File size: 1,598 Bytes
101ad9a
 
 
 
0fa8793
 
101ad9a
 
 
 
 
 
 
 
 
aae7167
0fa8793
 
 
 
aae7167
0fa8793
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
from typing import Optional, Union, Callable
from dataclasses import dataclass
from datasets import Dataset

from evaluate.evaluation_suite import EvaluationSuite

@dataclass
class SubTask:
    model_or_pipeline: Optional[Union[str, "Pipeline", Callable, "PreTrainedModel", "TFPreTrainedModel"]] = None
    data: Optional[Union[str, Dataset]] = None
    subset: Optional[str] = None
    split: Optional[str] = None
    data_preprocessor: Optional[Callable] = None,
    args_for_task: Optional[dict] = None


class EvaluationSuite:

    def __init__(self):
        self.preprocessor = None #lambda x: x["text"].lower()

        self.suite = [
            SubTask(
                data="imdb",
                split="test",
                data_preprocessor=self.preprocessor,
                args_for_task={
                    "metric": "accuracy",
                    "input_column": "text",
                    "label_column": "label",
                    "label_mapping": {
                        "LABEL_0": 0.0,
                        "LABEL_1": 1.0
                    }
                }
            ),
            SubTask(
                data="sst2",
                split="test[:10]",
                data_preprocessor=self.preprocessor,
                args_for_task={
                    "metric": "accuracy",
                    "input_column": "sentence",
                    "label_column": "label",
                    "label_mapping": {
                        "LABEL_0": 0.0,
                        "LABEL_1": 1.0
                    }
                }
            )
        ]