Add rmsle metric and reg:squaredlogerror objective (#4541)

src/metric/elementwise_metric.cu

@@ -153,6 +153,19 @@ struct EvalRowRMSE {
   }
 };
 
+struct EvalRowRMSLE {
+  char const* Name() const {
+    return "rmsle";
+  }
+  XGBOOST_DEVICE bst_float EvalRow(bst_float label, bst_float pred) const {
+    bst_float diff = std::log1p(label) - std::log1p(pred);
+    return diff * diff;
+  }
+  static bst_float GetFinal(bst_float esum, bst_float wsum) {
+    return std::sqrt(esum / wsum);
+  }
+};
+
 struct EvalRowMAE {
   const char *Name() const {
     return "mae";
@@ -349,6 +362,10 @@ XGBOOST_REGISTER_METRIC(RMSE, "rmse")
 .describe("Rooted mean square error.")
 .set_body([](const char* param) { return new EvalEWiseBase<EvalRowRMSE>(); });
 
+XGBOOST_REGISTER_METRIC(RMSLE, "rmsle")
+.describe("Rooted mean square log error.")
+.set_body([](const char* param) { return new EvalEWiseBase<EvalRowRMSLE>(); });
+
 XGBOOST_REGISTER_METRIC(MAE, "mae")
 .describe("Mean absolute error.")
 .set_body([](const char* param) { return new EvalEWiseBase<EvalRowMAE>(); });

src/objective/regression_loss.h

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2017 XGBoost contributors
+ * Copyright 2017-2019 XGBoost contributors
  */
 #ifndef XGBOOST_OBJECTIVE_REGRESSION_LOSS_H_
 #define XGBOOST_OBJECTIVE_REGRESSION_LOSS_H_
@@ -36,6 +36,29 @@ struct LinearSquareLoss {
   static const char* DefaultEvalMetric() { return "rmse"; }
 };
 
+struct SquaredLogError {
+  XGBOOST_DEVICE static bst_float PredTransform(bst_float x) { return x; }
+  XGBOOST_DEVICE static bool CheckLabel(bst_float label) {
+    return label > -1;
+  }
+  XGBOOST_DEVICE static bst_float FirstOrderGradient(bst_float predt, bst_float label) {
+    predt = fmaxf(predt, -1 + 1e-6);  // ensure correct value for log1p
+    return (std::log1p(predt) - std::log1p(label)) / (predt + 1);
+  }
+  XGBOOST_DEVICE static bst_float SecondOrderGradient(bst_float predt, bst_float label) {
+    predt = fmaxf(predt, -1 + 1e-6);
+    float res = (-std::log1p(predt) + std::log1p(label) + 1) /
+                std::pow(predt + 1, 2);
+    res = fmaxf(res, 1e-6f);
+    return res;
+  }
+  static bst_float ProbToMargin(bst_float base_score) { return base_score; }
+  static const char* LabelErrorMsg() {
+    return "label must be greater than -1 for rmsle so that log(label + 1) can be valid.";
+  }
+  static const char* DefaultEvalMetric() { return "rmsle"; }
+};
+
 // logistic loss for probability regression task
 struct LogisticRegression {
   // duplication is necessary, as __device__ specifier

src/objective/regression_obj.cu

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2015-2018 by Contributors
+ * Copyright 2015-2019 by Contributors
  * \file regression_obj.cu
  * \brief Definition of single-value regression and classification objectives.
  * \author Tianqi Chen, Kailong Chen
@@ -124,6 +124,10 @@ XGBOOST_REGISTER_OBJECTIVE(SquaredLossRegression, "reg:squarederror")
 .describe("Regression with squared error.")
 .set_body([]() { return new RegLossObj<LinearSquareLoss>(); });
 
+XGBOOST_REGISTER_OBJECTIVE(SquareLogError, "reg:squaredlogerror")
+.describe("Regression with root mean squared logarithmic error.")
+.set_body([]() { return new RegLossObj<SquaredLogError>(); });
+
 XGBOOST_REGISTER_OBJECTIVE(LogisticRegression, "reg:logistic")
 .describe("Logistic regression for probability regression task.")
 .set_body([]() { return new RegLossObj<LogisticRegression>(); });