Continue work on project 3.

assess_learners/DTLearner.py

@@ -1,28 +1,51 @@
 import numpy as np
 
+
 class DTLearner(object):
 
+    LEAF = -1
+    NA = -1
+
     def __init__(self, leaf_size = 1, verbose = False):
-        pass # move along, these aren't the drones you're looking for
+        self.leaf_size = leaf_size
+        self.verbose = verbose
 
     def author(self):
         return 'felixm' # replace tb34 with your Georgia Tech username
 
-    def addEvidence(self, dataX, dataY):
+    def create_node(self, factor: int, split: int, left: int, right: int):
+        return np.array((factor, split, 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] == 1:
+            return  self.create_node(self.LEAF, y[0], self.NA, self.NA)
+
+        if np.all(y[0] == y):
+            return self.create_node(self.LEAV, y[0], self.NA, self.NA)
+
+        # XXX: continue here
+        y = np.array([y])
+        correlations = np.corrcoef(xs, y, rowvar=True)
+        print(f"{correlations=}")
+
+        return 0
+
+    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
         """
+        if self.verbose:
+            print(data_x)
+            print(data_y)
+        self.tree = self.build_tree(data_x, data_y)
 
-        # slap on 1s column so linear regression finds a constant term
-        newdataX = np.ones([dataX.shape[0], dataX.shape[1]+1])
-        newdataX[:,0:dataX.shape[1]] = dataX
 
-        # build and save the model
-        self.model_coefs, residuals, rank, s = np.linalg.lstsq(newdataX,
-                                                               dataY,
-                                                               rcond=None)
 
     def query(self,points):
         """
@@ -30,7 +53,8 @@ class DTLearner(object):
         @param points: should be a numpy array with each row corresponding to a specific query.
         @returns the estimated values according to the saved model.
         """
-        return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
+        return
+        # return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
 
 if __name__=="__main__":
     print("the secret clue is 'zzyzx'")