def test_code(): fail = 0 fail_list = np.array([]) for i in range(1000): # create two learners and get data s = np.random.randint(0, 1489683274) #print(s) #s = 993360834 lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg(s) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print "LR < 0.9 DT: pass" else: print "LR >= 0.9 DT: fail" fail = fail + 1 fail_list = np.append(fail_list, s) print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT(s) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseDT if rmseDT < 0.9 * rmseLR: print "DT < 0.9 LR: pass" else: print "DT >= 0.9 LR: fail" fail = fail + 1 fail_list = np.append(fail_list, s) print print(fail, 'You failed') print(fail_list, 'Failed seeds')
def test_code(seedval=1489683273): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose = False) dtlearner = dt.DTLearner(verbose = False, leaf_size = 1) X, Y = best4LinReg(seed=seedval) dtX = X dtY = Y # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print "LR < 0.9 DT: pass" else: print "LR >= 0.9 DT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose = False) dtlearner = dt.DTLearner(verbose = False, leaf_size = 1) X, Y = best4DT(seed=seedval) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseDT if rmseDT < 0.9 * rmseLR: print "DT < 0.9 LR: pass" else: print "DT >= 0.9 LR: fail" print return dtX, dtY, X, Y
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg() numPass = 0 numFail = 0 # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseLR < 0.9 * rmseRT: numPass = numPass + 1 print "LR < 0.9 RT: pass" else: numFail = numFail + 1 print "LR < 0.9 RT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4RT() numPass = 0 numFail = 0 # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseRT < 0.9 * rmseLR: numPass = numPass + 1 print "RT < 0.9 LR: pass" else: numFail = numFail + 1 print "RT < 0.9 LR: fail" print
def test_code(): fail1, fail2 = 0, 0 for i in range(500): R = int(1000 * np.random.random_sample()) # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg(R) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print "LR < 0.9 DT: pass" else: fail1 += 1 print "LR >= 0.9 DT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT(R) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseDT if rmseDT < 0.9 * rmseLR: print "DT < 0.9 LR: pass" else: fail2 += 1 print "DT >= 0.9 LR: fail" print print "fail1: %i" % fail1 print "fail2: %i" % fail2
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg() # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseLR < 0.9 * rmseRT: print "LR < 0.9 RT: pass" else: print "LR < 0.9 RT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4RT(seed=5) # data = np.genfromtxt('../mc3_p1/Data/ripple.csv', delimiter = ','); ## data = data[1:,1:] # X = data[:,:-1]; Y = data[:,-1] # fig = plt.figure() # ax = fig.add_subplot(111, projection='3d') # ax.scatter(X[:,0], X[:,1], Y, c='c') # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseRT < 0.9 * rmseLR: print "RT < 0.9 LR: pass" else: print "RT < 0.9 LR: fail" print
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) numPass = 0 numFail = 0 for i in range(1000): X, Y = best4LinReg(1) # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results if rmseLR < 0.9 * rmseRT: numPass = numPass + 1 else: numFail = numFail + 1 print print "Number of Pass: "******"Number of Fail: " + str(numFail) # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) numPass = 0 numFail = 0 for i in range(1000): X, Y = best4RT(1) # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results if rmseRT < 0.9 * rmseLR: numPass = numPass + 1 else: numFail = numFail + 1 print print "Number of Pass: "******"Number of Fail: " + str(numFail)
def test_code(): i = list(range(0, 16)) for trial in i: # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg() # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print "LRL test number: ", trial, "\nLR < 0.9 DT: pass" else: print "LRL test number: ", trial, "\nLR >= 0.9 DT: fail" print i = list(range(1, 16)) for trial in i: # get data that is best for a decision tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT() # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseDT if rmseDT < 0.9 * rmseLR: print "DT test number: ", trial, "\nDT < 0.9 LR: pass" else: print "DT test number: ", trial, "\nDT >= 0.9 LR: fail" print
