I get this error when I try to run a CatBoost algorithm. It is one of the parameters so I don't understand why this error occurs when I comment out early_stopping_rounds I get the same error for cat_features parameter
from catboost import CatBoostClassifier
categorical_indexes = np.where(X.dtypes == 'object')[0]
X.drop(["id"], axis = 1, inplace = True)
params = {'loss_function':'Logloss',
'eval_metric':'AUC',
'verbose': 200,
"early_stopping_rounds": 200,
"cat_features": categorical_indexes,
'random_seed': 17}
cat = CatBoostClassifier(**params)
cat.fit(X,y)
Edit:
Upgraded catboost package via pip now I am getting another error
However, in my code I'm filtering categorical values then assigning to them to cat_features parameter
TypeError Traceback (most recent call last)
_catboost.pyx in _catboost.get_float_feature()
_catboost.pyx in _catboost._FloatOrNan()
_catboost.pyx in _catboost._FloatOrNanFromString()
TypeError: Cannot convert 'b'Triangle'' to float
During handling of the above exception, another exception occurred:
CatBoostError Traceback (most recent call last)
<ipython-input-13-1190699fd260> in <module>
74
75 cat = CatBoostClassifier(loss_function='Logloss', eval_metric='AUC', verbose=200, early_stopping_rounds=200, cat_features=np.array([ 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20]), random_seed=17)
---> 76 cat.fit(X,y)
77
78
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in fit(self, X, y, cat_features, text_features, sample_weight, baseline, use_best_model, eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period, silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
3786 self._fit(X, y, cat_features, text_features, None, sample_weight, None, None, None, None, baseline, use_best_model,
3787 eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period,
-> 3788 silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
3789 return self
3790
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in _fit(self, X, y, cat_features, text_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, use_best_model, eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period, silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
1670 use_best_model, eval_set, verbose, logging_level, plot,
1671 column_description, verbose_eval, metric_period, silent, early_stopping_rounds,
-> 1672 save_snapshot, snapshot_file, snapshot_interval, init_model
1673 )
1674 params = train_params["params"]
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in _prepare_train_params(self, X, y, cat_features, text_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, use_best_model, eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period, silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
1558
1559 train_pool = _build_train_pool(X, y, cat_features, text_features, pairs, sample_weight, group_id,
-> 1560 group_weight, subgroup_id, pairs_weight, baseline, column_description)
1561 if train_pool.is_empty_:
1562 raise CatBoostError("X is empty.")
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in _build_train_pool(X, y, cat_features, text_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, column_description)
968 raise CatBoostError("y has not initialized in fit(): X is not catboost.Pool object, y must be not None in fit().")
969 train_pool = Pool(X, y, cat_features=cat_features, text_features=text_features, pairs=pairs, weight=sample_weight, group_id=group_id,
--> 970 group_weight=group_weight, subgroup_id=subgroup_id, pairs_weight=pairs_weight, baseline=baseline)
971 return train_pool
972
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in __init__(self, data, label, cat_features, text_features, column_description, pairs, delimiter, has_header, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names, thread_count)
369 )
370
--> 371 self._init(data, label, cat_features, text_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
372 super(Pool, self).__init__()
373
c:\users\m\appdata\local\programs\python\python37\lib\site-packages\catboost\core.py in _init(self, data, label, cat_features, text_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
949 baseline = np.reshape(baseline, (samples_count, -1))
950 self._check_baseline_shape(baseline, samples_count)
--> 951 self._init_pool(data, label, cat_features, text_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
952
953
_catboost.pyx in _catboost._PoolBase._init_pool()
_catboost.pyx in _catboost._PoolBase._init_pool()
_catboost.pyx in _catboost._PoolBase._init_features_order_layout_pool()
_catboost.pyx in _catboost._set_features_order_data_pd_data_frame()
_catboost.pyx in _catboost.create_num_factor_data()
_catboost.pyx in _catboost.get_float_feature()
CatBoostError: Bad value for num_feature[non_default_doc_idx=0,feature_idx=5]="Triangle": Cannot convert 'b'Triangle'' to float
It seems you missed to specify the feature index or feature name for the categorical feature at "feature_idx=5" with value “Triangle”. Catboost tried to convert that binary string value to float
and got the CatBoostError
.
You can update that categorical feature indice or name to your variable categorical_indexes
when you construct the class CatBoostClassifier
, or you can provide the list of categorical feature indices or names to argument cat_features
of fit()
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With