def load(node_file, matrix_up, matrix_down, conjunction_file):
trust = TrustNetwork()
nodes = divisi2.load(node_file)
trust.nodes = OrderedSet(nodes)
trust._fast_matrix_up = divisi2.load(matrix_up)
trust._fast_matrix_down = divisi2.load(matrix_down)
trust._fast_conjunctions = divisi2.load(conjunction_file)
return trust
def load(node_file, matrix_up, matrix_down, conjunction_file):
trust = TrustNetwork()
nodes = divisi2.load(node_file)
trust.nodes = OrderedSet(nodes)
trust._fast_matrix_up = divisi2.load(matrix_up)
trust._transition_matrix = divisi2.load(matrix_down)
trust._fast_conjunctions = divisi2.load(conjunction_file)
return trust
def load(node_file, matrix_file, conjunction_file):
trust = BeliefNetwork()
nodes = divisi2.load(node_file)
for node in nodes:
trust.nodes.add(node)
trust.node_objs[node] = Node(node)
trust._fast_matrix = divisi2.load(matrix_file)
trust._fast_conjunctions = divisi2.load(conjunction_file)
return trust
def make_sim():
# Get similarity from the expanded version of ConceptNet.
# This is not blended with anything yet.
conceptnet = divisi2.load('conceptnet_big.pickle') #.normalize_all()
U, S, V = conceptnet.svd(k=100)
sim = divisi2.reconstruct_similarity(U, S, offset=0.1)
return sim
def createTuples(filePath):
print "Creating Tuples..."
proj = divisi2.load(filePath)
labels = proj.row_labels
d = dict()
for i in range(len(labels)):
d[tuple(proj[i])] = labels[i]
return d
def createTuples(filePath):
print "Creating Tuples..."
proj = divisi2.load(filePath)
labels = proj.row_labels
d = dict()
for i in range(len(labels)):
d[tuple(proj[i])] = labels[i]
return d
def make_exclude_file(game):
overlist = []
gamematix = divisi2.load(game + '.pickle')
nouns = gamematix.row_labels
overlist += nouns
overlist += verb_reader(game+'.inf')
overlist = [x.lower() for x in overlist]
return overlist
def make_blend(thefile):
conceptnet = divisi2.network.conceptnet_matrix('en')
thegame = divisi2.load(thefile).normalize_all()
blended_matrix = blend(conceptnet, thegame)
u,s,v = blended_matrix().svd()
similarity = divisi2.reconstruct_similarity(u,s)
pd[thefile.split('.')[0]] = similarity
return similarity
def make_blend(thefile):
conceptnet = divisi2.network.conceptnet_matrix('en').normalize_all()
thegame = divisi2.load(thefile).normalize_all()
blended_matrix = blend([conceptnet, thegame], [0.9, 0.1])
u,s,v = blended_matrix.svd()
similarity = divisi2.reconstruct_similarity(u, s) # offset=1.5)
pd.mkdir(thefile.split('.')[0])
pd[thefile.split('.')[0]]['blend'] = similarity
return similarity
def getSMatrix(self):
if 'smatrix' in self.cache:
return self.cache['smatrix']
graphFilename = self.graph.exported()
if not graphFilename:
graphFilename = self.graph.export()
self.graph.save()
matrix = divisi2.load(graphFilename)
smatrix = divisi2.network.sparse_matrix(matrix, 'nodes', 'features', cutoff=1)
self.cache['smatrix'] = smatrix
return smatrix
def __init__(self,db=None,mat_string=None):
self.d={}
self.ideas_list=[]
self.related_ideas_dict={}
self.f=None
self.read_from_file(db)
#create a sparse matrix from ideas.
if mat_string==None:
self.idea_matrix=divisi2.SparseMatrix.square_from_named_entries([(0,0,0)])
else:
self.idea_matrix=divisi2.load(mat_string)
self.categories=None
def generate():
ccipca = CCIPCAProcessor((8193, 200), plot=False)
ccipca.output_ccipca = CCIPCA(divisi2.load('chess.eigs'))
pipe = ronwtools.Pipeline(
ronwtools.AudioSource('../koyaanisqatsi.ogg'),
ronwtools.Mono(),
ronwtools.STFT(nfft=16384, nhop=4096, winfun=np.hanning),
ccipca,
ronwtools.ISTFT(nfft=16384, nhop=4096, winfun=np.hanning),
ronwtools.Framer(1048576)
)
for segment in pipe:
print np.max(segment)
segment /= np.max(segment)
audiolab.play(segment)
def create(filePath, resultPath):
f = open('spectralMatrix.txt', 'w')
proj = divisi2.load(filePath)
labels = proj.row_labels
for i in labels:
f.write(i + ' ')
count = 0
p = proj.row_named(i)
while count < len(p):
if count == len(p) - 1:
f.write(str(p[count]) + '\n')
else:
f.write(str(p[count]) + ' ')
count += 1
f.close()
def create(filePath, resultPath):
f = open('spectralMatrix.txt', 'w')
proj = divisi2.load(filePath)
labels = proj.row_labels
for i in labels:
f.write(i+' ')
count = 0
p = proj.row_named(i)
while count < len(p):
if count == len(p) - 1:
f.write(str(p[count]) + '\n')
else:
f.write(str(p[count])+' ')
count+=1
f.close()
def createSpectralMatrix():
