房租赛-模型测试

params = {
   
    'num_leaves': 31,
    'min_data_in_leaf': 20,
    'min_child_samples':20,
    'objective': 'regression',
    'learning_rate': 0.01,
    "boosting": "gbdt",
    "feature_fraction": 0.8,
    "bagging_freq": 1,
    "bagging_fraction": 0.85,
    "bagging_seed": 23,
    "metric": 'rmse',
    "lambda_l1": 0.2,
    "nthread": 4,
}
folds = KFold(n_splits=5, shuffle=True, random_state=2333)

oof_lgb = np.zeros(len(train))
predictions_lgb = np.zeros(len(test))
feature_importance_df = pd.DataFrame()

for fold_, (trn_idx, val_idx) in enumerate(folds.split(train.values, target.values)):
    print("fold {}".format(fold_))
    trn_data = lgb.Dataset(train.iloc[trn_idx], label=target.iloc[trn_idx], categorical_feature=categorical_feats)
    val_data = lgb.Dataset(train.iloc[val_idx], label=target.iloc[val_idx], categorical_feature=categorical_feats)

    num_round = 10000
    clf = lgb.train(params, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=500, early_stopping_rounds = 200)
    
    oof_lgb[val_idx] = clf.predict(train.iloc[val_idx], num_iteration=clf.best_iteration)
    
    fold_importance_df = pd.DataFrame()
    fold_importance_df["feature"] = features
    fold_importance_df["importance"] = clf.feature_importance()
    fold_importance_df["fold"] = fold_ + 1
    feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)
    
    predictions_lgb += clf.predict(test, num_iteration=clf.best_iteration) / folds.n_splits
    
print("CV Score: {:<8.5f}".format(r2_score(target, oof_lgb)))
fold 0
Training until validation scores don't improve for 200 rounds.

D:\app\anacode\anaconda\lib\site-packages\lightgbm\basic.py:1184: UserWarning: Using categorical_feature in Dataset.
  warnings.warn('Using categorical_feature in Dataset.')
D:\app\anacode\anaconda\lib\site-packages\lightgbm\basic.py:742: UserWarning: categorical_feature in param dict is overridden.
  warnings.warn('categorical_feature in param dict is overridden.')

[500]	training's rmse: 810.06	valid_1's rmse: 928.603
[1000]	training's rmse: 712.357	valid_1's rmse: 907.149
[1500]	training's rmse: 659.304	valid_1's rmse: 903.82
Early stopping, best iteration is:
[1542]	training's rmse: 655.892	valid_1's rmse: 903.404
fold 1
Training until validation scores don't improve for 200 rounds.

D:\app\anacode\anaconda\lib\site-packages\lightgbm\basic.py:1184: UserWarning: Using categorical_feature in Dataset.
  warnings.warn('Using categorical_feature in Dataset.')
D:\app\anacode\anaconda\lib\site-packages\lightgbm\basic.py:742: UserWarning: categorical_feature in param dict is overridden.
  warnings.warn('categorical_feature in param dict is overridden.')