Wnd

zoo/src/main/scala/com/intel/analytics/zoo/examples/recommendation/Ml1mWideAndDeep.scala

@@ -17,10 +17,11 @@
 package com.intel.analytics.zoo.examples.recommendation
 
 import com.intel.analytics.bigdl.numeric.NumericFloat
-import com.intel.analytics.bigdl.optim.{Adam, Top1Accuracy}
+import com.intel.analytics.bigdl.optim.{Adam, PrecisionRecallAUC, Top1Accuracy}
 import com.intel.analytics.zoo.common.NNContext
 import com.intel.analytics.zoo.models.recommendation._
-import com.intel.analytics.zoo.pipeline.api.keras.objectives.SparseCategoricalCrossEntropy
+import com.intel.analytics.zoo.pipeline.api.keras.metrics.AUC
+import com.intel.analytics.zoo.pipeline.api.keras.objectives.{BinaryCrossEntropy, SparseCategoricalCrossEntropy}
 import org.apache.log4j.{Level, Logger}
 import org.apache.spark.SparkConf
 import org.apache.spark.sql.functions._
@@ -58,7 +59,7 @@ object Ml1mWideAndDeep {
 
     val wideAndDeep: WideAndDeep[Float] = WideAndDeep[Float](
       params.modelType,
-      numClasses = 5,
+      numClasses = 1,
       columnInfo = localColumnInfo)
 
     val isImplicit = false
@@ -69,14 +70,15 @@ object Ml1mWideAndDeep {
       featureRdds.randomSplit(Array(0.8, 0.2))
     val trainRdds = trainpairFeatureRdds.map(x => x.sample)
     val validationRdds = validationpairFeatureRdds.map(x => x.sample)
+    println(validationRdds.count())
 
     val optimMethod = new Adam[Float](
       learningRate = 1e-2,
       learningRateDecay = 1e-5)
 
     wideAndDeep.compile(optimizer = optimMethod,
-      loss = SparseCategoricalCrossEntropy[Float](zeroBasedLabel = false),
-      metrics = List(new Top1Accuracy[Float]())
+      loss = BinaryCrossEntropy[Float](),
+      metrics = List(new AUC[Float](), new Top1Accuracy[Float]())
     )
     wideAndDeep.fit(trainRdds, batchSize = params.batchSize,
       nbEpoch = params.maxEpoch, validationData = validationRdds)
@@ -162,7 +164,17 @@ object Ml1mWideAndDeep {
       .select(unioned("userId"), unioned("itemId"), col("label"), col("gender"), col("age"),
         col("occupation"), col("genres"), col("age-gender"))
 
-    val rddOfSample = joined.rdd.map(r => {
+    // 3|261197|
+    // 5|226310|
+    val filtered = joined.filter(joined("label") === 3 || joined("label") === 5)
+
+    val relabel = (s: Int) => {
+      if (s == 3) 0 else 1
+    }
+    val relabelUDF = udf(relabel)
+    val relabeled = filtered.withColumn("label", relabelUDF(col("label")))
+
+    val rddOfSample = relabeled.rdd.map(r => {
       val uid = r.getAs[Int]("userId")
       val iid = r.getAs[Int]("itemId")
       UserItemFeature(uid, iid, Utils.row2Sample(r, columnInfo, modelType))

zoo/src/main/scala/com/intel/analytics/zoo/models/recommendation/Utils.scala

@@ -111,7 +111,7 @@ object Utils {
     val deepTensor: Array[Tensor[Float]] = getDeepTensors(r, columnInfo)
     val l = r.getAs[Int](columnInfo.label)
     val label = Tensor[Float](T(l))
-    label.resize(1, 1)
+//    label.resize(1, 1)
 
     modelType match {
       case "wide_n_deep" =>

zoo/src/main/scala/com/intel/analytics/zoo/models/recommendation/WideAndDeep.scala

@@ -121,21 +121,21 @@ class WideAndDeep[T: ClassTag](
 
     modelType match {
       case "wide" =>
-        val out = Activation("softmax").inputs(wideLinear)
+        val out = Activation("sigmoid").inputs(wideLinear)
         val model: Model[T] = Model(Array(inputWide), out)
           model.asInstanceOf[AbstractModule[Tensor[T], Tensor[T], T]]
 
       case "deep" =>
         val (inputDeep, mergeList) = deepMerge(inputInd, inputEmb, inputCon)
         val deepLinear = deepHidden(mergeList.toList)
-        val out = Activation("softmax").inputs(deepLinear)
+        val out = Activation("sigmoid").inputs(deepLinear)
         Model(inputDeep, out).asInstanceOf[AbstractModule[Tensor[T], Tensor[T], T]]
 
       case "wide_n_deep" =>
         val (inputDeep, mergeList) = deepMerge(inputInd, inputEmb, inputCon)
         val deepLinear = deepHidden(mergeList)
         val merged = Merge.merge(List(wideLinear, deepLinear), "sum")
-        val out = Activation("softmax").inputs(merged)
+        val out = Activation("sigmoid").inputs(merged)
         Model(Array(inputWide) ++ inputDeep, out)
           .asInstanceOf[AbstractModule[Tensor[T], Tensor[T], T]]
       case _ =>

zoo/src/main/scala/com/intel/analytics/zoo/pipeline/api/keras/metrics/AUC.scala

@@ -131,15 +131,15 @@ class AUC[T](thresholdNum: Int = 200)(implicit ev: TensorNumeric[T])
   override def apply(output: Activity, target: Activity):
   ValidationResult = {
     val _output = if (output.asInstanceOf[Tensor[T]].dim() == 2) {
-      output.asInstanceOf[Tensor[T]].squeeze(2)
+      output.asInstanceOf[Tensor[T]].clone().squeeze(2)
     } else {
-      output.asInstanceOf[Tensor[T]].squeeze()
+      output.asInstanceOf[Tensor[T]].clone().squeeze()
     }
 
     val _target = if (target.asInstanceOf[Tensor[T]].dim() == 2) {
-      target.asInstanceOf[Tensor[T]].squeeze(2)
+      target.asInstanceOf[Tensor[T]].clone().squeeze(2)
     } else {
-      target.asInstanceOf[Tensor[T]].squeeze()
+      target.asInstanceOf[Tensor[T]].clone().squeeze()
     }
     require(_output.dim() <= 2 && _target.dim() <= 2,
       s"${_output.dim()} dim format is not supported")