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 words_freqs(records, features):
#count each word in abstract and title:
all_w = 0
words = defaultdict(lambda: 0)
for rec in gen_record(records, features+['mc']):
words_l = text_to_words(" ".join([rec[f] for f in features]) )
for c in words_l:
words[c]+=1
all_w+=1
print "count of all words:", all_w
print "words found:"
w_sorted = sorted(list(words.iteritems()), key=lambda x:x[1], reverse=True)
for k, v in w_sorted:
print k, ":", v
def count_label_statistics(fname, fields):
"""
Counts the following statistics and prints them.
D is the dataset filtered by the condition to contain all of the fields
L is number of distinct labels in D.
-Label cardinality: the average number of labels of the examples in D
-Label density: the average number of labels of the examples in D divided by |L|
-Bolo11: the percentage of documents that contain at least 2 labels of the same 2 code prefix
-Bolo12: the percentage of documents that contain at least 2 labels of the same 3 code prefix
-Bolo21: the percentage of documents that contain at least 2 labels of different 2 code prefix
-Bolo22: the percentage of documents that contain at least 2 labels of different 3 code prefix
"""
all = 0
labels = set()
lc = 0
ld = 0
bolo11 = 0
bolo12 = 0
bolo21 = 0
bolo22 = 0
#count statistics
for lmc in gen_lmc(lambda: gen_record(fname, fields), fields):
all += 1
for mc in lmc:
labels.add(mc)
lc += len(lmc)
ld += len(lmc)
if contains2of_same_prefix(lmc, 2):
bolo11 += 1
if contains2of_same_prefix(lmc, 3):
bolo12 += 1
if contains2of_diff_prefix(lmc, 2):
bolo21 += 1
if contains2of_diff_prefix(lmc, 3):
bolo22 += 1
print '[count_label_statistics]: lmc:', lmc, contains2of_same_prefix(
lmc, 2), contains2of_same_prefix(lmc, 3), contains2of_diff_prefix(
lmc, 2), contains2of_diff_prefix(lmc, 3)
#print statistics
print "lc:", lc / all
print "ld:", ld / (all * len(labels))
print "bolo11 contain at least 2 of same 2 code prefix:", bolo11 / all
print "bolo12 contain at least 2 of same 3 code prefix:", bolo12 / all
print "bolo21 contain at least 2 of diff 2 code prefix:", bolo21 / all
print "bolo22 contain at least 2 of diff 3 code prefix:", bolo22 / all
def count_label_statistics(fname, fields):
"""
Counts the following statistics and prints them.
D is the dataset filtered by the condition to contain all of the fields
L is number of distinct labels in D.
-Label cardinality: the average number of labels of the examples in D
-Label density: the average number of labels of the examples in D divided by |L|
-Bolo11: the percentage of documents that contain at least 2 labels of the same 2 code prefix
-Bolo12: the percentage of documents that contain at least 2 labels of the same 3 code prefix
-Bolo21: the percentage of documents that contain at least 2 labels of different 2 code prefix
-Bolo22: the percentage of documents that contain at least 2 labels of different 3 code prefix
"""
all = 0
labels = set()
lc = 0
ld = 0
bolo11 = 0
bolo12 = 0
bolo21 = 0
bolo22 = 0
#count statistics
for lmc in gen_lmc(lambda: gen_record(fname, fields), fields):
all+=1
for mc in lmc:
labels.add(mc)
lc += len(lmc)
ld += len(lmc)
if contains2of_same_prefix(lmc, 2):
bolo11 += 1
if contains2of_same_prefix(lmc, 3):
bolo12 += 1
if contains2of_diff_prefix(lmc, 2):
bolo21 += 1
if contains2of_diff_prefix(lmc, 3):
bolo22 += 1
print '[count_label_statistics]: lmc:', lmc, contains2of_same_prefix(lmc, 2), contains2of_same_prefix(lmc, 3), contains2of_diff_prefix(lmc, 2), contains2of_diff_prefix(lmc, 3)
#print statistics
print "lc:", lc/all
print "ld:", ld/(all*len(labels))
print "bolo11 contain at least 2 of same 2 code prefix:", bolo11/all
print "bolo12 contain at least 2 of same 3 code prefix:", bolo12/all
print "bolo21 contain at least 2 of diff 2 code prefix:", bolo21/all
print "bolo22 contain at least 2 of diff 3 code prefix:", bolo22/all
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
print "codeprefixlen:", codeprefixlen
print "mincodeoccurences", mincodeoccurences
print "k:", k
print "smoothingparam:", smoothingparam
print "distancetrainingsteps:", distancetrainingsteps
print "filtered_by:", filtered_by
print "save_hierarchical_path:", save_hierarchical_path
print "save_train_generator_path:", save_train_generator_path
print "save_lenlabels_path:", save_lenlabels_path
log_level = logging.INFO
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
except:
print '5th argument: number of labels to consider'
sys.exit(1)
try:
shuffling_cnt = int(sys.argv[6])
except:
print '6th argument: How many records to sample before the further filtering.'
sys.exit(1)
try:
filtered_by = sys.argv[7:]
except:
print '7th argument: list of the fields to exist in considered records.'
sys.exit(1)
#prepare generators
rec_generator_first = lambda: gen_record(fname, filtered_by)
#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],
from zbl2py import record_read
from classifier_tester import LeaveOneOutAllCategories
from classifier_knn import KnnMatrixClassifier
import os
#lib_path = os.path.abspath(os.path.sep.join(['..', 'topic_classification']))
#sys.path.append(lib_path)
lib_path = os.path.abspath(
os.path.sep.join(['..', '..', '..', 'document_classification']))
sys.path.append(lib_path)
from data_io.zbl_record_generators import gen_record, mc2lmc_tomka_blad
if __name__ == '__main__':
records_file = sys.argv[1]
test_samples = int(sys.argv[2])
print "Arguments read:"
print "records_file =", records_file
print "test_samples =", test_samples
frecords = lambda: gen_record(records_file, ['mc', 'ti', 'ab', 'au'])
#loo = LeaveOneOutAllCategories(KnnMatrixClassifier, frecords, mc2lmc_tomka_blad)
#corr = loo.test(test_samples)
#print "Correctness:", corr
print "---training a classifier..."
knn = KnnMatrixClassifier(frecords, 7000, 100, mc2lmc_tomka_blad)
print "---performing leave one out..."
corr = knn.loo(test_samples)
print "COrrectness:", corr
sys.path.append(r'../')
from zbl2py import record_read
from classifier_tester import LeaveOneOutAllCategories
from classifier_knn import KnnMatrixClassifier
import os
#lib_path = os.path.abspath(os.path.sep.join(['..', 'topic_classification']))
#sys.path.append(lib_path)
lib_path = os.path.abspath(os.path.sep.join(['..', '..', '..', 'document_classification']))
sys.path.append(lib_path)
from data_io.zbl_record_generators import gen_record, mc2lmc_tomka_blad
if __name__ == '__main__':
records_file = sys.argv[1]
test_samples = int(sys.argv[2])
print "Arguments read:"
print "records_file =", records_file
print "test_samples =", test_samples
frecords = lambda: gen_record(records_file, ['mc', 'ti', 'ab', 'au'])
#loo = LeaveOneOutAllCategories(KnnMatrixClassifier, frecords, mc2lmc_tomka_blad)
#corr = loo.test(test_samples)
#print "Correctness:", corr
print "---training a classifier..."
knn = KnnMatrixClassifier(frecords, 7000, 100, mc2lmc_tomka_blad)
print "---performing leave one out..."
corr = knn.loo(test_samples)
print "COrrectness:", corr
