def test_validation(self):
with self.assertRaises(ValueError):
# More clusters than samples
nw = RBFKMeans(n_clusters=1000)
nw.train(self.data, epsilon=1e-5)
with self.assertRaises(ValueError):
# Number of clusters the same as number of samples
nw = RBFKMeans(n_clusters=self.data.shape[0])
nw.train(self.data, epsilon=1e-5)
with self.assertRaises(ValueError):
# One cluster
nw = RBFKMeans(n_clusters=1)
nw.train(self.data, epsilon=1e-5)
def test_classification(self):
result = np.array([
[0.228, 0.312],
[0.48166667, 0.76666667],
])
nw = RBFKMeans(n_clusters=2)
nw.train(self.data, epsilon=1e-5)
self.assertTrue(np.all(result == np.round(nw.centers, 8)))
if self.draw_plot:
classes = nw.predict(self.data)
for i, center in enumerate(nw.centers):
positions = np.argwhere(classes[:, 0] == i)
class_data = np.take(self.data, positions[:, 0], axis=0)
plt.plot(class_data[:, 0], class_data[:, 1], 'o')
for center in nw.centers:
plt.plot(center[0], center[1], 'kx')
plt.axis([0, 1, 0, 1])
plt.show()
import numpy as np
from neupy.algorithms import RBFKMeans
from mnist import MNIST
mnistData=MNIST('./mnistData')
imgTrain,lblTrain=mnistData.load_training()
imgTest,lblTest=mnistData.load_testing()
data = np.array(imgTrain)
rbfk_net = RBFKMeans(n_clusters=40, verbose=False)
rbfk_net.train(data, epsilon=1e-5)
print len(rbfk_net.centers)
new_data = np.array(imgTest[1])
print rbfk_net.predict(new_data).shape
X = df.drop(['Grade'], axis=1)
Y = df.Grade
#Using Built in train test split function in sklearn
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
# RBF and kmeans clustering by class
#Number of prototypes
#prototypes = int(input("Number of seed points:"))
prototypes = 12
#Finding cluster centers
df_cluster = X_train
df_cluster[
'Grade'] = Y_train #Reproduce original data but only with training values
rbfk_net = RBFKMeans(
n_clusters=prototypes) #Chose number of clusters that you want
rbfk_net.train(df_cluster, epsilon=1e-5)
center = pd.DataFrame(rbfk_net.centers)
# Turn the centers into prototypes values needed
X_prototypes = center.iloc[:, 0:-1]
Y_prototypes = center.iloc[:,
-1] #Y_prototypes is the last column of center since 'Grade' is the last feature added to center.
#Train GRNN
GRNNet = GRNN(std=0.1)
GRNNet.train(X_prototypes, Y_prototypes)
# Cross validataion
score = cross_val_score(GRNNet, X_train, Y_train, scoring='r2', cv=5)
print("")
#print("")
ClassD_df = data_train[data_train['Letter'].isin(['D'])]
ClassD_data = ClassD_df.drop(['Letter'], axis=1)
#print (ClassD_data)
#print("")
# RBF and kmeans clustering by class
#Number of prototypes
#prototypes = int(input("Number of prototypes:"))
prototypes = 4
eps = 1e-5
#Finding cluster centers
rbfk_netA = RBFKMeans(
n_clusters=prototypes) #Chose number of clusters that you want
rbfk_netA.train(ClassA_data, epsilon=eps)
center_classA = pd.DataFrame(rbfk_netA.centers)
rbfk_netB = RBFKMeans(n_clusters=prototypes)
rbfk_netB.train(ClassB_data, epsilon=eps)
center_classB = pd.DataFrame(rbfk_netB.centers)
rbfk_netC = RBFKMeans(n_clusters=prototypes)
rbfk_netC.train(ClassC_data, epsilon=eps)
center_classC = pd.DataFrame(rbfk_netC.centers)
#Defining my Y_train
letter_classA = ['A'] * prototypes
letter_classB = ['B'] * prototypes
letter_classC = ['C'] * prototypes