = []
for i in range(w_frontier.shape[1]):
weights = np.array(w_frontier.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(
weights, cov=cov, returns=returns, rm=rm, rf=rf, alpha=alpha
)
ret = mu_ @ weights
ret = ret.item()
ratio = (ret - rf) / risk
X1.append(risk)
Y1.append(ret)
Z1.append(ratio)
ax1 = ax.scatter(X1, Y1, c=Z1, cmap=cmap)
if w is not None:
X2 = []
Y2 = []
for i in range(w.shape[1]):
weights = np.array(w.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(
weights, cov=cov, returns=returns, rm=rm, rf=rf, alpha=alpha
)
ret = mu_ @ weights
ret = ret.item()
ratio = (ret - rf) / risk
X2.append(risk)
Y2.append(ret)
ax.scatter(X2, Y2, marker=marker, s=s ** 2, c=c, label=label)
ax.legend(loc="upper left")
xmin = np.min(X1) - np.abs(np.max(X1) - np.min(X1)) * 0.1
xmax = np.max(X1) + np.abs(np.max(X1) - np.min(X1)) * 0.1
ymin = np.min(Y1) - np.abs(np.max(Y1) - np.min(Y1)) * 0.1
ymax = np.max(Y1) + np.abs(np.max(Y1) - np.min(Y1)) * 0.1
ax.set_ylim(ymin, ymax)
ax.set_xlim(xmin, xmax)
ax.set_yticklabels(["{:.4%}".format(x) for x in ax.get_yticks()])
ax.set_xticklabels(["{:.4%}".format(x) for x in ax.get_xticks()])
ax.tick_params(axis="y", direction="in")
ax.tick_params(axis="x", direction="in")
ax.grid(linestyle=":")
colorbar = ax.figure.colorbar(ax1)
colorbar.set_label("Risk Adjusted Return Ratio")
fig = plt.gcf()
fig.tight_layout()
return ax
def plot_frontier(
w_frontier,
mu,
cov=None,
returns=None,
rm="MV",
rf=0,
alpha=0.05,
cmap="viridis",
w=None,
label="Portfolio",
marker="*",
s=16,
c="r",
height=6,
width=10,
ax=None,
):
"""
Creates a plot of the efficient frontier for a risk measure specified by
the user.
Parameters
----------
w_frontier : DataFrame
Portfolio weights of some points in the efficient frontier.
mu : DataFrame of shape (1, n_assets)
Vector of expected returns, where n_assets is the number of assets.
cov : DataFrame of shape (n_features, n_features)
Covariance matrix, where n_features is the number of features.
returns : DataFrame of shape (n_samples, n_features)
Features matrix, where n_samples is the number of samples and
n_features is the number of features.
rm : str, optional
The risk measure used to estimate the frontier.
The default is 'MV'. Posible values are:
- 'MV': Standard Deviation.
- 'MAD': Mean Absolute Deviation.
- 'MSV': Semi Standard Deviation.
- 'FLPM': First Lower Partial Moment (Omega Ratio).
- 'SLPM': Second Lower Partial Moment (Sortino Ratio).
- 'CVaR': Conditional Value at Risk.
- 'EVaR': Conditional Value at Risk.
- 'WR': Worst Realization (Minimax)
- 'MDD': Maximum Drawdown of uncompounded returns (Calmar Ratio).
- 'ADD': Average Drawdown of uncompounded returns.
- 'DaR': Drawdown at Risk of uncompounded returns.
- 'CDaR': Conditional Drawdown at Risk of uncompounded returns.
- 'UCI': Ulcer Index of uncompounded returns.
rf : float, optional
Risk free rate or minimum acceptable return. The default is 0.
alpha : float, optional
Significante level of VaR, CVaR, EVaR, DaR and CDaR.
The default is 0.05.
cmap : cmap, optional
Colorscale, represente the risk adjusted return ratio.
The default is 'viridis'.
w : DataFrame of shape (n_assets, 1), optional
A portfolio specified by the user. The default is None.
label : str, optional
Name of portfolio that appear on plot legend.
The default is 'Portfolio'.
marker : str, optional
Marker of w_. The default is '*'.
s : float, optional
Size of marker. The default is 16.
c : str, optional
Color of marker. The default is 'r'.
height : float, optional
Height of the image in inches. The default is 6.
width : float, optional
Width of the image in inches. The default is 10.
ax : matplotlib axis, optional
If provided, plot on this axis. The default is None.
Raises
------
ValueError
When the value cannot be calculated.
Returns
-------
ax : matplotlib Axes
Returns the Axes object with the plot for further tweaking.
