import numpy as np import decision_trees as dt #Training Set 1: X_train = np.array([ [0,1], [0,0], [1,0], [0,0], [1,1] ]) Y_train = np.array([ [1], [0], [0], [0], [1] ]) #Validation Set 1: X_val = np.array([ [0,0], [0,1], [1,0], [1,1] ]) Y_val = np.array([ [0], [1], [0], [1] ]) #Testing Set 1: X = np.array([ [0,0], [0,1], [1,0], [1,1] ]) Y = np.array([ [1], [1], [0], [1] ]) DT = dt.DT_train_binary(X_train, Y_train, 2) #DT.print_tree() test_acc = dt.DT_test_binary(X, Y, DT) print(test_acc) DT = dt.DT_train_binary_best(X_train, Y_train, X_val, Y_val) #DT.print_tree() test_acc = dt.DT_test_binary(X, Y, DT) print(test_acc) print() #Training Set 2: X_train = np.array([ [0,1,0,0], [0,0,0,1], [1,0,0,0], [0,0,1,1], [1,1,0,1], [1,1,0,0], [1,0,0,1], [0,1,0,1], [0,1,0,0] ]) Y_train = np.array([ [0], [1], [0], [0], [1], [0], [1], [1], [1] ]) #Validation Set 1: X_val = np.array([ [1,0,0,0], [0,0,1,1], [1,1,0,1], [1,1,0,0], [1,0,0,1], [0,1,0,0] ]) Y_val = np.array([ [0], [0], [1], [0], [1], [1] ])
RealX = np.array([[4.8, 3.4, 1.9, 0.2], [5, 3, 1.6, 1.2], [5, 3.4, 1.6, 0.2],
[5.2, 3.5, 1.5, 0.2], [5.2, 3.4, 1.4, 0.2],
[4.7, 3.2, 1.6, 0.2], [4.8, 3.1, 1.6, 0.2],
[5.4, 3.4, 1.5, 0.4], [7, 3.2, 4.7,
1.4], [6.4, 3.2, 4.7, 1.5],
[6.9, 3.1, 4.9, 1.5], [5.5, 2.3, 4, 1.3],
[6.5, 2.8, 4.6, 1.5], [5.7, 2.8, 4.5, 1.3],
[6.3, 3.3, 4.7, 1.6], [4.9, 2.4, 3.3, 1]])
RealY = np.array([[1], [1], [1], [1], [1], [1], [1], [1], [0], [0], [0], [0],
[0], [0], [0], [0]])
print()
print()
print('WRITE UP 1')
max_depth_1 = -1
DT_train_1 = dt.DT_train_binary(trainingX1, trainingY1, max_depth_1)
DT_train_1.toString()
train_acc_1 = dt.DT_test_binary(testingX1, testingY1, DT_train_1)
print('TRAIN1', train_acc_1)
DT_best_1 = dt.DT_train_binary_best(trainingX1, trainingY1, valX1, valY1)
DT_best_1.toString()
best_acc_1 = dt.DT_test_binary(testingX1, testingY1, DT_best_1)
print('BEST1', best_acc_1)
DT_train_2 = dt.DT_train_binary(trainingX2, trainingY2, max_depth_1)
DT_train_2.toString()
train_acc_2 = dt.DT_test_binary(testingX2, testingY2, DT_train_2)
print('TRAIN2', train_acc_2)
DT_best_2 = dt.DT_train_binary_best(trainingX2, trainingY2, valX2, valY2)
Y = []
for item in x_str:
temp = [float(x) for x in item.split(',')]
X.append(temp)
if len(y_str) > 0:
for item in y_str:
temp = int(item)
Y.append(temp)
X = np.array(X)
Y = np.array(Y)
return X, Y
X, Y = load_data("data_1.txt")
max_depth = 3
DT = dt.DT_train_binary(X, Y, max_depth)
test_acc = dt.DT_test_binary(X, Y, DT)
print("DT:", test_acc)
X, Y = load_data("data_4.txt")
acc = nn.KNN_test(X, Y, X, Y, 1)
print("KNN:", acc)
X, Y = load_data("data_5.txt")
mu = np.array([[1], [5]])
mu = kmeans.K_Means(X, 2, mu)
print("KMeans:", mu)
X, Y = load_data("data_6.txt")
mu = kmeans.K_Means(X, 2, [])
print("KMeans:", mu)
import numpy as np
import decision_trees as dt
# Default max depth value
max_depth = 2
# Training Set 1
X_1 = np.array([[0, 1], [0, 0], [1, 0], [0, 0], [1, 1]])
Y_1 = np.array([[1], [0], [0], [0], [1]])
# Validation Set 1
X_val_1 = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
Y_val_1 = np.array([[0], [1], [0], [1]])
# Test Set 1
X_test_1 = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
Y_test_1 = np.array([[1], [1], [0], [1]])
tree = dt.DT_train_binary(X_1, Y_1, max_depth)
test = dt.DT_test_binary(X_test_1, Y_test_1, tree)
tree_best = dt.DT_train_binary_best(X_1, Y_1, X_val_1, Y_val_1)
test_best = dt.DT_test_binary(X_test_1, Y_test_1, tree_best)
print("Training Set 1:")
print("Binary Test (max_depth = 2): ", test)
