def __cpp_sim_matrix_l_generation_routine__(sim_matrix_path, mscmodel, msc2ix,
secondary_codes_weight,
docid2seccodes):
#dstmatrixpath = TMPDIR+"/mlevel_similarity_matrix_"+similarity_aggregation_method_l+"_"+base64.b16encode(aux.quick_md5(sim_matrix_path+similarity_aggregation_method_l+str(MIN_COUNT_MSCPRIM)))
dstmatrixpath = sim_matrix_path + ".msc" + str(
MIN_COUNT_MSCPRIM) + "_" + similarity_aggregation_method_l
if not aux.exists(dstmatrixpath):
msc2wids_list = get_msc2wids_list(msc2ix, mscmodel,
secondary_codes_weight,
docid2seccodes)
cpp_wrapper.aggregate_simmatrix(sim_matrix_path,
dstmatrixpath,
msc2wids_list,
method=similarity_aggregation_method_l)
logging.info("[build_msc_tree] Loading simmatrix from: " +
str(dstmatrixpath))
(rows, cols, sim_matrix_l) = matrix_io.fread_smatrix(dstmatrixpath)
____validate_cpp_output____(msc2ix, rows)
return sim_matrix_l
train_generator_list = read_pickle(load_train_generator_path)
PRINTER('Loading labels path and elements count...')
lenlabels = len(read_pickle(load_labels_path))
elements_count = read_pickle(load_elements_count_path)
PRINTER("Finding label list...")
get_labels_of_record = mc2lmc_tomka_blad
find_all_labels = lambda frecords: get_labels_min_occurence(
lambda: gen_lmc(frecords), 1)
PRINTER("Loading distance matrix...")
import sys
sys.path.append(r'../')
from data_io.matrix_io import fread_smatrix
(rows, cols, data) = fread_smatrix(distancematrix)
id2rowind, id2colind = {}, {}
for ind, id in enumerate(rows):
id2rowind[id] = ind
for ind, id in enumerate(cols):
id2colind[id] = ind
print "len(train_generator_list):", len(train_generator_list)
print "len(rows):", len(rows)
#print "(rows, cols, data):", (rows, cols, data)
PRINTER("Training classifier...")
from time import time
def printer(x):
#import logging
def main(train_generator_list, labels, elements_count, classifier_name, k, smoothing_param, distancematrix, test_generator):
PRINTER("Finding label list...")
get_labels_of_record = mc2lmc_tomka_blad
find_all_labels = lambda frecords: get_labels_min_occurence(lambda: gen_lmc(frecords), 1)
PRINTER("Loading distance matrix...")
import sys
sys.path.append(r'../')
from data_io.matrix_io import fread_smatrix
(rows, cols, data) = fread_smatrix(distancematrix)
id2rowind, id2colind = {}, {}
for ind, id in enumerate(rows):
id2rowind[id] = ind
for ind, id in enumerate(cols):
id2colind[id] = ind
#print "len(train_generator_list):",len(train_generator_list)
#print "len(test_generator_list):",len(test_generator)
#print "len(rows):",len(rows)
#print "(rows, cols, data):", (rows, cols, data)
PRINTER("Training classifier...")
