Updating the mcc.py file with computation of mcc

mcc.py

@@ -11,16 +11,18 @@
 # 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."""
+"""TODO: MCC is a correlation coefficient between the observed and predicted binary classifications, and takes into account true and false positives and negatives."""
 
 import evaluate
 import datasets
+from sklearn.metrics import matthews_corrcoef
+
 
 
 # TODO: Add BibTeX citation
 _CITATION = """\
 @InProceedings{huggingface:module,
-title = {A great new module},
+title = {MCC Metric},
 authors={huggingface, Inc.},
 year={2020}
 }
@@ -28,7 +30,9 @@ 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.
+MCC (Matthews Correlation Coefficient) is a correlation coefficient between the observed and predicted binary classifications, and takes into account true and false positives and negatives. It can be computed with the equation:
+MCC = (TP * TN - FP * FN) / sqrt((TP+FP) * (TP+FN) * (TN+FP) * (TN+FN))
+Where TP is the true positives, TN is the true negatives, FP is the false positives, and FN is the false negatives.
 """
 
 
@@ -36,60 +40,50 @@ This new module is designed to solve this great ML task and is crafted with a lo
 _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 `int`): The predicted labels.
+    - **references** (`list` of `int`): The ground truth labels.
 Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+    - **mcc** (`float`): The MCC score. Minimum possible value is -1. Maximum possible value is 1. A higher MCC means that the predicted and observed binary classifications agree better, while a negative MCC means that they agree worse than chance.
 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}
+    Example 1-A simple example with some errors
+        >>> mcc_metric = evaluate.load('mcc')
+        >>> results = mcc_metric.compute(references=[0, 0, 1, 1, 1], predictions=[0, 1, 0, 1, 1])
+        >>> print(results)
+        {'mcc': 0.16666666666666666}
+    Example 2-The same example as Example 1, but with some different labels
+        >>> mcc_metric = evaluate.load('mcc')
+        >>> results = mcc_metric.compute(references=[0, 1, 2, 2, 2], predictions=[0, 2, 2, 1, 2])
+        >>> print(results)
+        {'mcc': 0.2041241452319315}
 """
 
 # TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
+BAD_WORDS_URL = "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.matthews_corrcoef.html"
 
 
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class MCC(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
+    """Compute MCC Scores"""
 
     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",
+            homepage="https://huggingface.co/evaluate-metric?message=Request%20sent",
             # 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"]
+            codebase_urls=[],
+            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):
-        """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,
-        }
+        """Returns the mcc scores"""
+        # Computes the MCC score using matthews_corrcoef from sklearn
+        
+        return {"mcc": matthews_corrcoef(references, predictions)}