Create validation data align with current Dataset. Parameters ---------- data : string, numpy array, pandas DataFrame, H2O DataTable's Frame, scipy.sparse or list of numpy arrays Data source of Dataset. If string, it represents the path to txt file.
(self, data, label=None, weight=None, group=None,
init_score=None, silent=False, params=None)
| 1094 | return self |
| 1095 | |
| 1096 | def create_valid(self, data, label=None, weight=None, group=None, |
| 1097 | init_score=None, silent=False, params=None): |
| 1098 | """Create validation data align with current Dataset. |
| 1099 | |
| 1100 | Parameters |
| 1101 | ---------- |
| 1102 | data : string, numpy array, pandas DataFrame, H2O DataTable's Frame, scipy.sparse or list of numpy arrays |
| 1103 | Data source of Dataset. |
| 1104 | If string, it represents the path to txt file. |
| 1105 | label : list, numpy 1-D array, pandas Series / one-column DataFrame or None, optional (default=None) |
| 1106 | Label of the data. |
| 1107 | weight : list, numpy 1-D array, pandas Series or None, optional (default=None) |
| 1108 | Weight for each instance. |
| 1109 | group : list, numpy 1-D array, pandas Series or None, optional (default=None) |
| 1110 | Group/query size for Dataset. |
| 1111 | init_score : list, numpy 1-D array, pandas Series or None, optional (default=None) |
| 1112 | Init score for Dataset. |
| 1113 | silent : bool, optional (default=False) |
| 1114 | Whether to print messages during construction. |
| 1115 | params : dict or None, optional (default=None) |
| 1116 | Other parameters for validation Dataset. |
| 1117 | |
| 1118 | Returns |
| 1119 | ------- |
| 1120 | valid : Dataset |
| 1121 | Validation Dataset with reference to self. |
| 1122 | """ |
| 1123 | ret = Dataset(data, label=label, reference=self, |
| 1124 | weight=weight, group=group, init_score=init_score, |
| 1125 | silent=silent, params=params, free_raw_data=self.free_raw_data) |
| 1126 | ret._predictor = self._predictor |
| 1127 | ret.pandas_categorical = self.pandas_categorical |
| 1128 | return ret |
| 1129 | |
| 1130 | def subset(self, used_indices, params=None): |
| 1131 | """Get subset of current Dataset. |