In [56]:

    

%matplotlib inline
from __future__ import absolute_import
from __future__ import print_function


    

In [63]:

    

import pandas as pd
import numpy as np

from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
from sklearn.svm import SVC


    

In [2]:

    

df = pd.read_csv("../data/Springleaf/train.csv")


    

    




/Library/Python/2.7/site-packages/pandas/io/parsers.py:1170: DtypeWarning: Columns (8,9,10,11,12,43,157,196,214,225,228,229,231,235,238) have mixed types. Specify dtype option on import or set low_memory=False.
  data = self._reader.read(nrows)

In [76]:

    

df_one = df[(df.target==1)][:5000]
df_zero = df[(df.target==0)][:5000]


    

In [77]:

    

df_reduced = df_one.append(df_zero)

df_tmp = df_reduced[["VAR_0002","VAR_0003","VAR_0004","VAR_0006","VAR_0007","target"]].dropna()

df_train =df_tmp.values


    

In [79]:

    

df_train.size


    

    
Out[79]:





59982

In [80]:

    

np.random.shuffle(df_train)

X = df_train[:,:4]
Y = df_train[:,5]

model = RandomForestClassifier(n_estimators =100)
scores = cross_validation.cross_val_score(model, X, Y, cv=5)


    

In [84]:

    

print (scores)
print (scores.mean())


    

    




[ 0.582       0.596       0.59129565  0.58229115  0.5877939 ]
0.587876138069

In [82]:

    

model_svm= SVC()
cross_validation.cross_val_score(model_svm, X, Y, cv=5)


    

    
Out[82]:





array([ 0.503     ,  0.5045    ,  0.50425213,  0.50575288,  0.51825913])

In [ ]: