Merge branch 'master' into master

R-package/demo/basic_walkthrough.R

@@ -64,8 +64,8 @@ raw = xgb.save.raw(bst)
 # load binary model to R
 bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
-# pred2 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred2-pred))))
+# pred3 should be identical to pred
+print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix

jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostModel.scala

@@ -32,8 +32,12 @@ class XGBoostModel(_booster: Booster)(implicit val sc: SparkContext) extends Ser
     import DataUtils._
     val broadcastBooster = testSet.sparkContext.broadcast(_booster)
     testSet.mapPartitions { testSamples =>
-      val dMatrix = new DMatrix(new JDMatrix(testSamples, null))
-      Iterator(broadcastBooster.value.predict(dMatrix))
+      if (testSamples.hasNext) {
+        val dMatrix = new DMatrix(new JDMatrix(testSamples, null))
+        Iterator(broadcastBooster.value.predict(dMatrix))
+      } else {
+        Iterator()
+      }
     }
   }
 

jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostSuite.scala

@@ -23,7 +23,7 @@ import scala.collection.mutable.ListBuffer
 import scala.io.Source
 
 import org.apache.commons.logging.LogFactory
-import org.apache.spark.mllib.linalg.DenseVector
+import org.apache.spark.mllib.linalg.{Vector => SparkVector, Vectors, DenseVector}
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.rdd.RDD
 import org.apache.spark.{SparkConf, SparkContext}
@@ -190,4 +190,24 @@ class XGBoostSuite extends FunSuite with BeforeAndAfter {
     assert(eval.eval(xgBoostModel.predict(testSetDMatrix), testSetDMatrix) < 0.1)
     customSparkContext.stop()
   }
+
+  test("test with empty partition") {
+
+    def buildEmptyRDD(sparkContext: Option[SparkContext] = None): RDD[SparkVector] = {
+      val sampleList = new ListBuffer[SparkVector]
+      sparkContext.getOrElse(sc).parallelize(sampleList, numWorkers)
+    }
+
+    val eval = new EvalError()
+    val trainingRDD = buildTrainingRDD()
+    val testRDD = buildEmptyRDD()
+    import DataUtils._
+    val tempDir = Files.createTempDirectory("xgboosttest-")
+    val tempFile = Files.createTempFile(tempDir, "", "")
+    val paramMap = List("eta" -> "1", "max_depth" -> "2", "silent" -> "0",
+      "objective" -> "binary:logistic").toMap
+    val xgBoostModel = XGBoost.train(trainingRDD, paramMap, 5, numWorkers)
+
+    println(xgBoostModel.predict(testRDD))
+  }
 }

python-package/xgboost/core.py

@@ -144,7 +144,8 @@ def _maybe_pandas_data(data, feature_names, feature_types):
 
     data_dtypes = data.dtypes
     if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in data_dtypes):
-        raise ValueError('DataFrame.dtypes for data must be int, float or bool')
+        bad_fields = [data.columns[i] for i, dtype in enumerate(data_dtypes) if dtype.name not in PANDAS_DTYPE_MAPPER ]  
+        raise ValueError('DataFrame.dtypes for data must be int, float or bool.\nDid not expect the data types in fie    lds '+', '.join(bad_fields))
 
     if feature_names is None:
         feature_names = data.columns.format()