In [2]:

    

%matplotlib inline
from matplotlib import pylab as pl
import cPickle as pickle
import pandas as pd
import numpy as np
import os


    

In [30]:

    

df = pd.DataFrame()
df['gb'] = pd.read_csv('../submissions/140928-predict.1.csv', index_col='clip', squeeze=True) #64
df['rf'] = pd.read_csv('../submissions/140926-predict.2.csv', index_col='clip', squeeze=True)
df['dbn'] = pd.read_csv('../submissions/140930-predict.5.csv', index_col='clip', squeeze=True)
df['best'] = pd.read_csv('../submissions/140928-predict.2.csv', index_col='clip', squeeze=True)


    

In [31]:

    

pd.scatter_matrix(df[['gb','rf','dbn','best']],figsize=(6, 6), diagonal='kde');


    

In [32]:

    

w_gb  = 0.4
w_rf = 1
w_dbn = 0.6

s = w_gb + w_rf + w_dbn

w_gb /= s
w_rf /= s
w_dbn /= s


    

In [33]:

    

w_gb, w_rf, w_dbn


    

    
Out[33]:





(0.2, 0.5, 0.3)

In [34]:

    

df['preictal'] = w_gb * df['gb'] + w_rf * df['rf'] + w_dbn * df['dbn']


    

In [39]:

    

df['preictal'].to_csv('../submissions/140930-predict.9.csv', header=True)


    

In [37]:

    

!head ../submissions/140930-predict.3.csv


    

    




clip,preictal
Dog_1_test_segment_0001.mat,0.399916666666667
Dog_1_test_segment_0002.mat,0.118000000000000
Dog_1_test_segment_0003.mat,0.121333333333333
Dog_1_test_segment_0004.mat,0.235666666666667
Dog_1_test_segment_0005.mat,0.147000000000000
Dog_1_test_segment_0006.mat,0.269329268292683
Dog_1_test_segment_0007.mat,0.047333333333333
Dog_1_test_segment_0008.mat,0.272000000000000
Dog_1_test_segment_0009.mat,0.085000000000000

In [38]:

    

pd.scatter_matrix(df[['best','preictal']])


    

    
Out[38]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x1154e6b50>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x113195150>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x11814f810>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x117988090>]], dtype=object)






    

In [ ]: