Hugo Dolan hugo1005

Bsc. Applied Computational Mathematics & Statistics

hugo1005 / portfolio_opimization.py

Created January 22, 2021 21:10

portfolio_opimization

	import requests
	import pandas as pd
	import time
	import json
	import numpy as np
	import scipy as sp
	import matplotlib.pyplot as plt
	import seaborn as sns
	from tqdm import tqdm
	import cvxopt as opt

hugo1005 / hierachical_bayes_model.py

Created January 6, 2021 14:03

	import pandas as pd
	import pymc3 as pm
	import matplotlib.pyplot as plt
	import numpy as np
	from tqdm import tqdm

	model_df = pd.read_csv('./breakpoints.csv')
	sectors = model_df['equity_sector'].unique()
	industry = model_df['equity_industry'].unique()

hugo1005 / Nested_plots.py

Created December 23, 2020 14:23

Nested / Picture In Picture Plots Example

	import matplotlib.pyplot as plt
	import pandas as pd

	font_title = {'family': 'roboto',
	'color': '#0f3567',
	'weight': 'bold',
	'size': 16,
	}

	font_mini_title = {'family': 'roboto',

hugo1005 / Games_Howell.py

Created December 23, 2020 14:21

Games Howell Test (Multiple Comparisons)

	from scipy.stats import f_oneway
	a = all_metrics[all_metrics['significance'] == 'insignficant']['post_covid_return'].dropna().values
	b = all_metrics[all_metrics['significance'] == 'intrinsic_only']['post_covid_return'].dropna().values
	c = all_metrics[all_metrics['significance'] == 'sharpe_only']['post_covid_return'].dropna().values
	d = all_metrics[all_metrics['significance'] == 'both']['post_covid_return'].dropna().values

	import statsmodels
	print(f_oneway(a,b,c,d)) # Signficicant Difference between groups

	from itertools import combinations, product

hugo1005 / AutoFitting.R

Created December 23, 2020 14:18

Fitting ARMA GARCH Models to many time series and saving the results