In [1]:

    

import os
from datetime import datetime
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt


    

In [2]:

    

os.chdir("..")


    

In [3]:

    

from Signals.BitcoinData import BitcoinData
from Signals.WikipediaData import WikipediaData
from Signals.FXData import FXData


    

In [4]:

    

bd = BitcoinData()
bitcoin = bd.get(datetime(2016, 1, 1), datetime(2016, 6, 1))


    

In [5]:

    

wd = WikipediaData()
wiki = wd.get(datetime(2016, 1, 1), datetime(2016, 6, 1))


    

In [6]:

    

fxd = FXData()
fx = fxd.get(datetime(2016, 1, 1), datetime(2016, 6, 1))


    

In [7]:

    

x = bitcoin.merge(fx, how='outer', left_index=True, right_index=True)\
           .merge(wiki, how='outer', left_index=True, right_index=True)


    

In [8]:

    

x['USDCNY'].fillna(method='pad', inplace=True)
x['USDEUR'].fillna(method='pad', inplace=True)
x['VIX'].fillna(method='pad', inplace=True)


    

In [9]:

    

x['next_open'] = x['Open'].shift(-1)
x['change'] = x['next_open'] - x['Open']
x['next_day_higher'] = x['change'].map(lambda x: x > 0)


    

In [10]:

    

def addlogret(df, col):
    df[col+'_logret'] = np.log(df[col]) - np.log(df[col].shift(1))
def addewma(df, col):
    for i in [3, 10, 30]:
        df[col+'_ewma_'+str(i)] = df[col].ewm(halflife=i).mean()
def addewmvar(df, col):
    for i in [3, 10, 30]:
        df[col+'_ewmvar_'+str(i)] = df[col].ewm(halflife=i).var()


    

In [11]:

    

for col in ['Open', 'Volume', 'USDCNY', 'USDEUR', 'VIX', 'views']:
    addlogret(x, col)
    addewma(x, col)
    addewma(x, col+"_logret")
    addewmvar(x, col)


    

In [12]:

    

x.dropna(inplace=True)


    

In [13]:

    

y = x['next_day_higher']


    

In [14]:

    

x.drop(['next_day_higher'], axis=1, inplace=True)


    

In [15]:

    

from sklearn import linear_model


    

In [16]:

    

logreg = linear_model.LogisticRegression(C=1e5)
logreg.fit(x, y)


    

    
Out[16]:





LogisticRegression(C=100000.0, class_weight=None, dual=False,
          fit_intercept=True, intercept_scaling=1, max_iter=100,
          multi_class='ovr', n_jobs=1, penalty='l2', random_state=None,
          solver='liblinear', tol=0.0001, verbose=0, warm_start=False)

In [17]:

    

print("Model score: {:.1f}%".format(100*logreg.score(x, y)))


    

    




Model score: 56.5%

In [18]:

    

from PerfAnalysis.PnL import PnL


    

In [19]:

    

pnl = PnL()
pnl.calc_pnl(x, y, price_col="Open")


    

    
Out[19]:





{'APR': 212.82985561414253,
 'cash': 0,
 'position': 0.51604581259045823,
 'value': 269.0353239359095}

In [20]:

    

bitcoin = bd.get(datetime(2016, 6, 1), datetime(2017, 1, 1))
wiki = wd.get(datetime(2016, 6, 1), datetime(2017, 1, 1))
fx = fxd.get(datetime(2016, 6, 1), datetime(2017, 1, 1))
x = bitcoin.merge(fx, how='outer', left_index=True, right_index=True)\
           .merge(wiki, how='outer', left_index=True, right_index=True)
x['USDCNY'].fillna(method='pad', inplace=True)
x['USDEUR'].fillna(method='pad', inplace=True)
x['VIX'].fillna(method='pad', inplace=True)
x['next_open'] = x['Open'].shift(-1)
x['change'] = x['next_open'] - x['Open']
x['next_day_higher'] = x['change'].map(lambda x: x > 0)
for col in ['Open', 'Volume', 'USDCNY', 'USDEUR', 'VIX', 'views']:
    addlogret(x, col)
    addewma(x, col)
    addewma(x, col+"_logret")
    addewmvar(x, col)
x.drop(['next_day_higher'], axis=1, inplace=True)
x.dropna(inplace=True)


    

In [21]:

    

pred = logreg.predict(x)


    

In [22]:

    

pnl.calc_pnl(x, pred, price_col="Open")


    

    
Out[22]:





{'APR': -111.22094549159256,
 'cash': 74.649234306898478,
 'position': 0,
 'value': 74.649234306898478}