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/RTLearner.py

@@ -1,83 +1,30 @@
 import numpy as np
+from AbstractTreeLearner import AbstractTreeLearner
 
 
-class RTLearner(object):
-
-    LEAF = -1
-    NA = -1
+class RTLearner(AbstractTreeLearner):
 
     def __init__(self, leaf_size = 1, verbose = False):
         self.leaf_size = leaf_size
         self.verbose = verbose
 
-    def author(self):
-        return 'felixm' # replace tb34 with your Georgia Tech username
-
-    def create_node(self, factor, split_value, left, right):
-        return np.array([[factor, split_value, left, right], ])
-
-    def build_tree(self, xs, y):
-        assert(xs.shape[0] == y.shape[0])
-        assert(xs.shape[0] > 0) # If this is 0 something went wrong.
-
-        if xs.shape[0] <= self.leaf_size:
-            value = np.median(y)
-            return  self.create_node(self.LEAF, value, self.NA, self.NA)
-
-        if np.all(y[0] == y):
-            return self.create_node(self.LEAF, y[0], self.NA, self.NA)
+    def get_i_and_split_value(self, xs, y):
+        """
+        @summary: Pick a random i and split value.
 
+        Make sure that not all X are the same for i and also pick
+        different values to average the split_value from.
+        """
         i = np.random.randint(0, xs.shape[1])
-        # If we pick an i for which all x are the same, try again.
         while np.all(xs[0,i] == xs[:,i]):
             i = np.random.randint(0, xs.shape[1])
 
-        r1, r2 = np.random.randint(0, xs.shape[0], size = 2)
-        split_value = (xs[r1, i] + xs[r2, i]) / 2.0
+        # I don't know about the performance of this, but at least it
+        # terminates reliably. If the two elements are the same something is
+        # wrong.
+        a = np.array(list(set(xs[:, i])))
+        r1, r2 = np.random.choice(a, size = 2, replace = False)
+        assert(r1 != r2)
+        split_value = (r1 + r2) / 2.0
+        return i, split_value
 
-        select_lt = xs[:, i] <= split_value
-        select_rt = xs[:, i] > split_value
-        # Avoid case where all values are low or equal to the median.
-        if select_lt.all() or select_rt.all():
-            select_lt = xs[:, i] < split_value
-            select_rt = xs[:, i] >= split_value
-
-        lt = self.build_tree(xs[select_lt], y[select_lt])
-        rt = self.build_tree(xs[select_rt], y[select_rt])
-        root = self.create_node(i, split_value, 1, rt.shape[0] + 1)
-
-        root = np.concatenate([root, lt, rt])
-        return root
-
-    def addEvidence(self, data_x, data_y):
-        """
-        @summary: Add training data to learner
-        @param dataX: X values of data to add
-        @param dataY: the Y training values
-        """
-        self.rel_tree = self.build_tree(data_x, data_y)
-
-    def query_point(self, point):
-        node_index = 0
-        while self.rel_tree[node_index, 0] != self.LEAF:
-            node = self.rel_tree[node_index]
-            split_factor = int(node[0])
-            split_value = node[1]
-            if point[split_factor] <= split_value:
-                node_index += int(node[2])
-            else:
-                node_index += int(node[3])
-        return self.rel_tree[node_index, 1]
-
-    def query(self, points):
-        """
-        @summary: Estimate a set of test points given the model we built.
-        @param points: should be a numpy array with each row corresponding to a specific query.
-        @returns the estimated values according to the saved model.
-        """
-        query_point = lambda p: self.query_point(p)
-        r = np.apply_along_axis(query_point, 1, points)
-        return r
-
-if __name__=="__main__":
-    print("the secret clue is 'zzyzx'")