def get_model(PARAMS):
model = XGBClassifier(booster='gbtree',
silent=True,
nthread=None,
random_state=42,
base_score=0.5,
colsample_bylevel=1,
n_estimators=50,
reg_lambda=1,
objective='binary:logistic')
model.max_depth = PARAMS.get("max_depth")
model.min_child_weight = PARAMS.get("min_child_weight")
model.gamma = PARAMS.get("gamma")
model.subsample = PARAMS.get("subsample")
model.colsample_bytree = PARAMS.get("colsample_bytree")
model.reg_alpha = PARAMS.get('reg_alpha')
model.learning_rate = PARAMS.get("learning_rate")
return model
best_clf_ind = bestClassifier(Results)
res = str(Results[best_clf_ind])
print("The best classifier is %s" % res)
# classifier : XGBoost
# First we tried to find the best max_depth parameter
#Here we take many value of n_estimators to generalise
tes_scores = []
depth_range = [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
21, 22, 23, 25, 26, 27, 28, 30, 50, 70, 90, 100
]
clf_test = XGBClassifier(n_estimators=10, silent=False)
for valeur in depth_range:
clf_test.max_depth = valeur
clf_test.fit(X_train2, y_train2)
y_pr = clf_test.predict_proba(X_test2)
tes_scores.append(roc_auc_score(y_test2, y_pr[:, 1]))
tes_scores3 = []
clf_test.n_estimators = 100
for valeur in depth_range:
clf_test.max_depth = valeur
clf_test.fit(X_train2, y_train2)
y_pr = clf_test.predict_proba(X_test2)
tes_scores3.append(roc_auc_score(y_test2, y_pr[:, 1]))
tes_scores2 = []
clf_test.n_estimators = 20
for valeur in depth_range:
