我的数据集具有超过100k的观测值和120个特征。我想将XGBoost和Dask Gridsearchcv一起使用来找到最佳参数。但是它引发了错误。请让我知道我在做什么错了

code：import dask_ml.model_selection as dcv

import dask.dataframe as dd

pipe1=Pipeline(steps=[('clf',XGBClassifier(objective= 'binary:logistic'))])

search_space=[{'clf__n_estimators': [100,150, 200, 300],

'clf__max_depth': [4,6,9],

'clf__learning_rate': [0.1, 0.01, 0.05],

'clf__random_state': [0],

'clf__subsample': [0.7,0.9,1],

'clf__colsamplebytree': [1.0, 0.9, 0.8]}]

grid_cpu=dcv.GridSearchCV(estimator=pipe1, param_grid=search_space, cv=5, scoring='roc_auc', return_train_score=True, n_jobs=-1,refit="AUC",scheduler='threads')

grid_cpu.fit(dd.from_pandas(X,npartitions=1), dd.from_pandas(y,npartitions=1))

print("Best parameters found: ",grid_mse.best_params_)

print("Best ROC found: ", np.sqrt(np.abs(grid_mse.best_score_)))

这里使用的X和y最初是一个pandas数据框。我试图在建模之前将其转换为dask数据框。我猜测那是我在那儿缺少的东西。

错误：AssertionError Traceback (most recent call last)

in

13 grid_cpu=dcv.GridSearchCV(estimator=pipe1, param_grid=search_space, cv=5, scoring='roc_auc', return_train_score=True, n_jobs=-1,

14 refit="AUC",scheduler='threads')

---> 15 grid_cpu.fit(dd.from_pandas(X,npartitions=1), dd.from_pandas(y,npartitions=1))

16 print("Best parameters found: ",grid_mse.best_params_)

17 print("Best ROC found: ", np.sqrt(np.abs(grid_mse.best_score_)))

~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask_ml\model_selection\_search.py in fit(self, X, y, groups, **fit_params)

1231 error_score=error_score,

1232 return_train_score=self.return_train_score,

-> 1233 cache_cv=self.cache_cv,

1234 )

1235

~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask_ml\model_selection\_search.py in build_cv_graph(estimator, cv, scorer, candidate_params, X, y, groups, fit_params, iid, error_score, return_train_score, cache_cv)

201

202 dsk = {}

--> 203 X_name, y_name, groups_name = to_keys(dsk, X, y, groups)

204 n_splits = compute_n_splits(cv, X, y, groups)

205

~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask_ml\model_selection\utils.py in to_keys(dsk, *args)

85 yield x.key

86 else:

---> 87 assert not is_dask_collection(x)

88 key = "array-" + tokenize(x)

89 dsk[key] = x

AssertionError: