|
import gradio as gr |
|
import yfinance as yf |
|
from pypfopt.discrete_allocation import DiscreteAllocation, get_latest_prices |
|
from pypfopt import EfficientFrontier |
|
from pypfopt import risk_models |
|
from pypfopt import expected_returns |
|
from pypfopt import plotting |
|
import copy |
|
import numpy as np |
|
import pandas as pd |
|
import plotly.express as px |
|
import matplotlib.pyplot as plt |
|
from datetime import datetime |
|
import datetime |
|
|
|
def plot_cum_returns(data, title): |
|
daily_cum_returns = 1 + data.dropna().pct_change() |
|
daily_cum_returns = daily_cum_returns.cumprod()*100 |
|
fig = px.line(daily_cum_returns, title=title) |
|
return fig |
|
|
|
def plot_efficient_frontier_and_max_sharpe(mu, S): |
|
|
|
ef = EfficientFrontier(mu, S) |
|
fig, ax = plt.subplots(figsize=(6,4)) |
|
ef_max_sharpe = copy.deepcopy(ef) |
|
plotting.plot_efficient_frontier(ef, ax=ax, show_assets=False) |
|
|
|
ef_max_sharpe.max_sharpe(risk_free_rate=0.02) |
|
ret_tangent, std_tangent, _ = ef_max_sharpe.portfolio_performance() |
|
ax.scatter(std_tangent, ret_tangent, marker="*", s=100, c="r", label="Max Sharpe") |
|
|
|
n_samples = 1000 |
|
w = np.random.dirichlet(np.ones(ef.n_assets), n_samples) |
|
rets = w.dot(ef.expected_returns) |
|
stds = np.sqrt(np.diag(w @ ef.cov_matrix @ w.T)) |
|
sharpes = rets / stds |
|
ax.scatter(stds, rets, marker=".", c=sharpes, cmap="viridis_r") |
|
|
|
ax.legend() |
|
return fig |
|
|
|
def output_results(start_date, end_date, tickers_string): |
|
tickers = tickers_string.split(',') |
|
|
|
|
|
stocks_df = yf.download(tickers, start=start_date, end=end_date)['Adj Close'] |
|
|
|
|
|
fig_indiv_prices = px.line(stocks_df, title='Price of Individual Stocks') |
|
|
|
|
|
fig_cum_returns = plot_cum_returns(stocks_df, 'Cumulative Returns of Individual Stocks Starting with $100') |
|
|
|
|
|
corr_df = stocks_df.corr().round(2) |
|
fig_corr = px.imshow(corr_df, text_auto=True, title = 'Correlation between Stocks') |
|
|
|
|
|
mu = expected_returns.mean_historical_return(stocks_df) |
|
S = risk_models.sample_cov(stocks_df) |
|
|
|
|
|
fig_efficient_frontier = plot_efficient_frontier_and_max_sharpe(mu, S) |
|
|
|
|
|
ef = EfficientFrontier(mu, S) |
|
ef.max_sharpe(risk_free_rate=0.02) |
|
weights = ef.clean_weights() |
|
expected_annual_return, annual_volatility, sharpe_ratio = ef.portfolio_performance() |
|
|
|
expected_annual_return, annual_volatility, sharpe_ratio = '{}%'.format((expected_annual_return*100).round(2)), \ |
|
'{}%'.format((annual_volatility*100).round(2)), \ |
|
'{}%'.format((sharpe_ratio*100).round(2)) |
|
|
|
weights_df = pd.DataFrame.from_dict(weights, orient = 'index') |
|
weights_df = weights_df.reset_index() |
|
weights_df.columns = ['Tickers', 'Weights'] |
|
|
|
|
|
stocks_df['Optimized Portfolio'] = 0 |
|
for ticker, weight in weights.items(): |
|
stocks_df['Optimized Portfolio'] += stocks_df[ticker]*weight |
|
|
|
|
|
fig_cum_returns_optimized = plot_cum_returns(stocks_df['Optimized Portfolio'], 'Cumulative Returns of Optimized Portfolio Starting with $100') |
|
|
|
return fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ |
|
expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns |
|
|
|
|
|
with gr.Blocks() as app: |
|
with gr.Row(): |
|
gr.HTML("<h1>Bohmian's Stock Portfolio Optimizer</h1>") |
|
|
|
with gr.Row(): |
|
start_date = gr.Textbox("2013-01-01", label="Start Date") |
|
end_date = gr.Textbox(datetime.datetime.now().date(), label="End Date") |
|
|
|
with gr.Row(): |
|
tickers_string = gr.Textbox("MA,META,V,AMZN,JPM,BA", |
|
label='Enter all stock tickers to be included in portfolio separated \ |
|
by commas WITHOUT spaces, e.g. "MA,META,V,AMZN,JPM,BA"') |
|
btn = gr.Button("Get Optimized Portfolio") |
|
|
|
with gr.Row(): |
|
gr.Markdown("Optimizied Portfolio Metrics") |
|
|
|
with gr.Row(): |
|
expected_annual_return = gr.Text(label="Expected Annual Return") |
|
annual_volatility = gr.Text(label="Annual Volatility") |
|
sharpe_ratio = gr.Text(label="Sharpe Ratio") |
|
|
|
with gr.Row(): |
|
fig_cum_returns_optimized = gr.Plot(label="Cumulative Returns of Optimized Portfolio (Starting Price of $100)") |
|
weights_df = gr.DataFrame(label="Optimized Weights of Each Ticker") |
|
|
|
with gr.Row(): |
|
fig_efficient_frontier = gr.Plot(label="Efficient Frontier") |
|
fig_corr = gr.Plot(label="Correlation between Stocks") |
|
|
|
with gr.Row(): |
|
fig_indiv_prices = gr.Plot(label="Price of Individual Stocks") |
|
fig_cum_returns = gr.Plot(label="Cumulative Returns of Individual Stocks Starting with $100") |
|
|
|
btn.click(fn=output_results, inputs=[start_date, end_date, tickers_string], |
|
outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ |
|
expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) |
|
|
|
app.launch() |