import numpy as np
import matplotlib.pyplot as plt
from classify import classify
from file_import import file_import
from nearest_points import nearest_points_naive_l1
from nearest_points import nearest_points_naive_sup
from nearest_points import nearest_points_opt_l1
from nearest_points import nearest_points_opt_sup
from scipy.spatial import KDTree
train = file_import("bananas-2-2d.train.csv")
test = file_import("bananas-2-2d.test.csv")
test_index = np.int(np.random.rand() * len(test))
k = 100
plt.figure(1)
nearest = nearest_points_naive_sup(test[test_index, :], train, k)
rest = [i for i in range(len(train)) if i not in nearest]
plt.scatter(train[nearest, 1], train[nearest, 2], s=0.6, c='r')
plt.scatter(train[rest, 1], train[rest, 2], s=0.6, c='k')
plt.scatter(test[test_index, 1], test[test_index, 2], s=1.5, c='b')
plt.figure(2)
nearest = nearest_points_naive_l1(test[test_index, :], train, k)
rest = [i for i in range(len(train)) if i not in nearest]
plt.scatter(train[nearest, 1], train[nearest, 2], s=0.6, c='r')
plt.scatter(train[rest, 1], train[rest, 2], s=0.6, c='k')
plt.scatter(test[test_index, 1], test[test_index, 2], s=1.5, c='b')
plt.figure(3)
nearest = nearest_points_opt_sup(test[test_index, :], train, k)
def classify(nametest, nametrain, Kset, l):
test = file_import(nametest)
train = file_import(nametrain)
D_test = test[:, 1:]
D_train = train[:, 1:]
n = len(train)
großk = int(max(Kset))
index_array = np.zeros((n, großk), dtype=int)
m_i = 0
tic = time.time()
for i in range(l):
block_size = n // l
train_i = train[i * block_size:(i + 1) * block_size, :]
a_i = train[0:i * block_size, :]
b_i = train[(i + 1) * block_size:, :]
train_strich_i = np.vstack((a_i, b_i))
D_train_i = train_i[:, 1:] #erste Spalte nicht dran
c_i = D_train[0:i * block_size, :]
d_i = D_train[(i + 1) * block_size:, :]
D_train_strich_i = np.vstack((c_i, d_i))
index_array_i = np.zeros((m_i, großk), dtype=int)
for j in range(0, len(D_train_i)):
index_j_i = nearest_points_naive_sup_2(D_train_i[j, :],
D_train_strich_i, großk)
index_array[m_i + j, :] = index_j_i
m_i = m_i + len(D_train_i)
toc = time.time()
print("%.10f seconds" % (toc - tic))
list_ks = []
tic = time.time()
for k in Kset:
errorarray = []
for i in range(l):
m_i = len(D_train_i)
block_size = n // l
train_i = train[i * block_size:(i + 1) * block_size, :]
a_i = train[0:i * block_size, :]
b_i = train[(i + 1) * block_size:, :]
train_strich_i = np.vstack((a_i, b_i))
D_train_i = train_i[:, 1:] #erste Spalte nicht dran
c_i = D_train[0:i * block_size, :]
d_i = D_train[(i + 1) * block_size:, :]
D_train_strich_i = np.vstack((c_i, d_i))
index_array_i = np.zeros((m_i, großk), dtype=int)
C_i = []
for j in range(0, m_i):
if train_i[j, 0] == np.sign(
np.sum(train_strich_i[index_array[m_i + j, :int(k)],
0])):
c = 0
else:
c = 1
C_i.append(c)
m_i += len(D_train_i)
error_classification_i = 1 / m_i * sum(C_i)
errorarray.append(error_classification_i)
middle_k = (1 / l) * sum(errorarray)
list_ks.append(middle_k)
toc = time.time()
print("%.10f seconds" % (toc - tic))
print(list_ks)
print(
[np.abs(list_ks[i] - list_ks[i + 1]) for i in range(len(list_ks) - 1)])
print(list_ks.index(min(list_ks)))
def classify(file_name, KSET, l):
tic = time.time()
k_max = max(KSET)
test = file_import(
file_name + ".test.csv") # Vollständiges Array; Enthält Klassifikation
train = file_import(file_name + ".train.csv") # dito
n = train.shape[0] # Anzahl Punkte
m = train.shape[
1] # Anzahl Dimensionen; Beachte: Enthält die Klassifikation
index_array = np.zeros(
(n, k_max), dtype=int
) # Enthält alle Indizes der k_max nächsten Nachbarn aller Punkte
block_size = n // l # Größe der D_i
D_i_array = np.zeros(
(l, block_size, m)) # Zu untersuchende Punkte von train
D_strich_i_array = np.zeros(
(l, block_size * (l - 1), m)) # Zu vergleichende Punkte von train
for i in range(l):
# Erzeuge alle benötigten Arrays an Punkten, i wird in der ersten Koordinate dieser Arrays indiziert
D_i_array[i] = train[i * block_size:(i + 1) * block_size, :]
lower_points = train[0:i * block_size, :]
upper_points = train[(i + 1) * block_size:l * block_size, :]
D_strich_i_array[i] = np.vstack((lower_points, upper_points))
toc = time.time()
print("Initialisierung : %.10f seconds" % (toc - tic))
tic = time.time()
for i in range(l):
# Bestimme die k_max nächsten Nachbarn
for j in range(0, block_size):
