Shelter Animal Outcomes 5

In [1]:

    

from sklearn.naive_bayes import GaussianNB 
from sklearn import cross_validation
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.grid_search import GridSearchCV
from sklearn.pipeline import Pipeline
from time import time
from operator import itemgetter
import numpy as np
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 = GaussianNB()
cross_validation.cross_val_score(clf, X, y, scoring="log_loss")


    

    
Out[4]:





array([-1.47093332, -1.58296243, -1.46664248])

In [5]:

    

def report(grid_scores, n_top=3):
    top_scores = sorted(grid_scores, key=itemgetter(1), reverse=True)[:n_top]
    for i, score in enumerate(top_scores):
        print("Model with rank: {0}".format(i + 1))
        print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
              score.mean_validation_score,
              np.std(score.cv_validation_scores)))
        print("Parameters: {0}".format(score.parameters))
        print("")


    

In [6]:

    

params = {
    "featureSelection__k" : [2, 3, 4, 5, 6, 7, 8]
    }


    

In [7]:

    

pipeline = Pipeline([
        ('featureSelection', SelectKBest(f_classif)),
        ('clf', GaussianNB())
    ])
grid_search = GridSearchCV(pipeline, params, n_jobs=-1, scoring='log_loss')
start = time()
grid_search.fit(X, y)
print("GridSearchCV took %.2f seconds for %d candidate parameter settings."
      % (time() - start, len(grid_search.grid_scores_)))
report(grid_search.grid_scores_)
predictions = grid_search.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()


    

    




GridSearchCV took 0.59 seconds for 7 candidate parameter settings.
Model with rank: 1
Mean validation score: -1.068 (std: 0.004)
Parameters: {'featureSelection__k': 2}

Model with rank: 2
Mean validation score: -1.075 (std: 0.008)
Parameters: {'featureSelection__k': 3}

Model with rank: 3
Mean validation score: -1.118 (std: 0.010)
Parameters: {'featureSelection__k': 4}







    
Out[7]:






  

    

      

      
Adoption
      
Died
      
Euthanasia
      
Return_to_owner
      
Transfer
    
  
  

    

      
1
      
0.002450
      
0.016726
      
0.115034
      
0.093750
      
0.772040
    
    

      
2
      
0.622077
      
0.001029
      
0.017173
      
0.249382
      
0.110339
    
    

      
3
      
0.646979
      
0.001344
      
0.026792
      
0.175275
      
0.149610
    
    

      
4
      
0.129043
      
0.010029
      
0.082384
      
0.293138
      
0.485407
    
    

      
5
      
0.647427
      
0.000379
      
0.010397
      
0.276589
      
0.065208
    
  

In [8]:

    

output.to_csv('../submission-GaussianNB.3.0.csv', index_label = 'ID')