seed = 47
n = 100
n_split = 50
reg = GradientBoostingRegressor(n_estimators=n, min_samples_split=n_split, learning_rate=0.5, random_state=seed)
regs = []
for i in (10, 10, 10, 5):
r = clone(reg)
r.min_sample_split = i
regs.append(r)
clf = GradientBoostingClassifier(n_estimators=500, min_samples_split=5, learning_rate=0.5, random_state=seed)
stacked = StackedClassiferRegressor(clf, regs=regs)
# get bins and labels
bins, labels = HazardBins(3)
# trained the stacked classifier & regressor
start_time = time.time()
stacked.fit(train[columns], train["Hazard"], bins, labels)
stop_time = time.time()
print "training time: %.2fs" % (stop_time - start_time)
haz_pred = stacked.predict(train[columns])
train_gini = Gini(haz_pred, train.Hazard)
print "Gini (training):", train_gini
# print 'Importances: ', clf.feature_importances_
#reg = GradientBoostingRegressor(n_estimators = n,
# min_samples_split = n_split,
# learning_rate = 0.5,
# random_state = seed)
#regs = []
#for i in (10, 10, 10, 5):
# r = clone(reg)
# r.min_sample_split = i
# regs.append(r)
clf = xgb.XGBClassifier(max_depth=5, n_estimators=n, silent=False,
learning_rate=0.3, gamma = 0, seed=seed)
stacked = StackedClassiferRegressor(clf, gbm)
# get bins and labels
bins, labels = HazardBins(3)
#labels = range(len(bins)-1)
# trained the stacked classifier & regressor
start_time = time.time()
stacked.fit(train[columns].as_matrix(), train['Hazard'].as_matrix(), bins, labels)
stop_time = time.time()
print "training time: %.2fs" % (stop_time - start_time)
haz_pred = stacked.predict(train[columns].as_matrix())
train_gini = Gini(haz_pred, train.Hazard)
print 'Gini (training):', train_gini
#print 'Importances: ', clf.feature_importances_
