1
我正在使用Spark(1.5.2)DataFrames並嘗試獲取分層數據集。我的數據已經被準備向二元分類並且只有這兩個值用於class
,1和0sampleBy返回非常偏斜的結果
val Array(trainingData, testData) = df.randomSplit(Array(0.7, 0.3))
val fractions: Map[Int, Double] = Map(1 -> 0.5, 0 -> 0.5)
val trainingData3 = trainingData.stat.sampleBy("class", fractions, new Random().nextLong)
println("Training True Class = " + trainingData3.where("class=1").count())
println("Training False Class = " + trainingData3.where("class=0").count())
在控制檯我得到表示1類的不正確大大比的輸出爲0:
Training True Class = 799845
Training False Class = 32797260
您可能正在尋找此http://stackoverflow.com/a/32241887/3415409 – eliasah