change to use exact match first

nl2bash_m.py

@@ -11,85 +11,121 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""TODO: Add a description here."""
+"""Exact Match metric."""
+import re
+import string
 
-import evaluate
 import datasets
+import numpy as np
 
+import evaluate
 
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
-}
-"""
 
-# TODO: Add description of the module here
-_DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+_DESCRIPTION = """
+Returns the rate at which the input predicted strings exactly match their references, ignoring any strings input as part of the regexes_to_ignore list.
 """
 
-
-# TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
 Args:
-    predictions: list of predictions to score. Each predictions
-        should be a string with tokens separated by spaces.
-    references: list of reference for each prediction. Each
-        reference should be a string with tokens separated by spaces.
+    predictions: List of predicted texts.
+    references: List of reference texts.
+    regexes_to_ignore: List, defaults to None. Regex expressions of characters to
+        ignore when calculating the exact matches. Note: these regexes are removed
+        from the input data before the changes based on the options below (e.g. ignore_case,
+        ignore_punctuation, ignore_numbers) are applied.
+    ignore_case: Boolean, defaults to False. If true, turns everything
+        to lowercase so that capitalization differences are ignored.
+    ignore_punctuation: Boolean, defaults to False. If true, removes all punctuation before
+        comparing predictions and references.
+    ignore_numbers: Boolean, defaults to False. If true, removes all punctuation before
+        comparing predictions and references.
 Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+    exact_match: Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
 Examples:
-    Examples should be written in doctest format, and should illustrate how
-    to use the function.
-
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
-    >>> print(results)
-    {'accuracy': 1.0}
+    >>> 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"], 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"], 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"], 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"], 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"], 2))
+    0.33
 """
 
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
+_CITATION = """
+"""
 
 
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class nl2bash_m(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
-
     def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
         return evaluate.MetricInfo(
-            # This is the description that will appear on the modules page.
-            module_type="metric",
             description=_DESCRIPTION,
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
-            # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
-            # Homepage of the module for documentation
-            homepage="http://module.homepage",
-            # Additional links to the codebase or references
-            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Value("string", id="sequence"),
+                    "references": datasets.Value("string", id="sequence"),
+                }
+            ),
+            reference_urls=[],
         )
 
-    def _download_and_prepare(self, dl_manager):
-        """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
-        pass
+    def _compute(
+        self,
+        predictions,
+        references,
+        regexes_to_ignore=None,
+        ignore_case=False,
+        ignore_punctuation=False,
+        ignore_numbers=False,
+    ):
+
+        if regexes_to_ignore is not None:
+            for s in regexes_to_ignore:
+                predictions = np.array([re.sub(s, "", x) for x in predictions])
+                references = np.array([re.sub(s, "", x) for x in references])
+        else:
+            predictions = np.asarray(predictions)
+            references = np.asarray(references)
+
+        if ignore_case:
+            predictions = np.char.lower(predictions)
+            references = np.char.lower(references)
+
+        if ignore_punctuation:
+            repl_table = string.punctuation.maketrans("", "", string.punctuation)
+            predictions = np.char.translate(predictions, table=repl_table)
+            references = np.char.translate(references, table=repl_table)
+
+        if ignore_numbers:
+            repl_table = string.digits.maketrans("", "", string.digits)
+            predictions = np.char.translate(predictions, table=repl_table)
+            references = np.char.translate(references, table=repl_table)
+
+        score_list = predictions == references
 
-    def _compute(self, predictions, references):
-        """Returns the scores"""
-        # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
-        return {
-            "accuracy": accuracy,
-        }
+        return {"exact_match": np.mean(score_list)}