lib/xgb/classifier.rb in xgb-0.1.1 vs lib/xgb/classifier.rb in xgb-0.1.2

@@ -1,39 +1,39 @@
 module Xgb
-  class Classifier
-    def initialize(max_depth: 3, learning_rate: 0.1, n_estimators: 100, objective: "binary:logistic", importance_type: "gain")
-      @params = {
-        max_depth: max_depth,
-        objective: objective,
-        learning_rate: learning_rate
-      }
-      @n_estimators = n_estimators
-      @importance_type = importance_type
+  class Classifier < Model
+    def initialize(max_depth: 3, learning_rate: 0.1, n_estimators: 100, objective: "binary:logistic", importance_type: "gain", **options)
+      super
     end
 
-    def fit(x, y)
+    def fit(x, y, eval_set: nil, early_stopping_rounds: nil, verbose: true)
       n_classes = y.uniq.size
 
       params = @params.dup
       if n_classes > 2
         params[:objective] = "multi:softprob"
         params[:num_class] = n_classes
       end
 
       dtrain = DMatrix.new(x, label: y)
-      @booster = Xgb.train(params, dtrain, num_boost_round: @n_estimators)
+      evals = Array(eval_set).map.with_index { |v, i| [DMatrix.new(v[0], label: v[1]), "validation_#{i}"] }
+
+      @booster = Xgb.train(params, dtrain,
+        num_boost_round: @n_estimators,
+        early_stopping_rounds: early_stopping_rounds,
+        verbose_eval: verbose,
+        evals: evals
+      )
       nil
     end
 
     def predict(data)
-      dmat = DMatrix.new(data)
-      y_pred = @booster.predict(dmat)
+      y_pred = super(data)
 
       if y_pred.first.is_a?(Array)
         # multiple classes
         y_pred.map do |v|
-          v.map.with_index.max_by { |v2, i| v2 }.last
+          v.map.with_index.max_by { |v2, _| v2 }.last
         end
       else
         y_pred.map { |v| v > 0.5 ? 1 : 0 }
       end
     end
@@ -46,23 +46,8 @@
         # multiple classes
         y_pred
       else
         y_pred.map { |v| [1 - v, v] }
       end
-    end
-
-    def save_model(fname)
-      @booster.save_model(fname)
-    end
-
-    def load_model(fname)
-      @booster = Booster.new(params: @params, model_file: fname)
-    end
-
-    def feature_importances
-      score = @booster.score(importance_type: @importance_type)
-      scores = @booster.feature_names.map { |k| score[k] || 0.0 }
-      total = scores.sum.to_f
-      scores.map { |s| s / total }
     end
   end
 end