Daniel@0: # Part of DML (Digital Music Laboratory)
Daniel@0: # Copyright 2014-2015 Daniel Wolff, City University
Daniel@0:  
Daniel@0: # This program is free software; you can redistribute it and/or
Daniel@0: # modify it under the terms of the GNU General Public License
Daniel@0: # as published by the Free Software Foundation; either version 2
Daniel@0: # of the License, or (at your option) any later version.
Daniel@0: # 
Daniel@0: # This program is distributed in the hope that it will be useful,
Daniel@0: # but WITHOUT ANY WARRANTY; without even the implied warranty of
Daniel@0: # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
Daniel@0: # GNU General Public License for more details.
Daniel@0: # 
Daniel@0: # You should have received a copy of the GNU General Public
Daniel@0: # License along with this library; if not, write to the Free Software
Daniel@0: # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
Daniel@0: 
Daniel@0: # -*- coding: utf-8 -*-
Daniel@0: __author__='wolffd'
Daniel@0: 
Daniel@0: 
Daniel@0: from rdflib import RDF, RDFS
Daniel@0: from csvutils import *
Daniel@0: from aggregate import *
Daniel@0: from n3Parser import get_rdf_graph_from_n3 
Daniel@0: import numpy
Daniel@0: from scipy.spatial import distance
Daniel@0: from collections import defaultdict
Daniel@0: 
Daniel@0: 
Daniel@0: 
Daniel@0: def per_file(inputs,opts={}):
Daniel@0:     places = []
Daniel@0:     lists = []
Daniel@0:     
Daniel@0:     #print_status(str(inputs))
Daniel@0:     # simtype = opts['sim_type']
Daniel@0:    
Daniel@0:     def accum(item):
Daniel@0: 
Daniel@0:         # add uri if everything went well
Daniel@0:         places.append(item['place'])
Daniel@0:         lists.append(item['list'])
Daniel@0:     
Daniel@0:     # accumulation 
Daniel@0:     st=for_each(inputs,accum)
Daniel@0:     
Daniel@0:     # get the histogram
Daniel@0:     (histo,index) = histogram(places)
Daniel@0:         
Daniel@0:     # get the songs for each place
Daniel@0:     list = []
Daniel@0:     for row in index.values():
Daniel@0:         list += [lists[i] for i in row]
Daniel@0:     
Daniel@0:     return { 'result': { 'hist': histo }, #AK requested this removed, 'lists': list}, 
Daniel@0:              'stats' : st }
Daniel@0:              
Daniel@0:              
Daniel@0: 
Daniel@0: # histogram the returns revers index as well
Daniel@0: def histogram(strin = []):
Daniel@0:     # build histogram 
Daniel@0:     histo = dict()
Daniel@0:     index = defaultdict(list)
Daniel@0:     for num, row in enumerate(strin):
Daniel@0:         histo[row] = histo.get(row, 0) + 1 
Daniel@0:         index[row] += [num]
Daniel@0: 
Daniel@0:     # return most frequent key
Daniel@0:     return ({'counts':histo.values(), 'places':histo.keys()}, index)