from datetime import datetime

from pandas_datareader import data

import pandas as pd

import numpy as np

from numpy import log, polyfit, sqrt, std, subtract

import statsmodels.tsa.stattools as ts

import statsmodels.api as sm

import matplotlib.pyplot as plt

import seaborn as sns

import pprint

symbList = ['GOOG','FB']

start_date = '2008/01/01'

end_date = '2018/01/01'

# Fetching data and initializing the IV column
#here's the way to add a new column: Initialize it, ha!

dataAll = pd.read_csv("CompaniesSP.csv")
#create a new column and give value 0, just to do something new in the data file
dataAll['IV'] = 0

#take the first8 columns of the file, iterating name range
data=dataAll.loc[:, 'Date':'SBUX']

data.head()

tickers =  ['AAPL', 'MSFT']

from pandas import read_csv
series = read_csv('CompaniesSP.csv', header=0, parse_dates=[0], index_col=0, squeeze=True)
print(type(series))
series.describe()

# This line is necessary for the plot to appear in a Jupyter notebook (you don't need it if you're working in Rodeo)
%matplotlib inline
# Control the default size of figures in this Jupyter notebook (n/a if working in Rodeo)
%pylab inline
pylab.rcParams['figure.figsize'] = (15, 9)   # Change the size of plots

# Plot the adjusted closing price of AAPL
series.loc[:, 'AAPL':'SBUX'].plot(grid = True)

series.loc[:, 'AAPL'].plot(grid = True)

#create changes and add the corresponding new columns
series['GOOG_Ret'] = series['GOOG'].pct_change().dropna()
series['SPX_Ret'] = series['SPX'].pct_change().dropna()
series['AAPL_Ret'] = series['AAPL'].pct_change().dropna()

#rolling correlation of google and sp500 of returns yearly (250 days)
series['GOOG_Ret'].rolling(252).corr(series['SPX_Ret']).plot(figsize=(15,4))

#create the historical 30day vol
series['SPX_HV21'] = series['SPX_Ret'].rolling(21).std() * np.sqrt(252) * 100
series['GOOG_HV21'] = series['GOOG_Ret'].rolling(21).std() * np.sqrt(252) * 100
series['AAPL_HV21'] = series['AAPL_Ret'].rolling(21).std() * np.sqrt(252) * 100

series[['GOOG_HV21','AAPL_HV21','SPX_HV21']].plot(figsize=(15,8), grid= True)

AAPL_TS=series['AAPL_Ret']

def hurst(AAPL_TS):
    # Create the range of lag values
    lags= range (2,100)
     # Calculate the array of variances of the lagged differences
    tau=[sqrt(std(subtract(AAPL_TS[lag:], AAPL_TS[-lag]))) for lag in lags]
     # Use a linear fit to estimate the hurst exponent
    poly = polyfit(log(lags), log(tau), 1)
     # Return the hurst exponent from the polyfit output
    return poly[0]*2.0

hurst(AAPL_TS)

series.loc[:, 'AAPL_Ret'].plot(grid = True)

AAPL_Price=series['AAPL']

def hurst(AAPL_Price):
    # Create the range of lag values
    lags= range (2,100)
     # Calculate the array of variances of the lagged differences
    tau=[sqrt(std(subtract(AAPL_Price[lag:], AAPL_Price[-lag]))) for lag in lags]
     # Use a linear fit to estimate the hurst exponent
    poly = polyfit(log(lags), log(tau), 1)
     # Return the hurst exponent from the polyfit output
    return poly[0]*2.0

hurst(AAPL_Price)

AAPL_Price2=series['2000-08-31':'2008-08-31']['AAPL']

AAPL_Price2.head()

AAPL_Price2.tail()

hurst(AAPL_Price2)

AAPL_Price3=series['2008-08-31':'2018-04-30']['AAPL']

hurst(AAPL_Price3)

AAPL_Price3=series['2008-08-31':'2018-04-30']['AAPL'].plot()

AAPL_Price16=series['2008-08-31':'2016-04-30']['AAPL']

hurst(AAPL_Price16)