Don't set_params at the end of set_state. (#4947)

* Don't set_params at the end of set_state.

* Also fix another issue found in dask prediction.

* Add note about prediction.

Don't support other prediction modes at the moment.

tests/python/test_with_dask.py

@@ -43,14 +43,17 @@ def test_from_dask_dataframe(client):
 
     prediction = xgb.dask.predict(client, model=booster, data=dtrain)
 
+    assert prediction.ndim == 1
     assert isinstance(prediction, da.Array)
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.shape[0] == kRows
 
     with pytest.raises(ValueError):
         # evals_result is not supported in dask interface.
         xgb.dask.train(
             client, {}, dtrain, num_boost_round=2, evals_result={})
 
+    prediction = prediction.compute()  # force prediction to be computed
+
 
 def test_from_dask_array(client):
     X, y = generate_array()
@@ -59,10 +62,12 @@ def test_from_dask_array(client):
     result = xgb.dask.train(client, {}, dtrain)
 
     prediction = xgb.dask.predict(client, result, dtrain)
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.shape[0] == kRows
 
     assert isinstance(prediction, da.Array)
 
+    prediction = prediction.compute()  # force prediction to be computed
+
 
 def test_regressor(client):
     X, y = generate_array()
@@ -72,7 +77,8 @@ def test_regressor(client):
     regressor.fit(X, y, eval_set=[(X, y)])
     prediction = regressor.predict(X)
 
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.ndim == 1
+    assert prediction.shape[0] == kRows
 
     history = regressor.evals_result()
 
@@ -91,7 +97,8 @@ def test_classifier(client):
     classifier.fit(X, y,  eval_set=[(X, y)])
     prediction = classifier.predict(X)
 
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.ndim == 1
+    assert prediction.shape[0] == kRows
 
     history = classifier.evals_result()