xgboost_wrapper.py

 
import sys
import math
 
import numpy as np


code_path = "/afs/cern.ch/user/j/jpavezse/systematics/xgboost/wrapper/"
sys.path.append(code_path)


import xgboost as xgb
import pdb
 
def logloss(y_true, Y_pred):
    return -1 * sum(math.log(y[int(label)]) if y[int(label)] > 0 else -np.inf for y, label in zip(Y_pred, y_true)) / len(Y_pred) 

class XGBoostClassifier():
    def __init__(self, num_boost_round=10, **params):
        self.clf = None
        self.num_boost_round = num_boost_round
        self.params = params
        self.params.update({'objective': 'multi:softprob'})
 
    def fit(self, X, y, num_boost_round=None):
        num_boost_round = num_boost_round or self.num_boost_round
        dtrain = xgb.DMatrix(X, label=y)
        self.clf = xgb.train(params=self.params, dtrain=dtrain, num_boost_round=num_boost_round)
 
    def predict(self, X):
        Y = self.predict_proba(X)
        y = np.argmax(Y, axis=1)
        return np.array(y)
 
    def predict_proba(self, X):
        dtest = xgb.DMatrix(X)
        return self.clf.predict(dtest)
 
    def score(self, X, y):
        Y = self.predict_proba(X)
        return 1 / logloss(y, Y)
 
    def get_params(self, deep=True):
        return self.params
 
    def set_params(self, **params):
        if 'num_boost_round' in params:
            self.num_boost_round = params.pop('num_boost_round')
        if 'objective' in params:
            del params['objective']
        self.params.update(params)
        return self