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 [23]:

    

df = pd.DataFrame()
# 0.75037
df['rf'] = pd.read_csv('../submissions/140926-predict.2.csv', index_col='clip', squeeze=True)
w_rf = 0.8
# 0.68846
df['rf1'] = pd.read_csv('../submissions/141029-predict.4.csv', index_col='clip', squeeze=True)
w_rf1 = 0.3

# 0.73188
df['gb'] = pd.read_csv('../submissions/140928-predict.1.csv', index_col='clip', squeeze=True)
w_gb  = 0.65

# 0.71603
df['dbn'] = pd.read_csv('../submissions/140930-predict.5.csv', index_col='clip', squeeze=True)
w_dbn = 0.45

# 0.71358
df['rfpca'] = pd.read_csv('../submissions/141001-predict.1.csv', index_col='clip', squeeze=True)
w_rfpca = 0.4

# 0.70404
df['rfica'] = pd.read_csv('../submissions/141022-predict.3.csv', index_col='clip', squeeze=True)
w_rfica = 0.35

# 0.80999
df['best'] = pd.read_csv('../submissions/141005-predict.2.csv', index_col='clip', squeeze=True)


    

In [24]:

    

pd.scatter_matrix(df[['gb','rf','rf1','rfpca','rfica','dbn','best']],figsize=(6, 6), diagonal='kde');


    

In [25]:

    

s = w_gb + w_rf + w_rf1 + w_rfpca + w_rfica + w_dbn

w_gb /= s
w_rf /= s
w_rf1 /= s
w_rfpca /= s
w_rfica /= s
w_dbn /= s


    

In [26]:

    

w_gb, w_rf, w_rf1, w_rfpca, w_rfica, w_dbn


    

    
Out[26]:





(0.22033898305084743,
 0.27118644067796605,
 0.10169491525423727,
 0.13559322033898302,
 0.11864406779661013,
 0.15254237288135591)

In [27]:

    

df['preictal'] = w_gb * df['gb'] + w_rf * df['rf'] + w_rf1 * df['rf1'] + w_rfpca * df['rfpca'] + w_rfica * df['rfica'] + w_dbn * df['dbn']


    

In [28]:

    

df['preictal'].to_csv('../submissions/141029-predict.5.csv', header=True)


    

In [29]:

    

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


    

In [8]: