Fix DTLearner. The issue was that I took the lenght of the wrong tree (right instead of left) for the root. Also avoid code duplication via abstract tree learner class because why not.

assess_learners/testlearner.py

@@ -36,8 +36,6 @@ if __name__=="__main__":
         print("Usage: python testlearner.py <filename>")
         sys.exit(1)
     inf = open(sys.argv[1])
-    # data = np.array([list(map(float,s.strip().split(',')[1:]))
-                     # for s in inf.readlines()[1:]])
     data = np.array([list(map(float,s.strip().split(',')[1:]))
                      for s in inf.readlines()[1:]])
 
@@ -51,32 +49,44 @@ if __name__=="__main__":
     testX = data[train_rows:,0:-1]
     testY = data[train_rows:,-1]
 
+    # trainX = data[:, 0:-1]
+    # trainY = data[:, -1]
+    # testX = data[:, 0:-1]
+    # testY = data[:, -1]
+
     print(f"{testX.shape}")
     print(f"{testY.shape}")
 
-    # create a learner and train it
-    # learner = lrl.LinRegLearner(verbose = True) # create a LinRegLearner
-    learner = dtl.DTLearner(verbose = True) # create a LinRegLearner
-    # learner = rtl.RTLearner(verbose = True) # create a LinRegLearner
-    # learner = bgl.BagLearner(dtl.DTLearner, bags=50) # create a LinRegLearner
+    def test_learner(learner_class, **kwargs):
+        print("\n-----------")
+        print(f"name={learner_class.__name__} {kwargs=}")
+        learner = learner_class(**kwargs)
+        learner.addEvidence(trainX, trainY)
+        print(learner.author())
+
+        # evaluate in sample
+        predY = learner.query(trainX) # get the predictions
+        rmse = math.sqrt(((trainY - predY) ** 2).sum()/trainY.shape[0])
+        print()
+        print("In sample results")
+        print(f"RMSE: {rmse}")
+        c = np.corrcoef(predY, y=trainY)
+        print(f"corr: {c[0,1]}")
+
+        # evaluate out of sample
+        predY = learner.query(testX) # get the predictions
+        rmse = math.sqrt(((testY - predY) ** 2).sum()/testY.shape[0])
+        print()
+        print("Out of sample results")
+        print(f"RMSE: {rmse}")
+        c = np.corrcoef(predY, y=testY)
+        print(f"corr: {c[0,1]}")
+        print()
+
+    # test_learner(lrl.LinRegLearner)
+    test_learner(dtl.DTLearner, leaf_size=1)
+    test_learner(rtl.RTLearner)
+    test_learner(rtl.RTLearner, leaf_size=5)
+    # test_learner(bgl.BagLearner, learner=dtl.DTLearner, bags=20)
     # learner = isl.InsaneLearner()
-    learner.addEvidence(trainX, trainY)
-    print(learner.author())
 
-    # evaluate in sample
-    predY = learner.query(trainX) # get the predictions
-    rmse = math.sqrt(((trainY - predY) ** 2).sum()/trainY.shape[0])
-    print()
-    print("In sample results")
-    print(f"RMSE: {rmse}")
-    c = np.corrcoef(predY, y=trainY)
-    print(f"corr: {c[0,1]}")
-
-    # evaluate out of sample
-    predY = learner.query(testX) # get the predictions
-    rmse = math.sqrt(((testY - predY) ** 2).sum()/testY.shape[0])
-    print()
-    print("Out of sample results")
-    print(f"RMSE: {rmse}")
-    c = np.corrcoef(predY, y=testY)
-    print(f"corr: {c[0,1]}")