def get_student():
student_id = get_int("Enter ID Number:")
matching_ids = [
student for student in student_list if student.id == student_id
]
if not matching_ids:
print("You're not in the list!")
get_student()
return matching_ids[0] # Take first student
def edit_id_number():
new_id = get_int("Enter your new ID number")
student.id = new_id
def edit_unit():
new_unit = get_int("Enter new unit")
course.unit = new_unit
def add_course():
code = get_string("Enter Code")
unit = get_int("Enter unit")
course_list.append(Course(unit=unit, code=code))
print(course_list[0].code) # TEST
def register():
name = get_string("Enter name")
id = get_int("Enter ID Number")
student_list.append(Student(name=name, id=id))
print(f"Welcome {name}!")
fig.suptitle('Proportion of variance explained by principal components')
ax1.bar(["{:.1e}".format(eigenvalue) for eigenvalue
in eigenvalue_df['eigenvalue']], eigenvalue_df['proportion_of_variance'])
ax1.set_xlabel("eigenvalue")
ax1.set_ylabel("proportion of variance explained")
ax2.plot(cumulative_plot, marker="^")
ax2.set_xlabel("# of principal components (sorted)")
ax2.set_ylabel("Cumulative prop. of variance explained")
ax2.set_ylim([0, 1])
plt.show()
reduced_eigenvalue_matrix = None
reduced_covariance_matrix = None
if user_input.get_boolean("Reduce dimensionality using PCA? (Y/N) "):
max_components = len(eigenvalue_df)
num_components = user_input.get_int("Enter desired number of components (1 to " +
str(max_components) + ") ", int_min=0, int_max=max_components)
reduced_eigenvalue_matrix, reduced_covariance_matrix = \
numerical_functions.run_principal_components_analysis(num_components, eigenvalue_df, eigenvector_df)
adjusted_final = float((weights.dot(reduced_covariance_matrix)).dot(weights.transpose()))
adjusted_portfolio_stddev = np.sqrt(adjusted_final)
adjusted_shift = np.expm1(adjusted_portfolio_stddev * z_score) * np.sqrt(holding_period)
adjusted_var = abs(np.sum(notional_values) * adjusted_shift)
helper_functions.output(f"PCA-adjusted portfolio standard deviation: {adjusted_portfolio_stddev:.2%}")
helper_functions.output(f"PCA-adjusted log return: {adjusted_shift:.2%}")
helper_functions.output(f"PCA-adjusted percentage return: "
f"{adjusted_portfolio_stddev * z_score * np.sqrt(holding_period):.2%}")
helper_functions.output(str(holding_period) + "-day" + f"{confidence_level: .2%}"
+ " PCA-adjusted VaR: $" + f'{adjusted_var:,.2f}')