Continue work on project 3.

assess_learners/testlearner.py

@@ -33,8 +33,14 @@ 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:]])
+                     for s in inf.readlines()])
+
+    # XXX: Get rid of some rows and columns for easier development.
+    # XXX: Remove later for testing!
+    # data = data[:10,5:]
 
     # compute how much of the data is training and testing
     train_rows = int(0.6* data.shape[0])
@@ -46,15 +52,18 @@ if __name__=="__main__":
     testX = data[train_rows:,0:-1]
     testY = data[train_rows:,-1]
 
-    print(f"{testX.shape}")
-    print(f"{testY.shape}")
+    # 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.addEvidence(trainX, trainY) # train it
+    # learner.addEvidence(trainX, trainY) # train it #XXX split back into test and non-test
+    learner.addEvidence(data[:,0:-1], data[:,-1])
     print(learner.author())
 
+    sys.exit(0)
+
     # evaluate in sample
     predY = learner.query(trainX) # get the predictions
     rmse = math.sqrt(((trainY - predY) ** 2).sum()/trainY.shape[0])