about an error in the multi-task regression

Open

#199 opened on Dec 25, 2023 10 comments 0 reactions 0 assignees View on GitHub

Dominant language: Python
Stars: 1.2k
Forks: 181
PR merge metrics: No merged PRs in 30d

Description

Hi,

Thanks for your wondering work. I am wondering if I could ask some question about the error in the multi-task regression in unimol.

My label of X,Y is like:

_SMILES,TARGET_0,TARGET_1,TARGET_2,TARGET_3,TARGET_4,TARGET_5,TARGET_6,TARGET_7,TARGET_8,TARGET_9,TARGET_10,TARGET_11,TARGET_12,TARGET_13,TARGET_14,TARGET_15,TARGET_16,TARGET_17,TARGET_18,TARGET_19,TARGET_20,TARGET_21,TARGET_22,TARGET_23,TARGET_24,TARGET_25,TARGET_26,TARGET_27,TARGET_28,TARGET_29,TARGET_30,TARGET_31,TARGET_32,TARGET_33,TARGET_34,TARGET_35,TARGET_36,TARGET_37,TARGET_38,TARGET_39,TARGET_40,TARGET_41,TARGET_42,TARGET_43,TARGET_44,TARGET_45,TARGET_46,TARGET_47,TARGET_48,TARGET_49,TARGET_50,TARGET_51,TARGET_52,TARGET_53,TARGET_54,TARGET_55,TARGET_56,TARGET_57,TARGET_58,TARGET_59,TARGET_60,TARGET_61,TARGET_62,TARGET_63,TARGET_64,TARGET_65,TARGET_66,TARGET_67,TARGET_68,TARGET_69,TARGET_70,TARGET_71,TARGET_72,TARGET_73,TARGET_74,TARGET_75,TARGET_76,TARGET_77,TARGET_78,TARGET_79,TARGET_80,TARGET_81,TARGET_82,TARGET_83,TARGET_84,TARGET_85,TARGET_86,TARGET_87,TARGET_88,TARGET_89,TARGET_90,TA_

And there is 140k smiles and 700+labels.
However, when I run the bohruim, the unimol shows that:

but I check my datasets:

I also used to transfer my datasets to the float16 and run the unimol but it is the same result.

I carefully check the output, the training is fine while the validation is not ok.

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/train.py:56, in MolTrain.fit(self, data)
54 self.trainer = Trainer(save_path=self.save_path, **self.config)
55 self.model = NNModel(self.data, self.trainer, **self.config)
---> 56 self.model.run()
57 scalar = self.data['target_scaler']
58 y_pred = self.model.cv['pred']

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/models/nnmodel.py:120, in NNModel.run(self)
117 if fold > 0:
118 # need to initalize model for next fold training
119 self.model = self._init_model(**self.model_params)
--> 120 _y_pred = self.trainer.fit_predict(
121 self.model, traindataset, validdataset, self.loss_func, self.activation_fn, self.save_path, fold, self.target_scaler)
122 y_pred[te_idx] = _y_pred
124 if 'multiclass_cnt' in self.data:

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/tasks/trainer.py:157, in Trainer.fit_predict(self, model, train_dataset, valid_dataset, loss_func, activation_fn, dump_dir, fold, target_scaler, feature_name)
154 batch_bar.close()
155 total_trn_loss = np.mean(trn_loss)
--> 157 y_preds, val_loss, metric_score = self.predict(
158 model, valid_dataset, loss_func, activation_fn, dump_dir, fold, target_scaler, epoch, load_model=False, feature_name=feature_name)
159 end_time = time.time()
160 total_val_loss = np.mean(val_loss)

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/tasks/trainer.py:254, in Trainer.predict(self, model, dataset, loss_func, activation_fn, dump_dir, fold, target_scaler, epoch, load_model, feature_name)
252 inverse_y_preds = target_scaler.inverse_transform(y_preds)
253 inverse_y_truths = target_scaler.inverse_transform(y_truths)
--> 254 metric_score = self.metrics.cal_metric(
255 inverse_y_truths, inverse_y_preds, label_cnt=label_cnt) if not load_model else None
256 else:
257 metric_score = self.metrics.cal_metric(
258 y_truths, y_preds, label_cnt=label_cnt) if not load_model else None

