Spaces:
Sleeping
Sleeping
Commit
•
b8bc601
1
Parent(s):
5663de8
add module default template
Browse files- README.md +44 -6
- app.py +6 -0
- pseudo_perplexity.py +95 -0
- requirements.txt +1 -0
- tests.py +17 -0
README.md
CHANGED
@@ -1,12 +1,50 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 3.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
title: pseudo_perplexity
|
3 |
+
datasets:
|
4 |
+
-
|
5 |
+
tags:
|
6 |
+
- evaluate
|
7 |
+
- measurement
|
8 |
+
description: "TODO: add a description here"
|
9 |
sdk: gradio
|
10 |
+
sdk_version: 3.0.2
|
11 |
app_file: app.py
|
12 |
pinned: false
|
13 |
---
|
14 |
|
15 |
+
# Measurement Card for pseudo_perplexity
|
16 |
+
|
17 |
+
***Module Card Instructions:*** *Fill out the following subsections. Feel free to take a look at existing measurement cards if you'd like examples.*
|
18 |
+
|
19 |
+
## Measurement Description
|
20 |
+
*Give a brief overview of this measurement, including what task(s) it is usually used for, if any.*
|
21 |
+
|
22 |
+
## How to Use
|
23 |
+
*Give general statement of how to use the measurement*
|
24 |
+
|
25 |
+
*Provide simplest possible example for using the measurement*
|
26 |
+
|
27 |
+
### Inputs
|
28 |
+
*List all input arguments in the format below*
|
29 |
+
- **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*
|
30 |
+
|
31 |
+
### Output Values
|
32 |
+
|
33 |
+
*Explain what this measurement outputs and provide an example of what the measurement output looks like. Modules should return a dictionary with one or multiple key-value pairs, e.g. {"bleu" : 6.02}*
|
34 |
+
|
35 |
+
*State the range of possible values that the measurement's output can take, as well as what in that range is considered good. For example: "This measurement can take on any value between 0 and 100, inclusive. Higher scores are better."*
|
36 |
+
|
37 |
+
#### Values from Popular Papers
|
38 |
+
*Give examples, preferrably with links to leaderboards or publications, to papers that have reported this measurement, along with the values they have reported.*
|
39 |
+
|
40 |
+
### Examples
|
41 |
+
*Give code examples of the measurement being used. Try to include examples that clear up any potential ambiguity left from the measurement description above. If possible, provide a range of examples that show both typical and atypical results, as well as examples where a variety of input parameters are passed.*
|
42 |
+
|
43 |
+
## Limitations and Bias
|
44 |
+
*Note any known limitations or biases that the measurement has, with links and references if possible.*
|
45 |
+
|
46 |
+
## Citation
|
47 |
+
*Cite the source where this measurement was introduced.*
|
48 |
+
|
49 |
+
## Further References
|
50 |
+
*Add any useful further references.*
|
app.py
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import evaluate
|
2 |
+
from evaluate.utils import launch_gradio_widget
|
3 |
+
|
4 |
+
|
5 |
+
module = evaluate.load("NimaBoscarino/pseudo_perplexity")
|
6 |
+
launch_gradio_widget(module)
|
pseudo_perplexity.py
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
|
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 |
+
"""TODO: Add a description here."""
|
15 |
+
|
16 |
+
import evaluate
|
17 |
+
import datasets
|
18 |
+
|
19 |
+
|
20 |
+
# TODO: Add BibTeX citation
|
21 |
+
_CITATION = """\
|
22 |
+
@InProceedings{huggingface:module,
|
23 |
+
title = {A great new module},
|
24 |
+
authors={huggingface, Inc.},
|
25 |
+
year={2020}
|
26 |
+
}
|
27 |
+
"""
|
28 |
+
|
29 |
+
# TODO: Add description of the module here
|
30 |
+
_DESCRIPTION = """\
|
31 |
+
This new module is designed to solve this great ML task and is crafted with a lot of care.
|
32 |
+
"""
|
33 |
+
|
34 |
+
|
35 |
+
# TODO: Add description of the arguments of the module here
|
36 |
+
_KWARGS_DESCRIPTION = """
|
37 |
+
Calculates how good are predictions given some references, using certain scores
|
38 |
+
Args:
|
39 |
+
predictions: list of predictions to score. Each predictions
|
40 |
+
should be a string with tokens separated by spaces.
|
41 |
+
references: list of reference for each prediction. Each
|
42 |
+
reference should be a string with tokens separated by spaces.
|
43 |
+
Returns:
|
44 |
+
accuracy: description of the first score,
|
45 |
+
another_score: description of the second score,
|
46 |
+
Examples:
|
47 |
+
Examples should be written in doctest format, and should illustrate how
|
48 |
+
to use the function.
|
49 |
+
|
50 |
+
>>> my_new_module = evaluate.load("my_new_module")
|
51 |
+
>>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
|
52 |
+
>>> print(results)
|
53 |
+
{'accuracy': 1.0}
|
54 |
+
"""
|
55 |
+
|
56 |
+
# TODO: Define external resources urls if needed
|
57 |
+
BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
|
58 |
+
|
59 |
+
|
60 |
+
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
|
61 |
+
class pseudo_perplexity(evaluate.Measurement):
|
62 |
+
"""TODO: Short description of my evaluation module."""
|
63 |
+
|
64 |
+
def _info(self):
|
65 |
+
# TODO: Specifies the evaluate.EvaluationModuleInfo object
|
66 |
+
return evaluate.MeasurementInfo(
|
67 |
+
# This is the description that will appear on the modules page.
|
68 |
+
module_type="measurement",
|
69 |
+
description=_DESCRIPTION,
|
70 |
+
citation=_CITATION,
|
71 |
+
inputs_description=_KWARGS_DESCRIPTION,
|
72 |
+
# This defines the format of each prediction and reference
|
73 |
+
features=datasets.Features({
|
74 |
+
'predictions': datasets.Value('int64'),
|
75 |
+
'references': datasets.Value('int64'),
|
76 |
+
}),
|
77 |
+
# Homepage of the module for documentation
|
78 |
+
homepage="http://module.homepage",
|
79 |
+
# Additional links to the codebase or references
|
80 |
+
codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
|
81 |
+
reference_urls=["http://path.to.reference.url/new_module"]
|
82 |
+
)
|
83 |
+
|
84 |
+
def _download_and_prepare(self, dl_manager):
|
85 |
+
"""Optional: download external resources useful to compute the scores"""
|
86 |
+
# TODO: Download external resources if needed
|
87 |
+
pass
|
88 |
+
|
89 |
+
def _compute(self, predictions, references):
|
90 |
+
"""Returns the scores"""
|
91 |
+
# TODO: Compute the different scores of the module
|
92 |
+
accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
|
93 |
+
return {
|
94 |
+
"accuracy": accuracy,
|
95 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
git+https://github.com/huggingface/evaluate@main
|
tests.py
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
test_cases = [
|
2 |
+
{
|
3 |
+
"predictions": [0, 0],
|
4 |
+
"references": [1, 1],
|
5 |
+
"result": {"metric_score": 0}
|
6 |
+
},
|
7 |
+
{
|
8 |
+
"predictions": [1, 1],
|
9 |
+
"references": [1, 1],
|
10 |
+
"result": {"metric_score": 1}
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"predictions": [1, 0],
|
14 |
+
"references": [1, 1],
|
15 |
+
"result": {"metric_score": 0.5}
|
16 |
+
}
|
17 |
+
]
|