def split_train_test_highest(fname, codeprefixlen, mincodeoccurences, filtered_by):
#prepare generators
rec_generator = lambda:gen_record(fname, filtered_by)
prefixed_rec_generator = lambda:gen_record_prefixed(rec_generator, codeprefixlen)
prefix_code_generator = lambda:gen_lmc(prefixed_rec_generator)
#generate labels
PRINTER('generating labels...')
labels = get_labels_min_occurence(prefix_code_generator, mincodeoccurences)
PRINTER('labels generated:')
PRINTER(str(labels))
#gen filtered records:
labelsset = set(labels)
prefix_code_generator = lambda:gen_record_filteredbylabels(prefixed_rec_generator, labelsset)
PRINTER('counting elements...')
elements_count = len(list(prefix_code_generator()))
PRINTER('number of elements' +str(elements_count))
#split into training and testing samples
PRINTER('splitting into training and testing...')
train_inds, test_inds = randomly_divide(elements_count, int(elements_count / 10))
train_generator = lambda:gen_record_fromshifts(prefix_code_generator, train_inds)
test_generator = lambda:gen_record_fromshifts(prefix_code_generator, test_inds)
PRINTER('splitted.')
elements_count = len(list(prefix_code_generator()))
return train_generator, test_generator, elements_count, labels, elements_count
def load_labels_codegen_elemcnt(fname, codeprefixlen, mincodeoccurences, filtered_by):
#prepare generators
rec_generator = lambda:gen_record(fname, filtered_by)
prefixed_rec_generator = lambda:gen_record_prefixed(rec_generator, codeprefixlen)
prefix_code_generator = lambda:gen_lmc(prefixed_rec_generator)
#generate labels
PRINTER('generating labels...')
labels = get_labels_min_occurence(prefix_code_generator, mincodeoccurences)
PRINTER('labels generated:')
PRINTER(str(labels))
#gen filtered records:
labelsset = set(labels)
prefix_code_generator = lambda:gen_record_filteredbylabels(prefixed_rec_generator, labelsset)
PRINTER('counting elements...')
elements_count = len(list(prefix_code_generator()))
PRINTER('number of elements' +str(elements_count))
return labels, labelsset, prefix_code_generator, elements_count
def load_labels_codegen_elemcnt(fname, codeprefixlen, mincodeoccurences,
filtered_by):
#prepare generators
rec_generator = lambda: gen_record(fname, filtered_by)
prefixed_rec_generator = lambda: gen_record_prefixed(
rec_generator, codeprefixlen)
prefix_code_generator = lambda: gen_lmc(prefixed_rec_generator)
#generate labels
PRINTER('generating labels...')
labels = get_labels_min_occurence(prefix_code_generator, mincodeoccurences)
PRINTER('labels generated:')
PRINTER(str(labels))
#gen filtered records:
labelsset = set(labels)
prefix_code_generator = lambda: gen_record_filteredbylabels(
prefixed_rec_generator, labelsset)
PRINTER('counting elements...')
elements_count = len(list(prefix_code_generator()))
PRINTER('number of elements' + str(elements_count))
return labels, labelsset, prefix_code_generator, elements_count
logging.basicConfig(level=log_level) #prepare generators rec_generator = lambda: gen_record(fname, filtered_by) prefixed_rec_generator = lambda: gen_record_prefixed(rec_generator, codeprefixlen) prefix_code_generator = lambda: gen_lmc(prefixed_rec_generator) #generate labels print "generating labels..." labels = get_labels_min_occurence(prefix_code_generator, mincodeoccurences) labelsset = set(labels) print "labels generated." print labels #gen filtered records: prefix_code_generator = lambda: gen_record_filteredbylabels(prefixed_rec_generator, labelsset) print "counting elements..." elements_count = len(list(prefix_code_generator())) print "number of elements:", elements_count #split into training and testing samples print "splitting into training and testing..." train_inds, test_inds = randomly_divide(elements_count, int(elements_count/10)) train_generator = lambda: gen_record_fromshifts(prefix_code_generator, train_inds) test_generator = lambda: gen_record_fromshifts(prefix_code_generator, test_inds) print "splitted." #train mlknn: print "training distance..." zbldistance = jaccard_distance.JaccardDistance(train_generator, elements_count-int(elements_count/10), distancetrainingsteps)
#choosing shuffling_cnt elements in random:
PRINTER("shuffling in random")
import random
chosen_records = random.sample(list(rec_generator_first()), shuffling_cnt)
rec_generator = lambda: chosen_records
prefixed_rec_generator = lambda: gen_record_prefixed(rec_generator, codeprefixlen)
prefix_code_generator = lambda: gen_lmc(prefixed_rec_generator)
#generate labels
PRINTER("generating labels...")
labels_counts = get_labels_counts(prefix_code_generator, mincodeoccurences)
#PRINTER("labels generated."
#PRINTER(sorted(labels_counts, key = lambda x: x[1], reverse = True)
biggest_labels = map(lambda x: x[0], sorted(labels_counts, key = lambda x: x[1],
reverse = True))[:biggest_labels_cnt]
labelsset = set(biggest_labels)
PRINTER(biggest_labels)
#gen filtered records:
prefix_code_generator = lambda: gen_record_filteredbylabels(prefixed_rec_generator, labelsset)
PRINTER("counting elements...")
elements_count = len(list(prefix_code_generator()))
PRINTER("number of elements:"+str(elements_count))
codes_generator = lambda: gen_lmc(prefix_code_generator)
PRINTER("labels per document statistics:"+str(get_labelperdocuments_counts(codes_generator)))
PRINTER("saving...")
write_zbl_records(open(savefname, 'w'), prefix_code_generator())