print("Binary Test (Best Depth): ", test_best)
print("Decision Tree (max_depth = 2): ", tree)
print("Decision Tree (Best Depth): ", tree_best)
# Training Set 2
X_2 = np.array([[0, 1, 0, 0], [0, 0, 0, 1], [1, 0, 0, 0], [0, 0, 1, 1],
[1, 1, 0, 1], [1, 1, 0, 0], [1, 0, 0, 1], [0, 1, 0, 1],
[0, 1, 0, 0]])
YT = np.array([[1], [1], [0], [0], [1], [0], [1], [1], [1]]) max_depth = -1 #DT = dt.DT_train_binary_best(X,Y,XV,YV) #print(DT) #DT = dt.DT_train_binary(X,Y,max_depth) #test_acc = dt.DT_test_binary(XT,YT,DT) #print(test_acc) dinnerX = np.array([[1, 1, 1, 0, 1, 1, 0], [0, 0, 1, 1, 0, 1, 1], [0, 1, 0, 0, 1, 0, 0], [1, 1, 0, 1, 0, 0, 1], [1, 0, 1, 0, 1, 1, 1], [1, 1, 0, 1, 1, 0, 1], [1, 1, 0, 0, 1, 1, 0], [0, 0, 0, 1, 0, 1, 1]]) dinnerY = np.array([[1], [1], [0], [1], [0], [1], [1], [0]]) dinnerTX = np.array([[0, 1, 1, 1, 0, 1, 0], [0, 1, 1, 1, 0, 0, 1], [1, 0, 0, 1, 1, 0, 0]]) dinnerTY = np.array([[0], [1], [0]]) DT1 = dt.DT_train_binary(dinnerX[:5],dinnerY[:5],5) #print(dt.DT_test_binary(dinnerTX,dinnerTY,DT1)) DT2 = dt.DT_train_binary(dinnerX[-5:],dinnerY[-5:],5) #print(dt.DT_test_binary(dinnerTX,dinnerTY,DT2)) DT3 = dt.DT_train_binary(dinnerX[1:6],dinnerY[1:6],5) #print(dt.DT_test_binary(dinnerTX,dinnerTY,DT3)) real = np.array([[4.8, 3.4, 1.9, 0.2], [5, 3, 1.6, 1.2], [5, 3.4, 1.6, 0.2], [5.2, 3.5, 1.5, 0.2], [5.2, 3.4, 1.4, 0.2], [4.7, 3.2, 1.6, 0.2], [4.8, 3.1, 1.6, 0.2], [5.4, 3.4, 1.5, 0.4], [7, 3.2, 4.7, 1.4], [6.4, 3.2, 4.7, 1.5], [6.9, 3.1, 4.9, 1.5], [5.5, 2.3, 4, 1.3], [6.5, 2.8, 4.6, 1.5], [5.7, 2.8, 4.5, 1.3], [6.3, 3.3, 4.7, 1.6], [4.9, 2.4, 3.3, 1]]) realL = np.array([[1], [1], [1], [1], [1], [1], [1], [1], [0], [0], [0], [0], [0], [0], [0], [0]]) DT = dt.DT_train_real(real,realL,-1) exit(1)
import decision_trees as dt
import numpy as np
# Test Data
# X = np.array([[0,1], [0,0], [1,0], [0,0], [1,1]]) # Training Set 1
# Y = np.array([[1], [0], [0], [0], [1]]) # Training labels 1
X = np.array([[1, 1, 0, 0], [1, 1, 1, 1], [1, 1, 1, 1], [0, 0, 0, 1],
[0, 0, 1, 1], [0, 0, 1, 0], [0, 0, 0, 0], [1, 0, 1, 0],
[1, 1, 1, 0], [0, 0, 1, 1]])
Y = np.array([[0], [1], [1], [0], [0], [1], [0], [0], [1], [0]])
DT = dt.DT_train_binary(X, Y, 1)
test_acc = dt.DT_test_binary(X, Y, DT)
print("ACC:", test_acc)
first_five = [training_one[i] for i in range(5)]
label_first = [label_one[i] for i in range(5)]
middle_five = [training_one[i] for i in range(2, 7)]
label_middle = [label_one[i] for i in range(2, 7)]
last_five = [training_one[i] for i in range(3, 8)]
label_last = [label_one[i] for i in range(3, 8)]
"""
first_tree = dt.DT_train_binary(first_five, label_first, 5)
acc = dt.DT_test_binary(first_five, label_first, first_tree)
#print(acc)
middle_tree = dt.DT_train_binary(middle_five, label_middle, 5)
acc = dt.DT_test_binary(middle_five, label_middle, middle_tree)
#print(acc)
"""
last_tree = dt.DT_train_binary(last_five, label_last, 5)
acc = dt.DT_test_binary(last_five, label_last, last_tree)
#print(acc)
"""
result = dt.DT_make_prediction(sample_1, first_tree)
print("result of sample 1 on first tree: " + str(result))
result = dt.DT_make_prediction(sample_2, first_tree)
print("result of sample 2 on first tree: " + str(result))
result = dt.DT_make_prediction(sample_3, first_tree)
print("result of sample 3 on first tree: " + str(result))
"""
"""
result = dt.DT_make_prediction(sample_1, middle_tree)
print("result of sample 1 on middle tree: " + str(result))
result = dt.DT_make_prediction(sample_2, middle_tree)
print("result of sample 2 on middle tree: " + str(result))