volest

A complete set of volatility estimators based on Euan Sinclair's Volatility Trading.

http://www.amazon.com/gp/product/0470181990/tag=quantfinancea-20

The original version incorporated network data acquisition from Yahoo!Finance from

pandas_datareader

pandas_datareader

The changes allow you to specify your own data so you're not tied into equity data from Yahoo! finance. If you're still using equity data, just download a CSV from finance.yahoo.com and use the

data.yahoo_data_helper

Volatility estimators include:

• Garman Klass
• Hodges Tompkins
• Parkinson
• Rogers Satchell
• Yang Zhang
• Standard Deviation

Also includes

• Skew
• Kurtosis
• Correlation

For each of the estimators, plot:

• Probability cones
• Rolling quantiles
• Rolling extremes
• Rolling descriptive statistics
• Histogram
• Comparison against arbirary comparable
• Correlation against arbirary comparable
• Regression against arbirary comparable

Create a term sheet with all the metrics printed to a PDF.

Page 1 - Volatility cones

Page 2 - Volatility rolling percentiles

Page 3 - Volatility rolling min and max

Page 4 - Volatility rolling mean, standard deviation and zscore

Page 5 - Volatility distribution

Page 6 - Volatility, benchmark volatility and ratio

Page 7 - Volatility rolling correlation with benchmark

Page 3 - Volatility OLS results

Example usage:

import volest
import data

data
symbol = 'JPM'
bench = '^GSPC'
data_file_path = '../JPM.csv'
bench_file_path = '../BENCH.csv'
estimator = 'GarmanKlass'
estimator windows
window = 30
windows = [30, 60, 90, 120]
quantiles = [0.25, 0.75]
bins = 100
normed = True
use the yahoo helper to correctly format data from finance.yahoo.com
jpm_price_data = data.yahoo_helper(symbol, data_file_path)
spx_price_data = data.yahoo_helper(bench, bench_file_path)
initialize class
vol = volest.VolatilityEstimator(
    price_data=jpm_price_data,
    estimator=estimator,
    bench_data=spx_price_data
)
call plt.show() on any of the below...
_, plt = vol.cones(windows=windows, quantiles=quantiles)
_, plt = vol.rolling_quantiles(window=window, quantiles=quantiles)
_, plt = vol.rolling_extremes(window=window)
_, plt = vol.rolling_descriptives(window=window)
_, plt = vol.histogram(window=window, bins=bins, normed=normed)
_, plt = vol.benchmark_compare(window=window)
_, plt = vol.benchmark_correlation(window=window)
... or create a pdf term sheet with all metrics in term-sheets/
vol.term_sheet(
    window,
    windows,
    quantiles,
    bins,
    normed
)

Hit me on twitter with comments, questions, issues @jasonstrimpel