ValueError: Input data must be 2 dimensional and non empty

在做点击率预估GBDT+LR模型时，使用lightgbm训练时，报错

# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, label = y_train)
lgb_eval = lgb.Dataset(X_test, label = y_test)

params = {
    'task': 'train',
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'metric': {'binary_logloss'},
    'num_leaves': 64,
    'num_trees': 100,
    'learning_rate': 0.01,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
}

# number of leaves,will be used in feature transformation
num_leaf = 64

print('Start training...')
# train
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=100,
                valid_sets=lgb_train)

有如下报错

ValueError                                Traceback (most recent call last)
 in ()
     25                 lgb_train,
     26                 num_boost_round=100,
---> 27                 valid_sets=lgb_train)

~/anaconda3/lib/python3.7/site-packages/lightgbm/engine.py in train(params, train_set, num_boost_round, valid_sets, valid_names, fobj, feval, init_model, feature_name, categorical_feature, early_stopping_rounds, evals_result, verbose_eval, learning_rates, keep_training_booster, callbacks)
    269     # construct booster
    270     try:
--> 271         booster = Booster(params=params, train_set=train_set)
    272         if is_valid_contain_train:
    273             booster.set_train_data_name(train_data_name)

~/anaconda3/lib/python3.7/site-packages/lightgbm/basic.py in __init__(self, params, train_set, model_file, model_str, silent)
   2603                 )
   2604             # construct booster object
-> 2605             train_set.construct()
   2606             # copy the parameters from train_set
   2607             params.update(train_set.get_params())

~/anaconda3/lib/python3.7/site-packages/lightgbm/basic.py in construct(self)
   1817                                 init_score=self.init_score, predictor=self._predictor,
   1818                                 silent=self.silent, feature_name=self.feature_name,
-> 1819                                 categorical_feature=self.categorical_feature, params=self.params)
   1820             if self.free_raw_data:
   1821                 self.data = None

~/anaconda3/lib/python3.7/site-packages/lightgbm/basic.py in _lazy_init(self, data, label, reference, weight, group, init_score, predictor, silent, feature_name, categorical_feature, params)
   1475                                                                                              feature_name,
   1476                                                                                              categorical_feature,
-> 1477                                                                                              self.pandas_categorical)
   1478         label = _label_from_pandas(label)
   1479 

~/anaconda3/lib/python3.7/site-packages/lightgbm/basic.py in _data_from_pandas(data, feature_name, categorical_feature, pandas_categorical)
    564     if isinstance(data, pd_Dataframe):
    565         if len(data.shape) != 2 or data.shape[0] < 1:
--> 566             raise ValueError('Input data must be 2 dimensional and non empty.')
    567         if feature_name == 'auto' or feature_name is None:
    568             data = data.rename(columns=str)

ValueError: Input data must be 2 dimensional and non empty.

报错字面的意思就是“输入数据必须是二维且非空的”，于是检查我的X_train和y_train，发现X_train是二维的，而y_train是 pandas.core.series.Series
ok，fine。。。是我切分数据集的时候的锅

X = df[cols_all[1:]]  # training dataset
# label encode
lbl = preprocessing.LabelEncoder()
X['site_domain'] = lbl.fit_transform(X['site_domain'].astype(str))#将提示的包含错误数据类型这一列进行转换
X['site_id'] = lbl.fit_transform(X['site_id'].astype(str))
X['site_category'] = lbl.fit_transform(X['site_category'].astype(str))
X['app_id'] = lbl.fit_transform(X['app_id'].astype(str))
X['app_category'] = lbl.fit_transform(X['app_category'].astype(str))
X_train = X.iloc[:-2000]
X_test = X.iloc[-2000:]  # testing dataset

y = df['click']  
y_train = y.iloc[:-2000] # training label
y_test = y.iloc[-2000:]  # testing label

1、不要用这种方式拆分数据集

x = data.iloc[:, 2:]
y = data.loc['Survived']
# 使用train_test_split函数划分数据集(训练集占75%，测试集占25%)
x_train, x_test, y_train，y_test = train_test_split(x, y, test_size=0.25, ramdon_state=0)

2、如果已经使用，那么再将pandas.core.series.Series转化为dataframe吧

y_train.to_frame()

tip：这种方法不能将index一起转换，如果需要转化index的话，那就

ok,fine