def extractTopicWordWeights( self, model_path ):
data = {}
words = []
topics = []
# Read in content of file (sparse matrix representation)
filename = '{}/{}'.format( model_path, ImportMallet.TOPIC_WORD_WEIGHTS )
with open( filename, 'r' ) as f:
lines = UnicodeReader( f )
for (topic, word, value) in lines:
topic = int(topic)
if topic not in data:
data[ topic ] = {}
data[ topic ][ word ] = float(value)
words.append( word )
topics.append( topic )
# Get list of terms and topic indexes
term_index = sorted( list( frozenset( words ) ) )
topic_index = sorted( list( frozenset( topics ) ) )
# Build dense matrix representation
matrix = []
for term in term_index :
row = []
for topic in topic_index :
row.append( data[ topic ][ term ] )
matrix.append( row )
# Generate topic labels
topic_str_index = [ 'Topic {}'.format(d) for d in topic_index ]
self.model.term_topic_matrix = matrix
self.model.term_index = term_index
self.model.topic_index = topic_str_index
def read( self ):
self.data = {}
filename = self.path + TokensAPI.TOKENS
with open( filename, 'r' ) as f:
lines = UnicodeReader( f )
for ( docID, docTokens ) in lines:
self.data[ docID ] = docTokens.split( ' ' )
def ReadAsSparseMatrix( filename ):
matrix = {}
with open( filename, 'r' ) as f:
lines = UnicodeReader( f )
for ( aKey, bKey, value ) in lines:
matrix[ (aKey, bKey) ] = float( value )
return matrix
def ReadAsSparseVector( filename ):
vector = {}
with open( filename, 'r' ) as f:
lines = UnicodeReader( f )
for ( key, value ) in lines:
vector[ key ] = float( value )
return vector
def ReadAsMatrix( filename ): matrix = [] with open( filename, 'r' ) as f: lines = UnicodeReader( f ) for line in lines: matrix.append( map( float, line ) ) return matrix
def readCsvAsMatrixStr(self, model_path, filename):
"""
Return a matrix (list of list) of string values.
Each row corresponds to a line of the input file.
Each cell (in a row) corresponds to a comma-separated value (in each line).
"""
data = []
filename = '{}/{}'.format(model_path, filename)
with open(filename, 'r') as f:
lines = UnicodeReader(f, delimiter=',')
data = [d for d in lines]
return data