import numpy as np
import pandas as pd

df = pd.read_csv('../data/10stocks_price.csv')  # stock price data

# Convert dates to timestamps and set date column as the index
df['date_gsheets'] = pd.to_datetime(df['date_gsheets'])
df.set_index('date_gsheets', inplace=True)

# Calculate returns for each stock
returns_df = df.pct_change(1)

# Estimating the risk of a 10 asset portfolio
num_stocks = 10
weights = [1 / num_stocks] * num_stocks  # vector (list) of weights
vcv_matrix = returns_df.cov()  # variance covariance matrix

# Calculate variance and standard deviation of the 10 asset portfolio
var_portfolio = np.dot(np.transpose(weights), np.dot(vcv_matrix, weights))
sd_portfolio = np.sqrt(var_portfolio)
sd_portfolio_annual = sd_portfolio * np.sqrt(250)

# Estimate individual stock risks for comparison
individual_risks = np.std(returns_df) * np.sqrt(250)