Example
-------
::
label = 'Max Risk Adjusted Return Portfolio'
mu = port.mu
cov = port.cov
returns = port.returns
ax = plf.plot_frontier(w_frontier=ws, mu=mu, cov=cov, returns=returns,
rm=rm, rf=0, alpha=0.05, cmap='viridis', w=w1,
label='Portfolio', marker='*', s=16, c='r',
height=6, width=10, ax=None)
.. image:: images/MSV_Frontier.png
"""
if not isinstance(w_frontier, pd.DataFrame):
raise ValueError("w_frontier must be a DataFrame")
if not isinstance(mu, pd.DataFrame):
raise ValueError("mu must be a DataFrame")
if not isinstance(cov, pd.DataFrame):
raise ValueError("cov must be a DataFrame")
if not isinstance(returns, pd.DataFrame):
raise ValueError("returns must be a DataFrame")
if returns.shape[1] != w_frontier.shape[0]:
a1 = str(returns.shape)
a2 = str(w_frontier.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
if w is not None:
if not isinstance(w, pd.DataFrame):
raise ValueError("w must be a DataFrame")
if w.shape[1] > 1 and w.shape[0] == 0:
w = w.T
elif w.shape[1] > 1 and w.shape[0] > 0:
raise ValueError("w must be a column DataFrame")
if returns.shape[1] != w.shape[0]:
a1 = str(returns.shape)
a2 = str(w.shape)
raise ValueError("shapes " + a1 + " and " + a2 + " not aligned")
mu_ = np.array(mu, ndmin=2)
item = rmeasures.index(rm)
x_label = rm_names[item] + " (" + rm + ")"
# title = "Efficient Frontier Mean - " + x_label
pretty_container_bgcolor = '#f9f9f9'
fig = go.Figure(
layout=go.Layout(
# title=title,
plot_bgcolor=pretty_container_bgcolor,
hovermode='x',
hoverdistance=100,
spikedistance=1000,
xaxis=dict(
title=rm_names[item] + " (" + rm + ")",
linecolor='#9a9a9a',
showgrid=False,
showspikes=True,
spikethickness=3,
spikedash='dot',
spikecolor='#FF0000',
spikemode='across'
),
yaxis=dict(
title="Expected Return",
linecolor='#9a9a9a',
showgrid=False
)
)
)
X1 = []
Y1 = []
Z1 = []
for i in range(w_frontier.shape[1]):
weights = np.array(w_frontier.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(
weights, cov=cov, returns=returns, rm=rm, rf=rf, alpha=alpha
)
ret = mu_ @ weights
ret = ret.item()
ratio = (ret - rf) / risk
X1.append(risk)
Y1.append(ret)
Z1.append(ratio)
fig.add_trace(
go.Scatter(
x=X1,
y=Y1
)
)
# ax1 = ax.scatter(X1, Y1, c=Z1, cmap=cmap)
if w is not None:
X2 = []
Y2 = []
for i in range(w.shape[1]):
weights = np.array(w.iloc[:, i], ndmin=2).T
risk = rk.Sharpe_Risk(
weights, cov=cov, returns=returns, rm=rm, rf=rf, alpha=alpha
)
ret = mu_ @ weights
ret = ret.item()
ratio = (ret - rf) / risk
X2.append(risk)
Y2.append(ret)
fig.add_trace(
go.Scatter(
x=X2,
y=Y2
)
)
fig.update_layout(
margin=dict(l=100, r=100, t=100, b=100)
)
#
# xmin = np.min(X1) - np.abs(np.max(X1) - np.min(X1)) * 0.1
# xmax = np.max(X1) + np.abs(np.max(X1) - np.min(X1)) * 0.1
# ymin = np.min(Y1) - np.abs(np.max(Y1) - np.min(Y1)) * 0.1
# ymax = np.max(Y1) + np.abs(np.max(Y1) - np.min(Y1)) * 0.1
#
# ax.set_ylim(ymin, ymax)
# ax.set_xlim(xmin, xmax)
#
# ax.set_yticklabels(["{:.4%}".format(x) for x in ax.get_yticks()])
# ax.set_xticklabels(["{:.4%}".format(x) for x in ax.get_xticks()])
#
# ax.tick_params(axis="y", direction="in")
# ax.tick_params(axis="x", direction="in")
#
# ax.grid(linestyle=":")
#
# colorbar = ax.figure.colorbar(ax1)
# colorbar.set_label("Risk Adjusted Return Ratio")
#
# fig = plt.gcf()
# fig.tight_layout()
return fig
