def cluster(self,
assignAndReturnDetails=False,
numberOfTopFeatures=5,
algorithmSource='nltk',
**kwargs):
bestFeatures, error = {}, None
if algorithmSource == 'nltk':
clusterer = cluster.KMeansClusterer(self.numberOfClusters,
euclidean_distance, **kwargs)
clusters = clusterer.cluster(self.vectors, True)
means = clusterer.means()
for id, mean in zip(clusterer.cluster_names(), means):
bestFeatures[id] = [
(dimension, score) for dimension, score in
sorted(zip([
self.dimensions.get(Clustering.DIMENSION_TO_PHRASE, i)
for i in range(len(mean))
], mean),
key=itemgetter(1),
reverse=True)[:numberOfTopFeatures] if score > 0
]
elif algorithmSource == 'biopython':
from Bio.Cluster import kcluster, clustercentroids
clusters, error, _ = kcluster(self.vectors,
nclusters=self.numberOfClusters,
npass=kwargs['repeats'])
means, _ = clustercentroids(self.vectors, self.masks, clusters)
means = [unitVector(c) for c in means]
for id, mean in zip(range(len(means)), means):
bestFeatures[id] = [
(dimension, score) for dimension, score in
sorted(zip([
self.dimensions.get(Clustering.DIMENSION_TO_PHRASE, i)
for i in range(len(mean))
], mean),
key=itemgetter(1),
reverse=True)[:numberOfTopFeatures] if score > 0
]
if assignAndReturnDetails:
documentAssignments = sorted(
[(docId, clusterId)
for docId, clusterId in zip(self.docIds, clusters)],
key=itemgetter(1))
clusters = dict(
(clusterId, [t[0] for t in documents])
for clusterId, documents in groupby(documentAssignments,
key=itemgetter(1)))
return {
'clusters': clusters,
'bestFeatures': bestFeatures,
'error': error
}
return clusters
def cluster(self, assignAndReturnDetails=False, numberOfTopFeatures = 5, algorithmSource='nltk', **kwargs):
bestFeatures, error = {}, None
if algorithmSource=='nltk':
clusterer = cluster.KMeansClusterer(self.numberOfClusters, euclidean_distance, **kwargs)
clusters = clusterer.cluster(self.vectors, True)
means = clusterer.means()
for id, mean in zip(clusterer.cluster_names(), means): bestFeatures[id]=[(dimension, score) for dimension, score in sorted(zip([self.dimensions.get(Clustering.DIMENSION_TO_PHRASE, i) for i in range(len(mean))], mean), key=itemgetter(1), reverse=True)[:numberOfTopFeatures] if score>0]
elif algorithmSource=='biopython':
from Bio.Cluster import kcluster, clustercentroids
clusters, error, _ = kcluster(self.vectors, nclusters=self.numberOfClusters, npass=kwargs['repeats'])
means, _ = clustercentroids(self.vectors, self.masks, clusters)
means = [unitVector(c) for c in means]
for id, mean in zip(range(len(means)), means): bestFeatures[id]=[(dimension, score) for dimension, score in sorted(zip([self.dimensions.get(Clustering.DIMENSION_TO_PHRASE, i) for i in range(len(mean))], mean), key=itemgetter(1), reverse=True)[:numberOfTopFeatures] if score>0]
if assignAndReturnDetails:
documentAssignments=sorted([(docId, clusterId)for docId, clusterId in zip(self.docIds, clusters)], key=itemgetter(1))
clusters = dict((clusterId, [t[0] for t in documents]) for clusterId, documents in groupby(documentAssignments, key=itemgetter(1)))
return {'clusters': clusters, 'bestFeatures': bestFeatures, 'error': error}
return clusters
[], [], [], [], [], [], [], [], [], [], [], [], [], [], [], []]
corr = [[], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [],
[], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [],
[], [], [], [], [], [], [], [], [], [], [], [], [], [], [], []]
dataset = []
clusterid, error, nfound = kcluster(X_features, cluster_number, None, None,
1, 1, 'a', 'c', None)
X_features = np.transpose(X_features)
for i in range(len(clusterid)):
dst[clusterid[i]].append(X_features[i])
X_features = np.transpose(X_features)
cdata, cmask = clustercentroids(X_features, None, clusterid, 'a', 1)
cdata = np.transpose(cdata)
for i in range(len(corr)):
for j in range(len(dst[i])):
cr, p_val = pearsonr(dst[i][j], cdata[i])
corr[i].append(cr)
ddst = []
accuracy_final = 0.0
for i in range(cluster_rep):
done = False
for j in range(len(dst)):
if i > len(dst):
done = True
# -*- coding: utf-8 -*-
"""
Created on Mon Aug 26 21:31:00 2019
bio.cluster.clustercentriods Test
@author: Administrator
"""
from sklearn.preprocessing import MinMaxScaler
from Bio.Cluster import kcluster
from Bio.Cluster import clustercentroids
import pandas as pd
df_full = pd.read_csv('../data/FCM_testdata.csv')
print(df_full.head(5))
print('size of df_full with real_labels:', df_full.shape)
columns = list(df_full.columns)
features = columns[:len(columns) - 1]
df = df_full[features]
print(df.head(5))
print('size of df without real_labels:', df.shape)
minMax = MinMaxScaler()
print(minMax)
dataset = minMax.fit_transform(df)
print(dataset[0:10, :])
clusterid1, error, nfound = kcluster(dataset, nclusters=3, dist='e', npass=100)
cdata, cmask = clustercentroids(dataset, clusterid=clusterid1)