Change best for LinReg to return optimal data

defeat_learners/gen_data.py

@@ -26,27 +26,63 @@ GT ID: 900897987 (replace with your GT ID)
 """
 
 import numpy as np
+import pandas as pd
 import math
 
-# this function should return a dataset (X and Y) that will work  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+
-# better for linear regression than decision trees  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
 def best4LinReg(seed=1489683273):
+    """
+    This function should return a dataset (X and Y) that will work better for
+    linear regression than decision trees.
+
+    We make Y a simple linear combination of X. That will give the Linear
+    Regression algorithm a very easy time (no RMSE at all) and beat the DT
+    easily.
+    """
     np.random.seed(seed)
-    X = np.zeros((100,2))  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    X = np.random.random(size=(100, 2)) * 200 - 100
-    Y = np.random.random(size = (100,))*200-100  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    Y = X[:, 0] * -2 + X[:, 1] * 3
-    # Here's is an example of creating a Y from randomly generated  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
-    # X with multiple columns  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
-    # Y = X[:,0] + np.sin(X[:,1]) + X[:,2]**2 + X[:,3]**3  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
     return X, Y
 
+
 def best4DT(seed=1489683273):
+    """
+    This function should return a dataset that will work better for decision
+    trees than linear regression.
+    """
+
+    # Z = np.append(X, Y.reshape(Y.shape[0], 1), 1)
+    # pd.DataFrame(Z).to_csv("Z.csv", header=None, index=None)
+    # np.random.seed(seed)
+    # X = np.random.random(size=(100, 10))*1000-100
+    # Y = np.random.random(size=(100,))*1000-100
+
     np.random.seed(seed)
-    X = np.zeros((100,2))  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    # X_1 = np.random.random(size=(100, 1))*200-100
-    Y = np.random.random(size = (100,))*200-100  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    # X_2 = np.random.random(size=(100, 1))*200-100
+    # X_3 = np.random.random(size=(100, 1))*200-100
+    # X_4 = np.random.random(size=(100, 1))*200-100
+    # X = np.concatenate([X_1, X_2, X_3, X_4], 1)
+
+    # XXX: I honestly don't know how to help the DTLearner, yet.
+
+    X_1 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
+    X_2 = np.asarray([i for i in range(100, 1100, 10)]).reshape(100, 1)
+    X_3 = np.asarray([i for i in range(200, 300)]).reshape(100, 1)
+    X_4 = np.asarray([i for i in range(300, 400)]).reshape(100, 1)
+    X_5 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
+    X_6 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
+    X_7 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
+    X_8 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
+    X = np.concatenate([X_1, X_2, X_3, X_4, X_5, X_6, X_7, X_8], 1)
+    # Y = X[:, 0] * 2 + X[:, 1] * 3
+    Y = np.random.random(size=(100,)) * 200 - 100
     return X, Y
 
-def author():  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
-    return 'tb34' #Change this to your user ID  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
 
-if __name__=="__main__":  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+def author():
+    return 'felixm'  # Change this to your user ID
+
+
+if __name__ == "__main__":
     print("they call me Tim.")

defeat_learners/testbest4.py

@@ -28,10 +28,12 @@ import DTLearner as dt
 from gen_data import best4LinReg, best4DT
 
 # compare two learners' rmse out of sample
+
+
 def compare_os_rmse(learner1, learner2, X, Y):
 
     # compute how much of the data is training and testing
-    train_rows = int(math.floor(0.6* X.shape[0]))  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    train_rows = int(math.floor(0.6 * X.shape[0]))
     test_rows = X.shape[0] - train_rows
 
     # separate out training and testing data
@@ -56,11 +58,12 @@ def compare_os_rmse(learner1, learner2, X, Y):
 
     return rmse1, rmse2
 
+
 def test_code():
 
     # create two learners and get data
-    lrlearner = lrl.LinRegLearner(verbose = False)  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    lrlearner = lrl.LinRegLearner(verbose=False)
-    dtlearner = dt.DTLearner(verbose = False, leaf_size = 1)  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    dtlearner = dt.DTLearner(verbose=False, leaf_size=1)
     X, Y = best4LinReg()
 
     # compare the two learners
@@ -78,8 +81,8 @@ def test_code():
     print
 
     # get data that is best for a random tree
-    lrlearner = lrl.LinRegLearner(verbose = False)  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    lrlearner = lrl.LinRegLearner(verbose=False)
-    dtlearner = dt.DTLearner(verbose = False, leaf_size = 1)  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+    dtlearner = dt.DTLearner(verbose=False, leaf_size=1)
     X, Y = best4DT()
 
     # compare the two learners
@@ -96,5 +99,6 @@ def test_code():
         print("DT >= 0.9 LR:  fail")
     print
 
-if __name__=="__main__":  		  	   		     			  		 			     			  	  		 	  	 		 			  		  			
+
+if __name__ == "__main__":
     test_code()