def main():
parser = gen_args()
args = parser.parse_args()
sessionid = args.sessionid
logger = logging.getLogger(__name__)
logger.addHandler(logging.StreamHandler())
if args.verbose:
logger.setLevel(logging.DEBUG)
if args.classical:
normalize = True
else:
normalize = False
if args.opinion:
corpus = corpusutil.create(args.opinion)
logger.debug("Number of documents in corpus: %d ", len(corpus))
if args.stopwords:
stopwords = args.stopwords.read().split()
datacreator = corpusutil.GenerateVectors(corpus = corpus, mindfpercent\
= args.mindfpercent,\
maxdfpercent =\
args.maxdfpercent,\
minfrequency =\
args.minfrequency,\
verbose = args.verbose,\
usebigrams = args.usebigrams,\
normalize = normalize,\
tf = args.tf,\
stopwords = stopwords)
else:
datacreator = corpusutil.GenerateVectors(corpus = corpus, mindfpercent\
= args.mindfpercent,\
maxdfpercent =\
args.maxdfpercent,\
minfrequency =\
args.minfrequency,\
verbose = args.verbose,\
usebigrams = args.usebigrams,\
normalize = normalize,\
tf = args.tf,\
stopwords = None)
result = datacreator.create()
docids = result['docids']
featuredict = result['featuredict']
elif args.corpus:
corpus = cPickle.load(args.corpus)
logger.debug("Number of documents in corpus: %d ", len(corpus))
if args.stopwords:
stopwords = args.stopwords.read().split()
datacreator = corpusutil.GenerateVectors(corpus = corpus, mindfpercent\
= args.mindfpercent,\
maxdfpercent =\
args.maxdfpercent,\
minfrequency =\
args.minfrequency,\
verbose = args.verbose,\
usebigrams = args.usebigrams,\
normalize = normalize,\
tf = args.tf,\
stopwords = stopwords)
else:
datacreator = corpusutil.GenerateVectors(corpus = corpus, mindfpercent\
= args.mindfpercent,\
maxdfpercent =\
args.maxdfpercent,\
minfrequency =\
args.minfrequency,\
verbose = args.verbose,\
usebigrams = args.usebigrams,\
normalize = normalize,\
tf = args.tf,\
stopwords = None)
result = datacreator.create()
docids = result['docids']
featuredict = result['featuredict']
else:
index = cPickle.load(args.indexstuff[0])
featuredict = cPickle.load(args.indexstuff[1])
docids = cPickle.load(args.indexstuff[2])
datacreator = corpusutil.GenerateVectors(index = index, featuredict =\
featuredict, docids = docids,\
ndocs_content = ndocs_content,\
normalize = normalize,\
tf = args.tf)
result = datacreator.create()
data = result['data']
p = data.shape[0]
n = data.shape[1]
logger.debug(" Vectors are of dimensions: (%d,%d)",\
p, n)
if args.saveint:
cPickle.dump(docids,open("tfidfvectors_key_"+sessionid+'.pck','w'))
spio.mmwrite(open("tfidfvectors_"+sessionid+".mtx",'w')\
,data,comment="CSC Matrix",field = 'real')
#DEFAULT_RANK chosen because it works well in practice.
DEFAULT_RANK = 250
r = args.r
maxr = min(p,n)
logger.debug(" Data can have rank not greate than : %d", maxr)
if maxr >= DEFAULT_RANK:
if DEFAULT_RANK > r or r > maxr:
r = DEFAULT_RANK
else:
r = int(maxr/2)
logger.debug(" Going to generate rank %d approximation", r)
ut,s,vt = sparsesvd(data,r)
red_data = ssp.csc_matrix(np.dot(ut.T,np.dot(np.diag(s),vt)))
logger.debug(" Generated rank %d approximation", r)
if normalize:
logger.debug(" Normalizing columns of reduced rank matrix...")
invnorms = np.zeros(n)
normsii = np.arange(0,n,1)
normsjj = np.arange(0,n,1)
for col in range(n):
invnorms[col] = math.sqrt((red_data[:,col].T*red_data[:,col]).todense())
if invnorms[col] is not 0:
invnorms[col] = 1/invnorms[col]
diag = ssp.coo_matrix((invnorms,(normsii,normsjj)),shape = (n,n)).tocsc()
red_data = red_data*diag
logger.debug(" Doing KMeans on reduced rank matrix...")