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg() # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseLR < 0.9 * rmseRT: print "LR < 0.9 RT: pass" else: print "LR < 0.9 RT: fail" print # share results for i in range(2000): # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) rtlearner = rt.RTLearner(verbose=False, leaf_size=1) X, Y = best4RT() # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # print # print "best4RT() results" # print "RMSE LR : ", rmseLR # print "RMSE RT : ", rmseRT if rmseRT < 0.9 * rmseLR: # print "RT < 0.9 LR: pass" continue else: print i # print "RT < 0.9 LR: fail" # print print "Done"
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) #X, Y = best4LinReg() X, Y = best4LinReg(seed=100, n_samples=100, n_features=5) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print "LR < 0.9 DT: pass" else: print "LR >= 0.9 DT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) #X, Y = best4DT() X, Y = best4DT(seed=10, n_samples=1000, n_features=10) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print print "best4DT() results" print "RMSE LR : ", rmseLR print "RMSE DT : ", rmseDT if rmseDT < 0.9 * rmseLR: print "DT < 0.9 LR: pass" else: print "DT >= 0.9 LR: fail" print
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg(seed=1) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print() print("best4LinReg() results") print(f"RMSE LR : {rmseLR}") print(f"RMSE DT : {rmseDT}") print(f"ratio LR/DT : {rmseLR/rmseDT}") if rmseLR < 0.9 * rmseDT: print("LR < 0.9 DT: pass") else: print("LR >= 0.9 DT: fail") print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT(seed=1010) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results print() print("best4RT() results") print(f"RMSE LR : {rmseLR}") print(f"RMSE DT : {rmseDT}") print(f"ratio DT/LR : {rmseDT/rmseLR}") if rmseDT < 0.9 * rmseLR: print("DT < 0.9 LR: pass") else: print("DT >= 0.9 LR: fail") print
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose = False) rtlearner = rt.RTLearner(verbose = False, leaf_size = 1) X, Y = best4LinReg() # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4LinReg() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseLR < 0.9 * rmseRT: print "LR < 0.9 RT: pass" else: print "LR < 0.9 RT: fail" print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose = False) rtlearner = rt.RTLearner(verbose = False, leaf_size = 1) X, Y = best4RT() # compare the two learners rmseLR, rmseRT = compare_os_rmse(lrlearner, rtlearner, X, Y) # share results print print "best4RT() results" print "RMSE LR : ", rmseLR print "RMSE RT : ", rmseRT if rmseRT < 0.9 * rmseLR: print "RT < 0.9 LR: pass" else: print "RT < 0.9 LR: fail" print
def test_code(): # create two learners and get data lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4LinReg(int(np.mod(time.time() * 10000, 10000))) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results # print # print "best4LinReg() results" # print "RMSE LR : ", rmseLR # print "RMSE DT : ", rmseDT if rmseLR < 0.9 * rmseDT: print '.', else: print "LR >= 0.9 DT: fail", 'LR RMSE=', rmseLR, 'DT RMSE=', rmseDT # print # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT(int(np.mod(time.time() * 10000, 10000))) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results # print # print "best4DT() results" # print "RMSE LR : ", rmseLR # print "RMSE DT : ", rmseDT if rmseDT < 0.9 * rmseLR: print '.', else: print "DT >= 0.9 LR: fail", 'DT RMSE=', rmseDT, 'LR RMSE=', rmseLR
def test_code(): # create two learners and get data tot = 0 m = np.random.randint(100000000, size=10000) for i in range(0, m.size): r = np.random.randint(1000000000) lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(leaf_size=1, verbose=False) X, Y = best4LinReg(seed=r) #np.savetxt('test.csv', X, delimiter=',') #np.savetxt('testy.csv', Y.astype(int), delimiter=',') # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) # share results if rmseLR >= 0.9 * rmseDT: print "LR < 0.9 DT: fail" tot += 1 # get data that is best for a random tree lrlearner = lrl.LinRegLearner(verbose=False) dtlearner = dt.DTLearner(verbose=False, leaf_size=1) X, Y = best4DT(seed=r) # compare the two learners rmseLR, rmseDT = compare_os_rmse(lrlearner, dtlearner, X, Y) if rmseDT >= 0.9 * rmseLR: print "DT >= 0.9 LR: fail" tot += 1 print(tot)
import numpy as np import gen_data import math print np.random.randint(0, 2 * math.pi, size=(100, 2)) X, Y = gen_data.best4DT(123) X2, Y2 = gen_data.best4DT(123) XL1, YL1 = gen_data.best4LinReg(123) XL2, YL2 = gen_data.best4LinReg(123) print X print Y print np.array_equal(X, X2) print np.array_equal(Y, Y2) print np.array_equal(XL1, XL2) print np.array_equal(YL1, YL2) print X.shape print Y.shape print np.random.randint(0, 2 * math.pi, size=(100, 2))