index_array[block_size * i + j, :] = nearest_points_opt_l1(
D_i_array[i, j, :], D_strich_i_array[i, :, :], k_max) # sic
list_ks = []
toc = time.time()
print("Nächste Nachbarn in train : %.10f seconds" % (toc - tic))
tic = time.time()
new_array = np.zeros(
(l, block_size, k_max)
) # Enthält Summen der Klassifikationen (ohne Signum) der n Punkte zu allen nächsten Nachbarn (bis k_max)
for i in range(l):
for j in range(block_size):
new_array[i, j, :] = np.cumsum(
D_strich_i_array[i, index_array[i * block_size + j, :], 0])
# new_array[i, j, 0] = np.sum(D_strich_i_array[i, index_array[i * block_size + j, 0], 0])
# for k in range(len(KSET) - 1):
# new_array[i, j, k + 1] = new_array[i, j, k] + D_strich_i_array[i, index_array[i * block_size + j, k + 1], 0]
temp1_array = np.sign(new_array)
temp2_array = np.zeros((l, block_size, k_max))
for i in range(l):
for j in range(block_size):
for k in range(len(KSET)):
if temp1_array[i, j, k] == 0:
temp1_array[i, j, k] = 1
if D_i_array[i, j, 0] == temp1_array[i, j, k]:
temp2_array[i, j, k] = 0
else:
temp2_array[i, j, k] = 1
temp3_array = np.sum(temp2_array, 1) / block_size
temp4_array = np.sum(temp3_array, 0) / l
# print(temp4_array)
toc = time.time()
print("Bestimmung von k_stern : %.10f seconds" % (toc - tic))
k_stern = np.argmin(temp4_array)
print("k_stern = " + str(k_stern))
print("Klassifikationsfehlerrate: " + str(temp4_array[k_stern]))
o = len(test)
test_classification = np.zeros(o)
test_index_array = np.zeros((l, o, k_stern), dtype=int)
tic = time.time()
for i in range(l):
for j in range(o):
test_index_array[i, j, :] = nearest_points_opt_l1(
test[j, :], D_strich_i_array[i, :, :], k_stern)
toc = time.time()
print("Nächste Nachbarn von test : %.10f seconds" % (toc - tic))
tic = time.time()
for j in range(o):
temp1 = 0
for i in range(l):
temp2 = np.sign(
np.sum(D_strich_i_array[i, test_index_array[i, j, :], 0]))
temp1 += temp2
if temp2 == 0:
temp1 += 1
test_classification[j] = np.sign(
temp1
) # Empirisch : Wird nicht Null, also keine weitere Abfrage nötig
toc = time.time()
print("Bestimmung der Klassifikation : %.10f seconds" % (toc - tic))
# print(test_classification)
test[:, 0] = test_classification
with open(file_name + ".result.csv", 'w', newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerows(test)
# print(test)
return test
import numpy as np
import time
from file_import import file_import
from nearest_points import nearest_points_naive_l1
from nearest_points import nearest_points_naive_sup
from nearest_points import nearest_points_opt_l1
from nearest_points import nearest_points_opt_sup
from scipy.spatial import KDTree
file_name = "ijcnn1.10000.train.csv"
k = 1
data = file_import(file_name)
n = data.shape[0]
result_array_1 = np.zeros((n, k))
tic = time.time()
for i in range(n):
result_array_1[i, :] = nearest_points_naive_l1(data[i, :], data, k)
toc = time.time()
print("l1-naiv : %.10f seconds" % (toc - tic))
data = file_import(file_name)
n = data.shape[0]
result_array_2 = np.zeros((n, k))
tic = time.time()
for i in range(n):
result_array_2[i, :] = nearest_points_naive_sup(data[i, :], data, k)
toc = time.time()
print("lsup-naiv : %.10f seconds" % (toc - tic))
data = file_import(file_name)
import matplotlib.pyplot as plt from classify import classify from file_import import file_import import numpy as np file_name = "bananas-2-2d" plt.figure(1) set=file_import(file_name + ".train.csv") list_1=[i for i in range(len(set)) if set[i,0]==1] list_2=[i for i in range(len(set)) if set[i,0]==-1] plt.scatter(set[list_1, 1], set[list_1, 2], s=0.6, c="k", label="1") plt.scatter(set[list_2, 1], set[list_2, 2], s=0.6, c="r", label="-1") plt.title(file_name + ".train") plt.legend(markerscale =7.5, title="Klassifikation") plt.figure(2) set=file_import(file_name + ".test.csv") list_1=[i for i in range(len(set)) if set[i,0]==1] list_2=[i for i in range(len(set)) if set[i,0]==-1] plt.scatter(set[list_1, 1], set[list_1, 2], s=0.6, c="k", label="1") plt.scatter(set[list_2, 1], set[list_2, 2], s=0.6, c="r", label="-1") plt.title(file_name + ".test") plt.legend(markerscale =7.5, title="Klassifikation") plt.figure(3) #set = classify(file_name, np.arange(1,200), 5) set=file_import(file_name + ".result.csv") list_1=[i for i in range(len(set)) if set[i,0]==1] list_2=[i for i in range(len(set)) if set[i,0]==-1] plt.scatter(set[list_1, 1], set[list_1, 2], s=0.6, c="k", label="1")