done

ece.py

@@ -44,20 +44,30 @@ Args:
         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.
+    y_true : array-like
+        Ground truth labels.
+    p_hat : array-like
+        Array of confidence estimates.
+    n_bins : int, default=15
+        Number of bins of :math:`[\\frac{1}{n_{\\text{classes}},1]` for the confidence estimates.
+    n_classes : int default=None
+        Number of classes. Estimated from `y` and `y_pred` if not given.
+    p : int, default=1
+        Power of the calibration error, :math:`1 \\leq p \\leq \\infty`.
 
 
 
-Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+Returns
+    Expected calibration error (ECE), float.
+
 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("jordyvl/ece")
+    >>> results = my_new_module.compute(references=[0, 1, 2], predictions=[[0.6, 0.2, 0.2], [0, 0.95, 0.05], [0.7, 0.1 ,0.2]])
     >>> print(results)
-    {'accuracy': 1.0}
+    {'ECE': 1.0}
 """
 
 # TODO: Define external resources urls if needed
@@ -200,9 +210,7 @@ class ECE(evaluate.EvaluationModule):
     """
 
     def __init__(self, n_bins=10, bin_range=None, scheme="equal-range", proxy="upper-edge", p=1):
-        #super().__init__(self)
         super().__init__()
-
         self.n_bins = n_bins
         self.bin_range = bin_range
         self.scheme = scheme