def rand(l1, l2):
"""
Compute the Adjusted Rand Index between two clusterings.
Parameters:
- - - - -
l1, l2 : array
cluster assignments
"""
return ars(l1, l2)
def matchClusteringLabels(filename):
text = [
line.strip()
for line in open('/home/haohanw/metagenomics/clusteringResult_' +
filename + '_filterMouse.txt')
]
result1 = {}
for line in text:
items = line.split('\t')
result1[items[0][1:]] = int(items[1])
rs1 = []
rs2 = []
text = [
line.strip() for line in open('/home/haohanw/metagenomics/Kaiju/' +
filename + '.label')
]
result2 = {}
for line in text:
items = line.split('\t')
rs1.append(int(items[1]))
rs2.append(result1[items[0]])
result2[items[0]] = int(items[1])
print 'organizing results, now calculating'
a = ars(rs1, rs2)
print 'final score', abs(a)
f = open(
'/home/haohanw/metagenomics/clusteringCompare_' + filename + '.txt',
'w')
sorted_result1 = sorted(result1.items(), key=operator.itemgetter(1))
for (n, v) in sorted_result1:
if n in result2:
f.writelines(n + '\t' + str(v) + '\t' + str(result2[n]) + '\n')
f.close()
def train(self):
step = 0
sum = 0
try:
while not self.coord.should_stop():
step += 1
loss, _, norm = self.sess.run([self.loss, self.opt, self.norm])
sum += loss
if step % 500 == 0:
assignments, = self.sess.run(
[self.assignments],
feed_dict={self.test_images: self.raw_images})
print('%s\t%0.4f\t%0.4f\t%0.4f\t%0.4f\t%0.4f\t%0.4f' %
(step, ars(self.labels, assignments),
mis(self.labels,
assignments), v_score(self.labels, assignments),
self.purity_score(self.labels,
assignments), norm, sum / step))
except tf.errors.OutOfRangeError:
print 'Done training'
finally:
self.coord.request_stop()
self.coord.join(self.threads)
model_2._fit_single(X, random_state=None)
# In[5]:
model_2.fit(X)
# In[8]:
model_2.row_labels_
# In[9]:
predicted_labels_2 = model_2.row_labels_
print(nmi(true_labels, predicted_labels_2), acc(true_labels,
predicted_labels_2),
ars(true_labels, predicted_labels_2),
amis(true_labels, predicted_labels_2))
# In[11]:
model_5 = NMTFcoclus_ONM3F.ONM3F(n_row_clusters=4, n_col_clusters=4)
model_5.fit(X)
# In[15]:
predicted_labels_5 = model_5.row_labels_
print(nmi(true_labels, predicted_labels_5), acc(true_labels,
predicted_labels_5),
ars(true_labels, predicted_labels_5),
amis(true_labels, predicted_labels_5))
X = np.append(X, noise, axis = 1) X= normalize(X) # Y = SelfOrganizingSwarm(iterations=250, alpha=1, beta = 0.9,delta=0.001, theta=3).fit_transform(X) # Y = PCA(2).fit_transform(X) # Y =TSNE().fit_transform(X) Y= GSOM().fit_transform(X, lr = 1.0, beta=0.5, sf=0.6, wd=0.175, fd=0.8)#X,lr = 1.0, beta=0.0,sf=0.01, fd=0.75, wd=0.5) # fig = plt.figure() # ax = Axes3D(fig)00 # ax.scatter(X.T[0], X.T.[1], X.T[2],c = color, alpha=0.5, edgecolors='none') # plt.show() plt.subplot(211) # ax = fig.add_subplot(211) plt.scatter(Y.T[0], Y.T[1], s = 15, c = plt.cm.jet(color/(n_clusters*1.0)), edgecolors='none', alpha=0.375) labs = KMeans(n_clusters).fit(Y).labels_ plt.subplot(212) plt.scatter(Y.T[0], Y.T[1], s = 15, c =plt.cm.jet(labs/(n_clusters*1.0)), edgecolors='none', alpha=0.375) print 'ars ', ars(color,labs) print 'ami ', ami(color, labs) # # Y = Isomap().fit_transform(X) # ax2 = fig.add_subplot(121) # ax2.scatter(Y.T[0], Y.T[1], c = color, edgecolors='none', alpha=0.5) plt.show()
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
from sklearn.metrics import adjusted_rand_score as ars
digits_train = pd.read_csv('./data/optdigits.tra', header=None)
digits_test = pd.read_csv('./data/optdigits.tes', header=None)
# 0-63 features, 64 target
X_train = digits_train[np.arange(64)]
y_train = digits_train[64]
X_test = digits_test[np.arange(64)]
y_test = digits_test[64]
kmeans = KMeans(n_clusters=10)
kmeans.fit(X_train)
y_pred = kmeans.predict(X_test)
print(ars(y_test, y_pred))