Python XGBClassifier.set_params方法代码示例

# 需要导入模块: from xgboost.sklearn import XGBClassifier [as 别名]
# 或者: from xgboost.sklearn.XGBClassifier import set_params [as 别名]
 def eval_fn(params):
     model = XGBClassifier(n_estimators=n_estimators_max, learning_rate=learning_rate, seed=seed)
     score = 0
     n_estimators = 0
     for tr, va in skf:
         X_tr, y_tr = X_train[tr], y_train[tr]
         X_va, y_va = X_train[va], y_train[va]
         model.set_params(**params)
         model.fit(X_tr, y_tr, eval_set=[(X_va, y_va)], eval_metric='logloss',
                   early_stopping_rounds=50, verbose=False)
         score += model.best_score
         n_estimators += model.best_iteration
     score /= n_folds
     n_estimators /= n_folds
     n_estimators_lst.append(n_estimators)
     result_str = "train:%.4f ntree:%5d  " % (score, n_estimators)
     if X_valid is not None:
         model.n_estimators = n_estimators
         model.fit(X_train, y_train)
         pr = model.predict_proba(X_valid)[:,1]
         sc_valid = log_loss(y_valid, pr)
         score_valid.append(sc_valid)
         result_str += "valid:%.4f" % sc_valid
     if verbose:
         print result_str
     return score

# 需要导入模块: from xgboost.sklearn import XGBClassifier [as 别名]
# 或者: from xgboost.sklearn.XGBClassifier import set_params [as 别名]
def main():
    data_train = pd.read_csv(args.train_dataset)
    X_train = data_train.drop(['Id', 'Class'], axis=1)
    y_train = data_train.loc[:, 'Class']
    data_test = pd.read_csv(args.test_dataset)
    X_test = data_test.drop(['Id'], axis=1)
    Id = data_test.loc[:, 'Id']
    clf = XGBClassifier()
    clf.set_params(**best_dicts)
    clf.fit(X_train, y_train)
    prediction = clf.predict_proba(X_test)
    columns = ['Prediction'+str(i) for i in range(1, 10)]
    prediction = pd.DataFrame(prediction, columns=columns)
    results = pd.concat([Id, prediction], axis=1)
    return (clf, results)

# 需要导入模块: from xgboost.sklearn import XGBClassifier [as 别名]
# 或者: from xgboost.sklearn.XGBClassifier import set_params [as 别名]
train.drop(x, axis=1, inplace=True)
test.drop(x, axis=1, inplace=True)

y_train = train['TARGET'].values
X_train = train.drop(['ID','TARGET'], axis=1).values

y_test = test['ID']
X_test = test.drop(['ID'], axis=1).values

xgb1 = XGBClassifier(
 learning_rate =0.1,
 n_estimators=600,
 max_depth=5,
 min_child_weight=1,
 gamma=0,
 subsample=0.6815,
 colsample_bytree=0.701,
 objective= 'binary:logistic',
 nthread=4,
 scale_pos_weight=1,
 seed=27)

xgtrain = xgb.DMatrix(X_train, label=y_train)
cvresult = xgb.cv(xgb1.get_xgb_params(), xgtrain, num_boost_round=xgb1.get_params()['n_estimators'], nfold=5,
metrics=['auc'], early_stopping_rounds=50, show_progress=False)
xgb1.set_params(n_estimators=cvresult.shape[0])
xgb1.fit(X_train, y_train, eval_metric='auc')
output = xgb1.predict_proba(X_test)[:,1]

submission = pd.DataFrame({"ID":y_test, "TARGET":output})
submission.to_csv("submission.csv", index=False)

# 需要导入模块: from xgboost.sklearn import XGBClassifier [as 别名]
# 或者: from xgboost.sklearn.XGBClassifier import set_params [as 别名]
                                    train_size=n_train, random_state=123)
 for idx, ignore in sss_train:
     X_train = X[train_idx][idx]
     y_train = target[train_idx][idx]
     #
     # 2.
     sss_train_inner = StratifiedShuffleSplit(y_train, n_iter=n_iter_cv, test_size=.1,
                                              random_state=456)
     model = XGBClassifier(n_estimators=1000, max_depth=10, subsample=.8, seed=987)
     params_lst_optimized = []
     for params in xgb_params_lst:
         n_estimators = 0
         for tr, va in sss_train_inner:
             X_tr, y_tr = X_train[tr], y_train[tr]
             X_va, y_va = X_train[va], y_train[va]
             model.set_params(**params)
             model.fit(X_tr, y_tr, eval_set=[(X_va, y_va)], eval_metric="mlogloss",
                       early_stopping_rounds=50, verbose=False)
             n_estimators += model.best_iteration
         sc = params.copy()
         sc.update({'n_estimators':n_estimators / n_iter_cv})
         params_lst_optimized.append(sc)
     print 'Step 2 Done.', datetime.now() - t0
     # 3.
     model = XGBClassifier(max_depth=10, subsample=.8)
     for params in params_lst_optimized:
         for seed_train in range(100, 100+n_iter_pred):
             params.update({'seed':seed_train})
             model.set_params(**params)
             model.fit(X_train, y_train)
             pr = model.predict_proba(X_test)