techwithshadab

def selection_to_picks(num_assets, selection):
    purchase = []
    for i in range(num_assets):
        if selection[i] == 1:
            purchase.append(stock_list[i])
    return purchase

techwithshadab

def index_to_selection(i, num_assets):
    s = "{0:b}".format(i).rjust(num_assets)
    x = np.array([1 if s[i]=='1' else 0 for i in reversed(range(num_assets))])
    return x

techwithshadab

# Retrieve Hamiltonian
qubitOp, offset = portfolio.get_operator(mu, sigma, risk_factor, budget, penalty)

techwithshadab

sns.pairplot(df)
plt.show()

techwithshadab

# Correlation Matrix
corr = df.corr()
f, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(corr, mask=np.zeros_like(corr, dtype=np.bool), annot=True, square=True, ax=ax, xticklabels=stock_list, yticklabels=stock_list)
plt.title("Correlation between Equities")
plt.show()

techwithshadab

# Covariance Matrix
sigma = data.get_period_return_covariance_matrix()
f, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(sigma, mask=np.zeros_like(sigma, dtype=np.bool), annot=True, square=True, ax=ax, xticklabels=stock_list, yticklabels=stock_list)
plt.title("Covariance between Equities")
plt.show()

techwithshadab

# Mean value of each assets
mu = data.get_period_return_mean_vector()
sns.barplot(y=mu, x = stock_list)
plt.show()

techwithshadab

# Closing Price History
fig, ax = plt.subplots(figsize=(15, 8))
ax.plot(df)
plt.title('Close Price History')
plt.xlabel('Date',fontsize =20)
plt.ylabel('Price in USD',fontsize = 20)
ax.legend(df.columns.values)
plt.show()

techwithshadab

df.describe()

techwithshadab

data = EikonDataProvider(stocks_list = stock_list, start_date=start_date, end_date=end_date)
data.run()
# Top 5 rows of data 
df = data.stock_data
df.head()