check in conf

multi-node/col-split/mushroom-col.conf

@@ -0,0 +1,35 @@
+# General Parameters, see comment for each definition
+# choose the booster, can be gbtree or gblinear
+booster = gbtree
+# choose logistic regression loss function for binary classification
+objective = binary:logistic
+
+# Tree Booster Parameters
+# step size shrinkage
+eta = 1.0 
+# minimum loss reduction required to make a further partition
+gamma = 1.0 
+# minimum sum of instance weight(hessian) needed in a child
+min_child_weight = 1 
+# maximum depth of a tree
+max_depth = 3 
+
+# Task Parameters
+# the number of round to do boosting
+num_round = 2
+# 0 means do not save any model except the final round model
+save_period = 0 
+use_buffer = 0
+
+# The path of training data %d is the wildcard for the rank of the data
+# The idea is each process take a feature matrix with subset of columns
+#
+data = "train.col%d" 
+
+# The path of validation data, used to monitor training process, here [test] sets name of the validation set
+eval[test] = "../../demo/data/agaricus.txt.test" 
+# evaluate on training data as well each round
+eval_train = 1
+
+# The path of test data, need to use full data of test, try not use it, or keep an subsampled version
+test:data = "../../demo/data/agaricus.txt.test"