bases += [LinearClassify, LogisticClassify]
def test(trd, trc, ted, tec):
print('bc', '\n')
bc = BaggedClassify(bases[np.random.randint(len(bases))], 20, trd, trc)
print(bc, '\n')
# print(bc.predict(ted), '\n')
# print(bc.predict_soft(ted), '\n')
# print(bc.confusion(ted, tec), '\n')
print(bc.auc(ted, tec), '\n')
print(bc.roc(ted, tec), '\n')
err = bc.err(ted, tec)
print(err, '\n')
return err
avg_err = test_randomly(bd1, bc1, 0.8, test)
print('avg_err')
print(avg_err)
## DETERMINISTIC TESTING #######################################################
# np.set_printoptions(linewidth=200)
#
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/classifier-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# classes = [float(row[-1].lower()) for row in csv.reader(open('../data/classifier-data.csv'))]
# trc = np.asarray(classes[0:40] + classes[50:90] + classes[100:140])
# tec = np.asarray(classes[40:50] + classes[90:100] + classes[140:150])
#
bd1, bc1 = np.array(bd1), np.array(bc1)
def test(trd, trc, ted, tec):
print('tc', '\n')
tc = TreeClassify(trd, trc)
print(tc, '\n')
# print(tc.predict(ted), '\n')
# print(tc.predict_soft(ted), '\n')
# print(tc.confusion(ted, tec), '\n')
# print(tc.auc(ted, tec), '\n')
# print(tc.roc(ted, tec), '\n')
err = tc.err(ted, tec)
print(err, '\n')
return err
avg_err = test_randomly(data, classes, 0.8, test)
print('avg_err')
print(avg_err)
## DETERMINISTIC TESTING #######################################################
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/classifier-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# classes = [float(row[-1].lower()) for row in csv.reader(open('../data/classifier-data.csv'))]
# trc = np.asarray(classes[0:40] + classes[50:90] + classes[100:140])
# tec = np.asarray(classes[40:50] + classes[90:100] + classes[140:150])
#
# btrd = trd[0:80,:]
# bted = ted[0:20,:]
err = gd.mse(ted, tec)
print('gd.mse =', err, '\n')
print('gd.predict(ted)')
print(gd.predict(ted))
print('gd.get_n()')
print(gd.get_n())
gd.train(base, 6, X2, Y2)
print('gd.get_n()')
print(gd.get_n())
err = gd.mse(ted, tec)
print('gd.mse =', err, '\n')
print('gd.predict(ted)')
print(gd.predict(ted))
return err
avg_err = test_randomly(data, predictions, 0.8, test=test, end=1)
print('avg_err')
print(avg_err)
################################################################################
################################################################################
###############################################################################
bd1,bc1 = np.array(bd1), np.array(bc1)
def test(trd, trc, ted, tec):
print('gbc', '\n')
gbc = GaussBayesClassify(trd, trc)
print(gbc, '\n')
# print(gbc.predict(ted), '\n')
# print(gbc.predict_soft(ted), '\n')
# print(gbc.confusion(ted, tec), '\n')
# print(gbc.auc(ted, tec), '\n')
# print(gbc.roc(ted, tec), '\n')
err = gbc.err(ted, tec)
print(err, '\n')
return err
avg_err = test_randomly(data, classes, 0.8, test)
print('avg_err')
print(avg_err)
## DETERMINISTIC TESTING #######################################################
#
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/classifier-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# classes = [float(row[-1].lower()) for row in csv.reader(open('../data/classifier-data.csv'))]
# trc = np.asarray(classes[0:40] + classes[50:90] + classes[100:140])
# tec = np.asarray(classes[40:50] + classes[90:100] + classes[140:150])
#
# btrd = trd[0:80,:]
# bted = ted[0:20,:]
if __name__ == "__main__":
## RANDOM TESTING ##############################################################
data, predictions = load_data_from_csv("../data/regressor-data.csv", -1, float)
data, predictions = arr(data), arr(predictions)
def test(trd, trc, ted, tec):
print("knnr", "\n")
knnr = KNNRegress(trd, trc)
print(knnr, "\n")
err = knnr.mae(ted, tec)
print(err, "\n")
return err
avg_err = test_randomly(data, predictions, 0.8, test)
print("avg_err")
print(avg_err)
## DETERMINISTIC TESTING #######################################################
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/regressor-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# trd2 = np.asarray(data[150:180] + data[200:230] + data[250:280])
# ted2 = np.asarray(data[180:200] + data[230:250] + data[280:300])
# trd3 = np.asarray(data[300:320] + data[350:370] + data[400:420])
# ted3 = np.asarray(data[320:350] + data[370:400] + data[420:450])
# predictions = [float(row[-1].lower()) for row in csv.reader(open('../data/regressor-data.csv'))]
# trp = np.asarray(predictions[0:40] + predictions[50:90] + predictions[100:140])
print('lr.predict(ted)')
print(lr.predict(ted))
err = lr.mse(ted, tec)
print('lr.mse(ted, tec) =', err)
err = lr.mae(ted, tec)
print('lr.mae(ted, tec) =', err)
err = lr.rmse(ted, tec)
print('lr.rmse(ted, tec) =', err)
return err
avg_err = test_randomly(X, Y, 0.8, test=test, end=100)
print('avg_err')
print(avg_err)
## DETERMINISTIC TESTING #######################################################
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/regressor-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# trd2 = np.asarray(data[150:180] + data[200:230] + data[250:280])
# ted2 = np.asarray(data[180:200] + data[230:250] + data[280:300])
# trd3 = np.asarray(data[300:320] + data[350:370] + data[400:420])
# ted3 = np.asarray(data[320:350] + data[370:400] + data[420:450])
#
# predictions = [float(row[-1].lower()) for row in csv.reader(open('../data/regressor-data.csv'))]
print('lr.predict(ted)')
print(lr.predict(ted))
err = lr.mse(ted, tec)
print('lr.mse(ted, tec) =', err)
err = lr.mae(ted, tec)
print('lr.mae(ted, tec) =', err)
err = lr.rmse(ted, tec)
print('lr.rmse(ted, tec) =', err)
return err
avg_err = test_randomly(X, Y, 0.8, test=test, end=100)
print('avg_err')
print(avg_err)
## DETERMINISTIC TESTING #######################################################
# data = [[float(val) for val in row[:-1]] for row in csv.reader(open('../data/regressor-data.csv'))]
# trd = np.asarray(data[0:40] + data[50:90] + data[100:140])
# ted = np.asarray(data[40:50] + data[90:100] + data[140:150])
# trd2 = np.asarray(data[150:180] + data[200:230] + data[250:280])
# ted2 = np.asarray(data[180:200] + data[230:250] + data[280:300])
# trd3 = np.asarray(data[300:320] + data[350:370] + data[400:420])
# ted3 = np.asarray(data[320:350] + data[370:400] + data[420:450])
#
# predictions = [float(row[-1].lower()) for row in csv.reader(open('../data/regressor-data.csv'))]