Log loss metric

[TomAugspurger]

No description provided.

[TomAugspurger]

The following gets sample_weight "working", in the sense that the computation completes:

diff --git a/dask_ml/metrics/classification.py b/dask_ml/metrics/classification.py
index 7766370..3025501 100644
--- a/dask_ml/metrics/classification.py
+++ b/dask_ml/metrics/classification.py
@@ -94,11 +94,13 @@ def accuracy_score(y_true, y_pred, normalize=True, sample_weight=None, compute=T
     return score
 
 
-def _log_loss_inner(x, y, **kwargs):
+def _log_loss_inner(x, y, sample_weight, **kwargs):
     # da.map_blocks wasn't able to concatenate together the results
     # when we reduce down to a scalar per block. So we make an
     # array with 1 element.
-    return np.array([sklearn.metrics.log_loss(x, y, **kwargs)])
+    if sample_weight is not None:
+        sample_weight = sample_weight.ravel()
+    return np.array([sklearn.metrics.log_loss(x, y, sample_weight=sample_weight, **kwargs)])
 
 
 def log_loss(
@@ -107,19 +109,20 @@ def log_loss(
     if y_true.ndim == 1:
         y_true = y_true.reshape(-1, 1)
     if sample_weight is not None:
-        raise ValueError("sample_weight is not supported.")
+        # raise ValueError("sample_weight is not supported.")
+        sample_weight = sample_weight.reshape(-1, 1)
     assert y_pred.ndim == 2
 
     result = da.map_blocks(
         _log_loss_inner,
         y_true,
         y_pred,
+        sample_weight,
         chunks=(1,),
         drop_axis=1,
         dtype="f8",
         eps=eps,
         normalize=normalize,
-        sample_weight=sample_weight,
         labels=labels,
     )
     if normalize:
diff --git a/tests/metrics/test_metrics.py b/tests/metrics/test_metrics.py
index 795fe7a..0876414 100644
--- a/tests/metrics/test_metrics.py
+++ b/tests/metrics/test_metrics.py
@@ -86,7 +86,7 @@ def test_pairwise_kernels(kernel):
     "sample_weight",
     [
         pytest.param(
-            True, marks=pytest.mark.xfail(reason="sample_weight not implemented")
+            True, # marks=pytest.mark.xfail(reason="sample_weight not implemented")
         ),
         False,
     ],

Unfortunately, this means the problem is no longer linear, so we can just take a simple sum / mean of the block-wise scores.

Although... I wonder if we could do a final weighted sum of the blockwise scores, weighted by each block's weight?

[TomAugspurger]

OK, I didn't do the math on sample_weight, but the tests pass :)