test upload

unigram.py

@@ -15,7 +15,8 @@
 
 import evaluate
 import datasets
-
+from collections import Counter
+import numpy as np
 
 # TODO: Add BibTeX citation
 _CITATION = """\
@@ -28,7 +29,7 @@ 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.
+This module calculates the unigram precision, recall, and f1 score.
 """
 
 
@@ -36,25 +37,20 @@ 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 list of int (token)
+    references: list of list of int (tokens)
 Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+    f1: the unigram f1 score.
+    precision: the unigram accuracy.
+    recall: the unigram recall.
 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])
+    >>> my_new_module = evaluate.load("ckb/unigram")
+    >>> results = my_new_module.compute(references=[[0, 1]], predictions=[[0, 1]])
     >>> print(results)
     {'accuracy': 1.0}
 """
 
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
 
 
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
@@ -81,15 +77,30 @@ class unigram(evaluate.Metric):
             reference_urls=["http://path.to.reference.url/new_module"]
         )
 
-    def _download_and_prepare(self, dl_manager):
-        """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
-        pass
+
+    def _prec_recall_f1_score(pred_items, gold_items):
+        """
+        Compute precision, recall and f1 given a set of gold and prediction items.
+        :param pred_items: iterable of predicted values
+        :param gold_items: iterable of gold values
+        :return: tuple (p, r, f1) for precision, recall, f1
+        """
+        common = Counter(gold_items) & Counter(pred_items)
+        num_same = sum(common.values())
+        if num_same == 0:
+            return 0, 0, 0
+        precision = 1.0 * num_same / len(pred_items)
+        recall = 1.0 * num_same / len(gold_items)
+        f1 = (2 * precision * recall) / (precision + recall)
+        return np.array(precision, recall, f1)
 
     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)
+        score = sum(self._prec_recall_f1_score(i,j) for i, j in zip(predictions, references)) / len(predictions)
         return {
-            "accuracy": accuracy,
-        }
+            "precision": score[0],
+            "recall": score[1],
+            "f1": score[2],
+            
+        }