kmeans = corpusutil.KMeans(data = red_data,k = args.k,n = args.n, delta =\
args.delta,randomcentroids =\
args.randomcentroids, verbose =
args.verbose,classical = args.classical)
result = kmeans.run()
clusters = result['clusters']
centroids = result['centroids']
centroiddict = result['centroiddict']
if args.saveint:
cPickle.dump(clusters,open("redrank_clusters_"+sessionid+'.pck','w'))
spio.mmwrite(open("redrank_centroids_"+sessionid+'.mtx','w'),centroids,\
comment="CSC Matrix", field = 'real')
logger.info(" %d Clusters Generated ",len(clusters))
result = corpusutil.getcentroids(data,clusters)
originalmat_centroids = result['centroids']
originalmat_centroiddict = result['centroiddict']
if args.saveint:
spio.mmwrite(open("originalmat_centroids_"+sessionid+'.mtx','w'),\
originalmat_centroids,comment="CSC Matrix", field = 'real')
vis_output = corpusutil.genconceptclouds(centroids = centroids,\
centroiddict = centroiddict,\
featuredict = featuredict,\
corpus = corpus,\
clusters = clusters,\
docids = docids,\
sessionid = sessionid)
svdkmeansvis = open("svdkmeans-concept_clouds_"+str(sessionid)+'.html','w')
svdkmeansvis.write(vis_output)
svdkmeansvis.close()
vis_output = corpusutil.genfeatureclouds(originalmat_centroids.todense(),\
originalmat_centroiddict,\
featuredict,sessionid)
svdkmeansvis = open("svdkmeans-feature_clusters_"+str(sessionid)+'.html','w')
svdkmeansvis.write(vis_output)
svdkmeansvis.close()
def main():
parser = gen_args()
args = parser.parse_args()
sessionid = args.sessionid
logger = logging.getLogger(__name__)
logger.addHandler(logging.StreamHandler())
if args.verbose:
logger.setLevel(logging.DEBUG)
if args.stopwords:
stopwords = args.stopwords.read().split()
else:
stopwords = None
if args.classical:
normalize = True
else:
normalize = False
if args.opinion or args.corpus:
if args.opinion:
corpus = corpusutil.create(args.opinion)
else:
corpus = cPickle.load(args.corpus)
logger.debug("Number of documents in corpus: %d ", len(corpus))
datacreator = corpusutil.GenerateVectors(corpus = corpus, mindfpercent\
= args.mindfpercent,\
maxdfpercent =\
args.maxdfpercent,\
minfrequency =\
args.minfrequency,\
verbose = args.verbose,\
usebigrams = args.usebigrams,\
normalize = normalize,\
tf = args.tf,\
stopwords = stopwords)
result = datacreator.create()
docids = result['docids']
featuredict = result['featuredict']
else:
index = cPickle.load(args.indexstuff[0])
featuredict = cPickle.load(args.indexstuff[1])
docids = cPickle.load(args.indexstuff[2])
datacreator = corpusutil.GenerateVectors(index = index, featuredict =\
featuredict, docids = docids,\
ndocs_content = ndocs_content,\
normalize = normalize,\
tf = args.tf)
result = datacreator.create()
X = result['data']
if args.k is None:
MIN_K = 2
MAX_K = 50
SAMPLE_SIZE_PERCENT = 100
spectral = SpectralClusterer(X = X, usecosine = args.usecosine, sigma =\
args.sigma, n = args.n, delta =\
args.delta, MIN_K = MIN_K, MAX_K = MAX_K,\
SAMPLE_SIZE_PERCENT = SAMPLE_SIZE_PERCENT,\
randomcentroids = args.randomcentroids,\
classical = args.classical, verbose = \
args.verbose)
else:
spectral = SpectralClusterer(X = X, usecosine = args.usecosine, sigma = \
args.sigma, k = args.k, n = args.n, delta = \
args.delta, randomcentroids = \
args.randomcentroids, classical =\
args.classical, verbose =\
args.verbose)
clusters = spectral.run()
result = corpusutil.getcentroids(X, clusters, normalize)
centroids = result['centroids']
centroiddict = result['centroiddict']
logger.info(" %d Clusters Generated ",len(clusters))
vis_output = corpusutil.genconceptclouds(centroids = centroids,\
centroiddict = centroiddict,\
featuredict = featuredict,\
corpus = corpus,\
clusters = clusters,\
docids = docids,\
sessionid = sessionid)
kmeansvis = open("Spectral-concept_clouds_"+str(sessionid)+'.html','w')
kmeansvis.write(vis_output)
kmeansvis.close()
vis_output = corpusutil.genfeatureclouds(centroids.todense(),centroiddict,\
featuredict,sessionid)
kmeansvis = open("Spectral-feature_clusters_"+str(sessionid)+'.html','w')
kmeansvis.write(vis_output)
kmeansvis.close()