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/utils/metrics.py:197, in Metrics.cal_metric(self, label, predict, nan_value, threshold, label_cnt)
195 def cal_metric(self, label, predict, nan_value=-1.0, threshold=0.5, label_cnt=None):
196 if self.task in ['regression', 'multilabel_regression']:
--> 197 return self.cal_reg_metric(label, predict, nan_value)
198 elif self.task in ['classification', 'multilabel_classification']:
199 return self.cal_classification_metric(label, predict, nan_value)

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/utils/metrics.py:175, in Metrics.cal_reg_metric(self, label, predict, nan_value)
172 metric, _, _ = metric_value
173 def nan_metric(label, predict): return cal_nan_metric(
174 label, predict, nan_value, metric)
--> 175 res_dict[metric_type] = nan_metric(label, predict)
177 return res_dict

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/utils/metrics.py:173, in Metrics.cal_reg_metric..nan_metric(label, predict)
--> 173 def nan_metric(label, predict): return cal_nan_metric(
174 label, predict, nan_value, metric)

File /opt/conda/lib/python3.8/site-packages/unimol-0.0.2-py3.8.egg/unimol/utils/metrics.py:49, in cal_nan_metric(y_true, y_pred, nan_value, metric_func)
47 _mask = mask[:, i]
48 if not (~_mask).all():
---> 49 result.append(metric_func(
50 y_true[:, i][_mask], y_pred[:, i][_mask]))
51 return np.mean(result)

File /opt/conda/lib/python3.8/site-packages/sklearn/utils/validation.py:63, in _deprecate_positional_args.._inner_deprecate_positional_args..inner_f(*args, **kwargs)
61 extra_args = len(args) - len(all_args)
62 if extra_args <= 0:
---> 63 return f(*args, **kwargs)
65 # extra_args > 0
66 args_msg = ['{}={}'.format(name, arg)
67 for name, arg in zip(kwonly_args[:extra_args],
68 args[-extra_args:])]

File /opt/conda/lib/python3.8/site-packages/sklearn/metrics/_regression.py:335, in mean_squared_error(y_true, y_pred, sample_weight, multioutput, squared)
274 @_deprecate_positional_args
275 def mean_squared_error(y_true, y_pred, *,
276 sample_weight=None,
277 multioutput='uniform_average', squared=True):
278 """Mean squared error regression loss.
279
280 Read more in the :ref:`User Guide `.
(...)
333 0.825...
334 """
--> 335 y_type, y_true, y_pred, multioutput = _check_reg_targets(
336 y_true, y_pred, multioutput)
337 check_consistent_length(y_true, y_pred, sample_weight)
338 output_errors = np.average((y_true - y_pred) ** 2, axis=0,
339 weights=sample_weight)

File /opt/conda/lib/python3.8/site-packages/sklearn/metrics/_regression.py:89, in _check_reg_targets(y_true, y_pred, multioutput, dtype)
55 """Check that y_true and y_pred belong to the same regression task.
56
57 Parameters
(...)
86 the dtype argument passed to check_array.
87 """
88 check_consistent_length(y_true, y_pred)
---> 89 y_true = check_array(y_true, ensure_2d=False, dtype=dtype)
90 y_pred = check_array(y_pred, ensure_2d=False, dtype=dtype)
92 if y_true.ndim == 1:

File /opt/conda/lib/python3.8/site-packages/sklearn/utils/validation.py:720, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
716 raise ValueError("Found array with dim %d. %s expected <= 2."
717 % (array.ndim, estimator_name))
719 if force_all_finite:
--> 720 _assert_all_finite(array,
721 allow_nan=force_all_finite == 'allow-nan')
723 if ensure_min_samples > 0:
724 n_samples = _num_samples(array)

File /opt/conda/lib/python3.8/site-packages/sklearn/utils/validation.py:103, in _assert_all_finite(X, allow_nan, msg_dtype)
100 if (allow_nan and np.isinf(X).any() or
101 not allow_nan and not np.isfinite(X).all()):
102 type_err = 'infinity' if allow_nan else 'NaN, infinity'
--> 103 raise ValueError(
104 msg_err.format
105 (type_err,
106 msg_dtype if msg_dtype is not None else X.dtype)
107 )
108 # for object dtype data, we only check for NaNs (GH-13254)
109 elif X.dtype == np.dtype('object') and not allow_nan:

ValueError: Input contains NaN, infinity or a value too large for dtype('float32').`

I am wondering how can I do that I had carefully clean and check my datasets and make sure that it is fine, but I do not know if the unimol can handle such a big datasets.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

about an error in the multi-task regression

Description

Contributor guide

Assessment

Get new issues in your inbox