In [1]:

    

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import csv
import glob

filename = '/home/octo/Dropbox'+ '/SPY4Aug17.csv'


    

In [2]:

    

# loading csv file
def get_csv_pd(path):
    #spy_pd=pd.read_csv('C:\\Users\Michal\Dropbox\IB_data\SPY.csv',sep=' ',names=['askPrice','askSize','bidPrice','bidSize'],index_col=0,parse_dates=True)
    #spy_pd=pd.read_csv(path+'\SPY.csv',sep=',',names=['askPrice','askSize','bidPrice','bidSize'],index_col=0,parse_dates=True)
    spy_pd=pd.read_csv(path,sep=',',dtype={'askPrice':np.float32,'askSize':np.float32,
                                           'bidPrice':np.float32,'bidSize':np.float32},index_col=0,parse_dates=True)
    #spy_pd = pd.read_csv(path, usecols=['askPrice','askSize','bidPrice','bidSize'], engine='python', skipfooter=3)
    return spy_pd

def get_csv_pd_notime(path):
    #spy_pd=pd.read_csv('C:\\Users\Michal\Dropbox\IB_data\SPY.csv',sep=' ',names=['askPrice','askSize','bidPrice','bidSize'],index_col=0,parse_dates=True)
    #spy_pd=pd.read_csv(path+'\SPY.csv',sep=',',names=['askPrice','askSize','bidPrice','bidSize'],index_col=0,parse_dates=True)
    spy_pd = pd.read_csv(path, usecols=['askPrice','askSize','bidPrice','bidSize'], engine='python', skipfooter=3)
    return spy_pd


def preprocessing(df):
    df.bidPrice=df.loc[:,'bidPrice'].replace(to_replace=0, method='ffill')
    df.bidSize=df.loc[:,'bidSize'].replace(to_replace=0, method='ffill')
    df.askPrice=df.loc[:,'askPrice'].replace(to_replace=0, method='ffill')
    df.askSize=df.loc[:,'askSize'].replace(to_replace=0, method='ffill')
    df=df.dropna()
    # to exclude 0
    df=df[df['bidPrice']>df.bidPrice.mean()-df.bidPrice.std()]
    df=df[df['askPrice']>df.askPrice.mean()-df.askPrice.std()]
    df['mid']=(df.askPrice+df.bidPrice)/2
    df['vwap']=((df.loc[:,'bidPrice']*df.loc[:,'bidSize'])+(df.loc[:,'askPrice']*df.loc[:,'askSize']))/(df.loc[:,'bidSize']+df.loc[:,'askSize'])
    df['spread']=df.vwap-(df.askPrice+df.bidPrice)/2
    df['v']=(df.askPrice+df.bidPrice)/2-((df.askPrice+df.bidPrice)/2).shift(60)
    df['return']=(df.askPrice/df.bidPrice.shift(1))-1
    df['sigma']=df.spread.rolling(60).std()
    return df

def normalise(df,window_length=60):
    dfn=(df-df.rolling(window_length).min())/(df.rolling(window_length).max()-df.rolling(window_length).min())
    return dfn

def de_normalise(df,window_length=60):
    dn=(df*(df.rolling(window_length).max()-df.rolling(window_length).min()))+df.rolling(window_length).min()
    return dn


    

In [3]:

    

data=get_csv_pd(filename)
data=preprocessing(data)
data=normalise(data)
data=data.dropna()


    

In [4]:

    

data.head()


    

    
Out[4]:







  

    

      

      
askPrice
      
askSize
      
bidPrice
      
bidSize
      
mid
      
vwap
      
spread
      
v
      
return
      
sigma
    
  
  

    

      
2017-08-03 11:47:20.626235
      
1.0
      
1.000000
      
1.0
      
0.005450
      
1.0
      
0.996154
      
0.992248
      
1.0
      
0.997059
      
0.922860
    
    

      
2017-08-03 11:47:20.634236
      
1.0
      
0.938356
      
1.0
      
0.005450
      
1.0
      
0.996154
      
0.992248
      
1.0
      
0.997059
      
0.909415
    
    

      
2017-08-03 11:47:21.618171
      
1.0
      
0.938356
      
1.0
      
0.008174
      
1.0
      
0.993846
      
0.987597
      
1.0
      
0.997059
      
0.890605
    
    

      
2017-08-03 11:47:21.624172
      
1.0
      
0.962329
      
1.0
      
0.008174
      
1.0
      
0.993846
      
0.987597
      
1.0
      
0.997059
      
0.866367
    
    

      
2017-08-03 11:47:22.140355
      
1.0
      
0.962329
      
1.0
      
0.318801
      
1.0
      
0.853846
      
0.705426
      
1.0
      
0.997059
      
0.813401
    
  

In [5]:

    

import pickle
#from sklearn.cross_validation import train_test_split
from sklearn import linear_model
from sklearn.svm import SVR
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC


    

In [9]:

    

# saving linear model
df=data.tail(20000)
X=df[['askPrice','askSize','bidPrice','bidSize','vwap','spread','v','return','sigma']]
y=df.mid


    

In [10]:

    

regr = linear_model.LinearRegression()
regr_model=regr.fit(X,y)
# save the model to disk
filename_rgr = 'rgr.sav'
pickle.dump(regr_model, open(filename_rgr, 'wb'))


    

In [11]:

    

svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.9) #kernel='linear' #kernel='poly'
svr_model = svr_rbf.fit(X, y)
# save the model to disk
filename_svr = 'svr.sav'
pickle.dump(svr_model, open(filename_svr, 'wb'))


    

In [12]:

    

##### Model is saved from ML_20SEP


    

In [ ]: