KDDocClassificationDataHandler.Config¶
Component: KDDocClassificationDataHandler
-
class
KDDocClassificationDataHandler.
Config
[source] Bases:
DocClassificationDataHandler.Config
Configuration class for KDDocClassificationDataHandler.
-
columns_to_read
¶ List[str] – List containing the names of the columns to read from the data files.
-
max_seq_len
¶ int – Maximum sequence length for the input. The input is trimmed after the maximum sequence length.
-
All Attributes (including base classes)
- columns_to_read: List[str] =
['doc_label', 'text', 'dict_feat', 'target_probs', 'target_labels']
- shuffle: bool =
True
- sort_within_batch: bool =
True
- train_path: str =
'train.tsv'
- eval_path: str =
'eval.tsv'
- test_path: str =
'test.tsv'
- train_batch_size: int =
128
- eval_batch_size: int =
128
- test_batch_size: int =
128
- max_seq_len: int =
-1
Default JSON
{
"columns_to_read": [
"doc_label",
"text",
"dict_feat",
"target_probs",
"target_labels"
],
"shuffle": true,
"sort_within_batch": true,
"train_path": "train.tsv",
"eval_path": "eval.tsv",
"test_path": "test.tsv",
"train_batch_size": 128,
"eval_batch_size": 128,
"test_batch_size": 128,
"max_seq_len": -1
}