# proj is a ReconstructedMatrix of the form terms:terms.
proj = divisi2.load('C:\Users\LLPadmin\Desktop\luminoso\ThaiFoodStudy\Results\spectral.rmat')
# create sparse matrix for clusters of the form terms:clusters (row, col).
clusterMatrix, cluster_names, term_names, termsDict = randomClustersMatrix(proj.col_labels, 10)
count = 0
while True:
count += 1
clusterMatrix = divisi2.aligned_matrix_multiply(proj.left, divisi2.aligned_matrix_multiply(proj.right,clusterMatrix))
repeat = normalize(clusterMatrix, termsDict, cluster_names, term_names)
if repeat:
print count
break
return clusterMatrix
def correlate():
ccipca = CCIPCAProcessor((8193, 200), plot=False, amnesia=1.0)
ccipca.ccipca = CCIPCA(divisi2.load('chess.eigs'))
ccipca.ccipca.iteration = 100000
ccipca.output_ccipca = ccipca.ccipca
pipe = ronwtools.Pipeline(
ronwtools.AudioSource('../chess.ogg'),
ronwtools.Mono(),
ronwtools.STFT(nfft=16384, nhop=4096, winfun=np.hanning),
ccipca,
ronwtools.ISTFT(nfft=16384, nhop=4096, winfun=np.hanning),
ronwtools.Framer(1048576)
)
for segment in pipe:
print np.max(segment)
segment /= np.max(segment)
audiolab.play(segment)
def createSpectralMatrix(k):
# proj is a ReconstructedMatrix of the form terms:terms.
proj = divisi2.load(os.path.abspath('../../ThaiFoodStudy')+'/Results/spectral.rmat')
#proj = examples.spreading_activation()
# create sparse matrix for clusters of the form terms:clusters (row, col).
clusterMatrix, cluster_names, term_names, termsDict = randomClustersMatrix(proj.row_labels, k)
count = 0
while True:
count += 1
print count
clusterMatrix = divisi2.aligned_matrix_multiply(proj.left, divisi2.aligned_matrix_multiply(proj.right,clusterMatrix))
repeat = normalize(clusterMatrix, termsDict, cluster_names, term_names)
if repeat:
print "Aftert "+str(count)+" iterations, we got acceptable clusters."
break
return clusterMatrix
def createSpectralMatrix(k):
# proj is a ReconstructedMatrix of the form terms:terms.
proj = divisi2.load(
os.path.abspath('../../ThaiFoodStudy') + '/Results/spectral.rmat')
#proj = examples.spreading_activation()
# create sparse matrix for clusters of the form terms:clusters (row, col).
clusterMatrix, cluster_names, term_names, termsDict = randomClustersMatrix(
proj.row_labels, k)
count = 0
while True:
count += 1
print count
clusterMatrix = divisi2.aligned_matrix_multiply(
proj.left,
divisi2.aligned_matrix_multiply(proj.right, clusterMatrix))
repeat = normalize(clusterMatrix, termsDict, cluster_names, term_names)
if repeat:
print "Aftert " + str(
count) + " iterations, we got acceptable clusters."
break
return clusterMatrix
def get_matrices(self):
return dict((os.path.basename(filename), divisi2.load(filename))
for filename in self.get_matrices_files()
if filename.endswith('.smat'))
def game_synonyms(game, threshold=1):
dict = {}
for obj in divisi2.load(game + '.pickle').row_labels:
dict[obj] = [ x[0] for x in game_sims(game, obj, threshold=threshold) ]
return dict
def get_matrices(self):
return dict((os.path.basename(filename), divisi2.load(filename))
for filename in self.get_matrices_files()
if filename.endswith('.smat'))
def load(db):
db.idea_matrix=divisi2.load("idea_mat.pickle")
from csc import divisi2
import numpy as np
import json, luminoso2, time, urllib2
from divisi2 import DenseMatrix
from csc_utils.ordered_set import OrderedSet
from charm_exceptions import *
#model = luminoso2.load('pldb_2011_may')
model = luminoso2.load('hack_2011_oct/Model')
sponsormat = divisi2.load("sponsors.dmat")
doc_matrix = model.get_doc_matrix('pldb')
tag_matrix = model.get_tag_matrix()
tag_matrix = model.get_tag_matrix()
tag_matrix = DenseMatrix.concatenate(tag_matrix, sponsormat)
for i in xrange(doc_matrix.shape[0]):
doc_matrix.row_labels[i] = doc_matrix.row_labels[i].replace('hack_2011_oct/Documents', 'PLDBDocs')
# print doc_matrix.row_labels[i]
def get_related_sponsors(email, n=10):
if not ('sponsor', email) in tag_matrix.row_labels:
return []
vec = tag_matrix.row_named(('sponsor', email))
got = divisi2.dot(tag_matrix, vec)
results = []
for tag, weight in got.top_items(len(got)):
key, value = tag
if key == 'sponsor':
results.append((value, weight))
if len(results) >= n:
