In [1]:
import pandas as pd
from pandas import Timedelta as td
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt
import datetime as dt
from pykalman import KalmanFilter
In [2]:
start = '2002-1-1'
end= '2015, 12, 1'
#p= pattern length
p = 125
#o = outcome length
o = 25
In [3]:
def ret_index(prices):
'''
return index of 1 dollar invested in that instrument
'''
rets = prices.pct_change()
index = (rets+1).cumprod()
return (index-1)*100
In [7]:
px = get_pricing('SPY', start, end, fields= 'price')
i = len(px.index)-1
#verify
current_close = px.iloc[i]
current_date = px.index[i]
print current_date, current_close
#historical data within to serach for similar patterns
h = px[:i-p]
cp = px.iloc[i-p:i]
In [8]:
def similar(x):
'''
condition: patterns have to be correlated according to the pearson correlation
'''
sp_corr_value, sp_corr_pvalue = stats.pearsonr(cp.values,x)
if sp_corr_value < sp_corr_pvalue: # correlation value returned by pearnson has to be grather than p_value
return np.NAN
else:
return sp_corr_value
In [11]:
correlation = pd.rolling_apply(h,p,similar)# apply the similar function to each row of the historical dataframe
correlation.name = 'corr'
correlation.dropna(inplace=True)
correlation.plot(style='ro')
Out[11]:
In [12]:
df = pd.DataFrame(correlation).dropna()
df['date']=df.index
df.columns = ['corr', 'date']
df['delta'] = (df['date']-df['date'].shift(1))/pd.Timedelta('1 days')
df['delta'].fillna(p+1, inplace=True)
df['eval'] = df.apply(lambda x: x['date'] if x['delta'] >7 else np.NAN, axis=1)
df.fillna(method = 'pad', inplace=True)
df[:5]
Out[12]:
In [13]:
# lista di date a cui corrispondono i massimi valori di correlazione
pat = df['corr'].groupby(df['eval']).apply(lambda x: x.argmax()).values
pat
Out[13]:
In [14]:
max_corr = df['corr'].loc[[_ for _ in pat]]
max_corr.order(ascending=False, inplace=True)
max_corr = max_corr[:10]
pat_names = max_corr.index
In [15]:
correlation.plot(style='ro', alpha= .2)
max_corr.plot(style= 'ko')
Out[15]:
In [16]:
pat_list = [px.iloc[(i+1)-p:i+1] for i, date in enumerate(px.index) if date in pat_names]
out_list = [px.iloc[(i+1):(i+1)+o] for i, date in enumerate(px.index) if date in pat_names]
df_pat = pd.concat(pat_list, axis= 1)
df_out = pd.concat(out_list, axis=1)
df_pat.columns= pat_names
df_out.columns= pat_names
In [17]:
ri= ret_index(cp).fillna(0).values
for d in pat_names:
q_p = df_pat[d].dropna()
q_o = df_out[d].dropna()
q_p = q_p.reset_index(drop=True)
q_o = q_o.reset_index(drop=True)
r_p= ret_index(q_p).fillna(0)
r_o = ret_index(q_o).fillna(0)
r_p= r_p.values
r_o = r_o.values
plt.plot(range(p), r_p-r_p[-1])
plt.plot([_+(p-1) for _ in range(o)], r_o-r_o[0])
plt.plot(ri-ri[-1], 'k')
plt.show()
df_pat.plot()
plt.show()
In [ ]: