def __init__(self, corpus, numBest = None, dtype = numpy.float32, numFeatures = None):
"""
If `numBest` is left unspecified, similarity queries return a full list (one
float for every document in the corpus, including the query document):
If `numBest` is set, queries return `numBest` most similar documents, as a
sorted list:
>>> sms = MatrixSimilarity(corpus, numBest = 3)
>>> sms[vec12]
[(12, 1.0), (30, 0.95), (5, 0.45)]
"""
if numFeatures is None:
logging.info("scanning corpus of %i documents to determine the number of features" %
len(corpus))
numFeatures = 1 + utils.getMaxId(corpus)
logging.info("creating matrix for %i documents and %i features" %
(len(corpus), numFeatures))
self.numFeatures = numFeatures
self.numBest = numBest
self.corpus = numpy.empty(shape = (len(corpus), numFeatures), dtype = dtype, order = 'F')
self.normalize = True
# iterate over corpus, populating the numpy matrix
for docNo, vector in enumerate(corpus):
if docNo % 1000 == 0:
logging.info("PROGRESS: at document #%i/%i" % (docNo, len(corpus)))
vector = matutils.unitVec(matutils.sparse2full(vector, numFeatures))
self.corpus[docNo] = vector
self.corpus = numpy.asmatrix(self.corpus)
def __init__(self,
corpus,
numBest=None,
dtype=numpy.float32,
numFeatures=None):
"""
If `numBest` is left unspecified, similarity queries return a full list (one
float for every document in the corpus, including the query document):
If `numBest` is set, queries return `numBest` most similar documents, as a
sorted list:
>>> sms = MatrixSimilarity(corpus, numBest = 3)
>>> sms[vec12]
[(12, 1.0), (30, 0.95), (5, 0.45)]
"""
if numFeatures is None:
logging.info(
"scanning corpus of %i documents to determine the number of features"
% len(corpus))
numFeatures = 1 + utils.getMaxId(corpus)
logging.info("creating matrix for %i documents and %i features" %
(len(corpus), numFeatures))
self.numFeatures = numFeatures
self.numBest = numBest
self.corpus = numpy.empty(shape=(len(corpus), numFeatures),
dtype=dtype)
self.normalize = True
if corpus is not None:
# iterate over corpus, populating the numpy matrix
for docNo, vector in enumerate(corpus):
if docNo % 1000 == 0:
logging.info("PROGRESS: at document #%i/%i" %
(docNo, len(corpus)))
vector = matutils.unitVec(
matutils.sparse2full(vector, numFeatures))
self.corpus[docNo] = vector
self.corpus = numpy.asmatrix(self.corpus)