update format

app.py

@@ -0,0 +1,6 @@
+import evaluate
+from evaluate.utils import launch_gradio_widget
+
+
+module = evaluate.load("nl2bash_metric")
+launch_gradio_widget(module)

nl2bash_metric.py

@@ -15,9 +15,10 @@
 import re
 import string
 
+import datasets
 import numpy as np
 
-import datasets
+import evaluate
 
 
 _DESCRIPTION = """
@@ -39,48 +40,48 @@ Args:
     ignore_numbers: Boolean, defaults to False. If true, removes all punctuation before
         comparing predictions and references.
 Returns:
-    exact_match: Dictionary containing exact_match rate. Possible values are between 0.0 and 100.0, inclusive.
+    exact_match: Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
 Examples:
-    >>> exact_match = datasets.load_metric("exact_match")
+    >>> exact_match = evaluate.load("exact_match")
     >>> refs = ["the cat", "theater", "YELLING", "agent007"]
     >>> preds = ["cat?", "theater", "yelling", "agent"]
     >>> results = exact_match.compute(references=refs, predictions=preds)
-    >>> print(round(results["exact_match"], 1))
-    25.0
-    >>> exact_match = datasets.load_metric("exact_match")
+    >>> print(round(results["exact_match"], 2))
+    0.25
+    >>> exact_match = evaluate.load("exact_match")
     >>> refs = ["the cat", "theater", "YELLING", "agent007"]
     >>> preds = ["cat?", "theater", "yelling", "agent"]
     >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell"], ignore_case=True, ignore_punctuation=True)
-    >>> print(round(results["exact_match"], 1))
-    50.0
-    >>> exact_match = datasets.load_metric("exact_match")
+    >>> print(round(results["exact_match"], 2))
+    0.5
+    >>> exact_match = evaluate.load("exact_match")
     >>> refs = ["the cat", "theater", "YELLING", "agent007"]
     >>> preds = ["cat?", "theater", "yelling", "agent"]
     >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True)
-    >>> print(round(results["exact_match"], 1))
-    75.0
-    >>> exact_match = datasets.load_metric("exact_match")
+    >>> print(round(results["exact_match"], 2))
+    0.75
+    >>> exact_match = evaluate.load("exact_match")
     >>> refs = ["the cat", "theater", "YELLING", "agent007"]
     >>> preds = ["cat?", "theater", "yelling", "agent"]
     >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True, ignore_numbers=True)
-    >>> print(round(results["exact_match"], 1))
-    100.0
-    >>> exact_match = datasets.load_metric("exact_match")
+    >>> print(round(results["exact_match"], 2))
+    1.0
+    >>> exact_match = evaluate.load("exact_match")
     >>> refs = ["The cat sat on the mat.", "Theaters are great.", "It's like comparing oranges and apples."]
     >>> preds = ["The cat sat on the mat?", "Theaters are great.", "It's like comparing apples and oranges."]
     >>> results = exact_match.compute(references=refs, predictions=preds)
-    >>> print(round(results["exact_match"], 1))
-    33.3
+    >>> print(round(results["exact_match"], 2))
+    0.33
 """
 
 _CITATION = """
 """
 
 
-@datasets.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
-class nl2bash_metric(datasets.Metric):
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class nl2bash_metric(evaluate.Metric):
     def _info(self):
-        return datasets.MetricInfo(
+        return evaluate.MetricInfo(
             description=_DESCRIPTION,
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
@@ -127,4 +128,4 @@ class nl2bash_metric(datasets.Metric):
 
         score_list = predictions == references
 
-        return {"exact_match": np.mean(score_list) * 100}
+        return {"exact_match": np.mean(score_list)}