def plot_scatter(self):
'''
Overrides the parent class method. Plots all the data points in 2D.
'''
#Create a clusterer document list to get the index of a doc (horrible hack I know)
clusterer_document_list = [key for key in self.document_dict.keys()]
corpus = nltk.TextCollection([document.tokens for document in self.document_dict.values()])
all_terms_vector = list(set(corpus))
table = construct_orange_table(all_terms_vector)
meta_col_name="cluster_id"
table = add_metas_to_table(table, meta_col_name=meta_col_name)
instances = []
for cluster in self.clusters:
for doc_id, doc_content in cluster.document_dict.iteritems():
index = clusterer_document_list.index(doc_id)
#We use index = 1 to force the function to construct the vector according to all the documents in the collection
self.construct_term_doc_matrix(index, doc_content)
oc = OnlineCluster(self.td_matrix, 1, doc_id, doc_content, self.attributes)
oc.resize(all_terms_vector)
inst = Orange.data.Instance(table.domain, list(oc.center))
inst[meta_col_name] = str(cluster.id)
instances.insert(index, inst)
#we have a table with the clusters ids as metas.
table.extend(instances)
from visualizations.mds import MDS
mds = MDS(table)
classes_list = []
for c in self.clusters:
classes_list.append(c.id)
mds.plot(classes_list=classes_list, class_col_name="cluster_id")
def plot_scatter(self):
'''
Plots all the data points in 2D.
'''
assert self.attributes and self.td_matrix != None
#Create a clusterer document list to get the index of a doc (horrible hack I know)
clusterer_document_list = [key for key in self.document_dict.keys()]
table = construct_orange_table(self.attributes)
meta_col_name="cluster_id"
table = add_metas_to_table(table, meta_col_name=meta_col_name)
instances = []
for cluster in self.clusters:
#A small hack for dbscan noise cluster. It's id is -1 and color scale is wrong if -1
if cluster.id == -1: cluster.id += len(self.clusters);
for doc_id in cluster.document_dict.iterkeys():
index = clusterer_document_list.index(doc_id)
inst = Orange.data.Instance(table.domain, list(self.td_matrix[index]))
inst[meta_col_name] = str(cluster.id)
instances.insert(index, inst)
#we have a table with the clusters ids as metas.
table.extend(instances)
mds = MDS(table)
classes_list = []
for c in self.clusters:
classes_list.append(c.id)
mds.plot(classes_list=classes_list, class_col_name="cluster_id")
def save_table(self, filename):
'''
It stores the term-docuemtn matrix as a tab delimited file
which is supported by Orange.
'''
if self.td_matrix != None:
t = construct_orange_table(self.attributes, self.td_matrix)
t = add_metas_to_table(t, self.document_dict.keys())
orange.saveTabDelimited (filename+".tab", t)
self.table_name = filename
else:
raise Exception("Oops. It seems that you have not constructed a term-document matrix. Use construct_term_document_matrix()")
def save_table(self, filename):
'''
It stores the term-docuemtn matrix as a tab delimited file
which is supported by Orange.
'''
if self.td_matrix != None:
t = construct_orange_table(self.attributes, self.td_matrix)
t = add_metas_to_table(t, self.document_dict.keys())
orange.saveTabDelimited(filename + ".tab", t)
self.table_name = filename
else:
raise Exception(
"Oops. It seems that you have not constructed a term-document matrix. Use construct_term_document_matrix()"
)
def plot_scatter(self):
'''
Overrides the parent class method. Plots all the data points in 2D.
'''
#Create a clusterer document list to get the index of a doc (horrible hack I know)
clusterer_document_list = [key for key in self.document_dict.keys()]
corpus = nltk.TextCollection(
[document.tokens for document in self.document_dict.values()])
all_terms_vector = list(set(corpus))
table = construct_orange_table(all_terms_vector)
meta_col_name = "cluster_id"
table = add_metas_to_table(table, meta_col_name=meta_col_name)
instances = []
for cluster in self.clusters:
for doc_id, doc_content in cluster.document_dict.iteritems():
index = clusterer_document_list.index(doc_id)
#We use index = 1 to force the function to construct the vector according to all the documents in the collection
self.construct_term_doc_matrix(index, doc_content)
oc = OnlineCluster(self.td_matrix, 1, doc_id, doc_content,
self.attributes)
oc.resize(all_terms_vector)
inst = Orange.data.Instance(table.domain, list(oc.center))
inst[meta_col_name] = str(cluster.id)
instances.insert(index, inst)
#we have a table with the clusters ids as metas.
table.extend(instances)
from visualizations.mds import MDS
mds = MDS(table)
classes_list = []
for c in self.clusters:
classes_list.append(c.id)
mds.plot(classes_list=classes_list, class_col_name="cluster_id")