def train_KMeans_train():
"""
Test that KMeans has a working train abstract method
"""
some = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]])
m = KMeans(some)
assert m.train()
# Finally, select only the relevant information for clustering data = data.iloc[:, 4:] data = (data - data.min()) / (data.max() - data.min()) # assignment arguments to variables kCount = args.kCount outName = args.outName numExp = args.numExp convCount = args.convCount numIters = args.numIters reassignThresh = args.reassignThresh # run kMeans clustering clusterer = KMeans(kCount, numIters, reassignThresh) clusterer.train(data) finalCentroids = clusterer.clusters # plotting native contacts vs RMSD nativeContacts = data['NC'] rmsd = data['rmsd'] blah = finalCentroids[:, [0, 7]] plt.scatter(rmsd, nativeContacts) plt.scatter(blah[:,0], blah[:,1], c='r', marker ='x', s = 20) plt.show()
"""
A working demo using KMeans
"""
import numpy as np
import scipy.io as sio
import matplotlib.pyplot as plt
data = sio.loadmat('data.mat')
X = np.array(data['X'])
from KMeans import KMeans
k = 3
est = KMeans(k)
c = est.train(X)
colors=np.array(['green', 'red', 'blue'])
# lets plot on matplotlib
for i in range(k):
x = X[np.where(c == i)[0]]
plt.scatter(x[:, 0], x[:, 1], color=colors[i])
# plt.savefig('clustering_example.png')
plt.show()
"""
A working demo using KMeans
"""
import numpy as np
import scipy.io as sio
import matplotlib.pyplot as plt
data = sio.loadmat('data.mat')
X = np.array(data['X'])
from KMeans import KMeans
k = 3
est = KMeans(k)
c = est.train(X)
colors = np.array(['green', 'red', 'blue'])
# lets plot on matplotlib
for i in range(k):
x = X[np.where(c == i)[0]]
plt.scatter(x[:, 0], x[:, 1], color=colors[i])
# plt.savefig('clustering_example.png')
plt.show()
