Spaces:
Running
Running
Update Space (evaluate main: e51c679b)
Browse files- README.md +53 -6
- app.py +6 -0
- exact_match.py +65 -0
- requirements.txt +4 -0
README.md
CHANGED
@@ -1,12 +1,59 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 3.0.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
title: Exact Match
|
3 |
+
emoji: 🤗
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: green
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.0.2
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
+
tags:
|
11 |
+
- evaluate
|
12 |
+
- comparison
|
13 |
---
|
14 |
|
15 |
+
|
16 |
+
# Comparison Card for Exact Match
|
17 |
+
|
18 |
+
## Comparison description
|
19 |
+
|
20 |
+
Given two model predictions the exact match score is 1 if they are the exact same, and is 0 otherwise. The overall exact match score is the average.
|
21 |
+
|
22 |
+
- **Example 1**: The exact match score if prediction 1.0 is [0, 1] is 0, given prediction 2 is [0, 1].
|
23 |
+
- **Example 2**: The exact match score if prediction 0.0 is [0, 1] is 0, given prediction 2 is [1, 0].
|
24 |
+
- **Example 3**: The exact match score if prediction 0.5 is [0, 1] is 0, given prediction 2 is [1, 1].
|
25 |
+
|
26 |
+
## How to use
|
27 |
+
|
28 |
+
At minimum, this metric takes as input predictions and references:
|
29 |
+
```python
|
30 |
+
>>> exact_match = evaluate.load("exact_match", module_type="comparison")
|
31 |
+
>>> results = exact_match.compute(predictions1=[0, 1, 1], predictions2=[1, 1, 1])
|
32 |
+
>>> print(results)
|
33 |
+
{'exact_match': 0.66}
|
34 |
+
```
|
35 |
+
|
36 |
+
## Output values
|
37 |
+
|
38 |
+
Returns a float between 0.0 and 1.0 inclusive.
|
39 |
+
|
40 |
+
## Examples
|
41 |
+
|
42 |
+
```python
|
43 |
+
>>> exact_match = evaluate.load("exact_match", module_type="comparison")
|
44 |
+
>>> results = exact_match.compute(predictions1=[0, 0, 0], predictions2=[1, 1, 1])
|
45 |
+
>>> print(results)
|
46 |
+
{'exact_match': 1.0}
|
47 |
+
```
|
48 |
+
|
49 |
+
```python
|
50 |
+
>>> exact_match = evaluate.load("exact_match", module_type="comparison")
|
51 |
+
>>> results = exact_match.compute(predictions1=[0, 1, 1], predictions2=[1, 1, 1])
|
52 |
+
>>> print(results)
|
53 |
+
{'exact_match': 0.66}
|
54 |
+
```
|
55 |
+
|
56 |
+
|
57 |
+
## Limitations and bias
|
58 |
+
|
59 |
+
## Citations
|
app.py
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import evaluate
|
2 |
+
from evaluate.utils import launch_gradio_widget
|
3 |
+
|
4 |
+
|
5 |
+
module = evaluate.load("exact_match", module_type="comparison")
|
6 |
+
launch_gradio_widget(module)
|
exact_match.py
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright 2022 The HuggingFace Evaluate Authors
|
2 |
+
#
|
3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4 |
+
# you may not use this file except in compliance with the License.
|
5 |
+
# You may obtain a copy of the License at
|
6 |
+
#
|
7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8 |
+
#
|
9 |
+
# Unless required by applicable law or agreed to in writing, software
|
10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12 |
+
# See the License for the specific language governing permissions and
|
13 |
+
# limitations under the License.
|
14 |
+
"""Exact match test for model comparison."""
|
15 |
+
|
16 |
+
import datasets
|
17 |
+
import numpy as np
|
18 |
+
|
19 |
+
import evaluate
|
20 |
+
|
21 |
+
|
22 |
+
_DESCRIPTION = """
|
23 |
+
Returns the rate at which the predictions of one model exactly match those of another model.
|
24 |
+
"""
|
25 |
+
|
26 |
+
|
27 |
+
_KWARGS_DESCRIPTION = """
|
28 |
+
Args:
|
29 |
+
predictions1 (`list` of `int`): Predicted labels for model 1.
|
30 |
+
predictions2 (`list` of `int`): Predicted labels for model 2.
|
31 |
+
|
32 |
+
Returns:
|
33 |
+
exact_match (`float`): Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
|
34 |
+
|
35 |
+
Examples:
|
36 |
+
>>> exact_match = evaluate.load("exact_match", module_type="comparison")
|
37 |
+
>>> results = exact_match.compute(predictions1=[1, 1, 1], predictions2=[1, 1, 1])
|
38 |
+
>>> print(results)
|
39 |
+
{'exact_match': 1.0}
|
40 |
+
"""
|
41 |
+
|
42 |
+
|
43 |
+
_CITATION = """
|
44 |
+
"""
|
45 |
+
|
46 |
+
|
47 |
+
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
|
48 |
+
class ExactMatch(evaluate.EvaluationModule):
|
49 |
+
def _info(self):
|
50 |
+
return evaluate.EvaluationModuleInfo(
|
51 |
+
module_type="comparison",
|
52 |
+
description=_DESCRIPTION,
|
53 |
+
citation=_CITATION,
|
54 |
+
inputs_description=_KWARGS_DESCRIPTION,
|
55 |
+
features=datasets.Features(
|
56 |
+
{
|
57 |
+
"predictions1": datasets.Value("int64"),
|
58 |
+
"predictions2": datasets.Value("int64"),
|
59 |
+
}
|
60 |
+
),
|
61 |
+
)
|
62 |
+
|
63 |
+
def _compute(self, predictions1, predictions2):
|
64 |
+
score_list = predictions1 == predictions2
|
65 |
+
return {"exact_match": np.mean(score_list)}
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# TODO: fix github to release
|
2 |
+
git+https://github.com/huggingface/evaluate.git@505123230059f9605da8951880eddc9d1fbf4278
|
3 |
+
datasets~=2.0
|
4 |
+
scipy
|