Shelter Animal Outcomes 4

In [1]:

    

from sklearn.linear_model import LogisticRegression
from sklearn import cross_validation
from sklearn.feature_selection import RFECV
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 = LogisticRegression()
cross_validation.cross_val_score(clf, X, y, scoring="log_loss")


    

    
Out[4]:





array([-1.02051202, -1.01842145, -1.02075702])

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]:

    

pipeline = Pipeline([
        ('featureSelection', RFECV(estimator=LogisticRegression(), scoring='log_loss')),
        ('clf', LogisticRegression())
    ])
pipeline.fit(X, y)
params = {
    'clf__C': [1, 3, 10, 30, 100, 300, 1000]
}
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 41.07 seconds for 7 candidate parameter settings.
Model with rank: 1
Mean validation score: -1.020 (std: 0.001)
Parameters: {'clf__C': 10}

Model with rank: 2
Mean validation score: -1.020 (std: 0.001)
Parameters: {'clf__C': 30}

Model with rank: 3
Mean validation score: -1.020 (std: 0.001)
Parameters: {'clf__C': 100}







    
Out[6]:






  

    

      

      
Adoption
      
Died
      
Euthanasia
      
Return_to_owner
      
Transfer
    
  
  

    

      
1
      
0.092272
      
0.006857
      
0.054737
      
0.248775
      
0.597359
    
    

      
2
      
0.446318
      
0.002682
      
0.055541
      
0.334910
      
0.160550
    
    

      
3
      
0.675391
      
0.004771
      
0.030689
      
0.048345
      
0.240804
    
    

      
4
      
0.243726
      
0.005215
      
0.062152
      
0.254290
      
0.434617
    
    

      
5
      
0.586253
      
0.001345
      
0.019162
      
0.309073
      
0.084166
    
  

In [6]:

    

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