Recursive feature elimination on Random Forest using scikit-learn

Question

I\'m trying to preform recursive feature elimination using scikit-learn and a random forest classifier, with OOB ROC as the method of scoring each subset create

Answer 1

Here's what I ginned up. It's a pretty simple solution, and relies on a custom accuracy metric (called weightedAccuracy) since I'm classifying a highly unbalanced dataset. But, it should be easily made more extensible if desired.

from sklearn import datasets
import pandas
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
from sklearn.metrics import confusion_matrix


def get_enhanced_confusion_matrix(actuals, predictions, labels):
    """"enhances confusion_matrix by adding sensivity and specificity metrics"""
    cm = confusion_matrix(actuals, predictions, labels = labels)
    sensitivity = float(cm[1][1]) / float(cm[1][0]+cm[1][1])
    specificity = float(cm[0][0]) / float(cm[0][0]+cm[0][1])
    weightedAccuracy = (sensitivity * 0.9) + (specificity * 0.1)
    return cm, sensitivity, specificity, weightedAccuracy

iris = datasets.load_iris()
x=pandas.DataFrame(iris.data, columns=['var1','var2','var3', 'var4'])
y=pandas.Series(iris.target, name='target')

response, _  = pandas.factorize(y)

xTrain, xTest, yTrain, yTest = cross_validation.train_test_split(x, response, test_size = .25, random_state = 36583)
print "building the first forest"
rf = RandomForestClassifier(n_estimators = 500, min_samples_split = 2, n_jobs = -1, verbose = 1)
rf.fit(xTrain, yTrain)
importances = pandas.DataFrame({'name':x.columns,'imp':rf.feature_importances_
                                }).sort(['imp'], ascending = False).reset_index(drop = True)

cm, sensitivity, specificity, weightedAccuracy = get_enhanced_confusion_matrix(yTest, rf.predict(xTest), [0,1])
numFeatures = len(x.columns)

rfeMatrix = pandas.DataFrame({'numFeatures':[numFeatures], 
                              'weightedAccuracy':[weightedAccuracy], 
                              'sensitivity':[sensitivity], 
                              'specificity':[specificity]})

print "running RFE on  %d features"%numFeatures

for i in range(1,numFeatures,1):
    varsUsed = importances['name'][0:i]
    print "now using %d of %s features"%(len(varsUsed), numFeatures)
    xTrain, xTest, yTrain, yTest = cross_validation.train_test_split(x[varsUsed], response, test_size = .25)
    rf = RandomForestClassifier(n_estimators = 500, min_samples_split = 2,
                                n_jobs = -1, verbose = 1)
    rf.fit(xTrain, yTrain)
    cm, sensitivity, specificity, weightedAccuracy = get_enhanced_confusion_matrix(yTest, rf.predict(xTest), [0,1])
    print("\n"+str(cm))
    print('the sensitivity is %d percent'%(sensitivity * 100))
    print('the specificity is %d percent'%(specificity * 100))
    print('the weighted accuracy is %d percent'%(weightedAccuracy * 100))
    rfeMatrix = rfeMatrix.append(
                                pandas.DataFrame({'numFeatures':[len(varsUsed)], 
                                'weightedAccuracy':[weightedAccuracy], 
                                'sensitivity':[sensitivity], 
                                'specificity':[specificity]}), ignore_index = True)    
print("\n"+str(rfeMatrix))    
maxAccuracy = rfeMatrix.weightedAccuracy.max()
maxAccuracyFeatures = min(rfeMatrix.numFeatures[rfeMatrix.weightedAccuracy == maxAccuracy])
featuresUsed = importances['name'][0:maxAccuracyFeatures].tolist()

print "the final features used are %s"%featuresUsed