Shelter Animal Outcomes 6

In [1]:

    

from sklearn.svm import SVC
from sklearn import cross_validation
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.pipeline import make_pipeline
import pandas as pd


    

In [2]:

    

df_train = pd.read_csv('../Shelter_train.csv')
df_test = pd.read_csv('../Shelter_test.csv')


    

In [3]:

    

X = df_train.ix[:, :-1]
y = df_train.ix[:, -1]
df_test = df_test.drop('ID', 1)


    

In [4]:

    

clf = SVC(probability=True)
cross_validation.cross_val_score(clf, X, y, scoring="log_loss")


    

    
Out[4]:





array([-0.99546749, -0.98174512, -0.97886519])

In [5]:

    

%timeit clf.fit(X, y)


    

    




1 loop, best of 3: 3min 48s per loop

In [9]:

    

X_new = SelectKBest(chi2, k=7).fit_transform(X, y)
cross_validation.cross_val_score(clf, X_new, y, scoring="log_loss")


    

    
Out[9]:





array([-0.99748181, -0.98330549, -0.98156068])

In [10]:

    

selector = SelectKBest(chi2, k=7)
predictor = make_pipeline(selector, clf)
predictor.fit(X, y)
predictions = predictor.predict_proba(df_test)
output = pd.DataFrame(predictions, columns=['Adoption', 'Died', 'Euthanasia', 'Return_to_owner', 'Transfer'])
output.index.names = ['ID']
output.index += 1
output.head()


    

    
Out[10]:






  

    

      

      
Adoption
      
Died
      
Euthanasia
      
Return_to_owner
      
Transfer
    
  
  

    

      
1
      
0.017044
      
0.008535
      
0.073380
      
0.114324
      
0.786717
    
    

      
2
      
0.514006
      
0.004215
      
0.036188
      
0.211757
      
0.233833
    
    

      
3
      
0.591613
      
0.006544
      
0.039136
      
0.118934
      
0.243773
    
    

      
4
      
0.108488
      
0.007611
      
0.064966
      
0.378202
      
0.440732
    
    

      
5
      
0.566251
      
0.005415
      
0.035276
      
0.233439
      
0.159619
    
  

In [11]:

    

output.to_csv('../submission-SVC.2.0.csv', index_label = 'ID')