from time import time
def printer(x):
#import logging
logging.info('['+classifier_name+']'+x)
def distance(a, b):
try:
return data[id2rowind[a['an']]][id2colind[b['an']]]
except:
return data[id2colind[b['an']]][id2rowind[a['an']]]
start = time()
if classifier_name=='mlknn_basic':
def get_neighbours(sample, k):
return find_closest_points_sorted(sample, train_generator_list, [sample], k, distance)
k = int(k)
from mlknn import mlknn_basic
classifier = mlknn_basic.MlknnBasic(train_generator_list, get_neighbours, k, smoothing_param, get_labels_of_record, lambda x:1, printer)
elif classifier_name == 'mlknn_threshold':
def get_neighbours(sample, k):
return find_closest_points_sorted(sample, train_generator_list, [sample], k, distance)
k = int(k)
from mlknn import mlknn_threshold
classifier = mlknn_threshold.MlknnThreshold(train_generator_list, get_neighbours, k, smoothing_param, get_labels_of_record, lambda x:1, printer)
elif classifier_name == 'mlknn_tensembled':
def get_neighbours(sample, k):
return find_closest_points_sorted(sample, train_generator_list, [sample], k, distance)
k = map(int, k.strip().split(','))
PRINTER("loaded k-list: "+str(k))
from mlknn import mlknn_tensembled
classifier = mlknn_tensembled.MlknnTEnsembled(train_generator_list, get_neighbours, k, get_labels_of_record, lambda x:1, printer)
elif classifier_name=='mlknn-basic-tree':
def get_neighbours(sample, k, train_gen):
return find_closest_points_sorted(sample, train_gen, [sample], k, distance)
k = int(k)
from mlknn import mlknn_basic
mlknn_callable = lambda train_gen, get_labels_of_record_arg: mlknn_basic.MlknnBasic(train_gen, lambda sample, k: get_neighbours(sample, k, train_gen),
k, smoothing_param, get_labels_of_record_arg, lambda x:1, printer)
label_mappings = (lambda x: x[:2], lambda x: x[:3], lambda x: x)
from mltools.ml_hierarchical import MlHierarchical
classifier = MlHierarchical(train_generator_list, mlknn_callable, label_mappings, get_labels_of_record)
elif classifier_name == 'mlknn-threshold-tree':
def get_neighbours(sample, k, train_gen):
return find_closest_points_sorted(sample, train_gen, [sample], k, distance)
k = int(k)
from mlknn import mlknn_threshold
mlknn_callable = lambda train_gen, get_labels_of_record_arg: mlknn_threshold.MlknnThreshold(train_gen, lambda sample, k: get_neighbours(sample, k, train_gen),
k, smoothing_param, get_labels_of_record_arg, lambda x:1, printer)
label_mappings = (lambda x: x[:2], lambda x: x[:3], lambda x: x)
from mltools.ml_hierarchical import MlHierarchical
classifier = MlHierarchical(train_generator_list, mlknn_callable, label_mappings, get_labels_of_record)
elif classifier_name == 'mlknn-tensembled-tree':
def get_neighbours(sample, k, train_gen):
return find_closest_points_sorted(sample, train_gen, [sample], k, distance)
k = map(int, k.strip().split(','))
PRINTER("loaded k-list: "+str(k))
from mlknn import mlknn_tensembled
mlknn_callable = lambda train_gen, get_labels_of_record_arg: mlknn_tensembled.MlknnTEnsembled(train_gen, lambda sample, k: get_neighbours(sample, k, train_gen),
k, get_labels_of_record_arg, lambda x:1, printer)
label_mappings = (lambda x: x[:2], lambda x: x[:3], lambda x: x)
from mltools.ml_hierarchical import MlHierarchical
classifier = MlHierarchical(train_generator_list, mlknn_callable, label_mappings, get_labels_of_record)
PRINTER("Time taken for training:"+str(start-time()))
PRINTER("------------------------")
PRINTER("---Testing classifier---")
PRINTER("------------------------")
classify_oracle = mc2lmc_tomka_blad
from mltools.multilabel_evaluate import multilabel_evaluate, multilabel_evaluate_printresults
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = multilabel_evaluate(lambda: test_generator, classify_oracle, classifier.__getattribute__('classify'), len(labels),
[('full label', lambda x: x), ('half label', lambda x: x[:3]), ('low label', lambda x: x[:2])])
PRINTER("-----------RESULTS-----------")
multilabel_evaluate_printresults(accuracy, precision, recall, hammingloss, subset01loss, fmeasure, PRINTER)
return accuracy, precision, recall, hammingloss, subset01loss, fmeasure
k2avgsil = silhouettes(simmatrix, possible_k, clustering_method)
return max((v, k) for k, v in k2avgsil.iteritems())[1]
if __name__ == "__main__":
import doctest
doctest.testmod()
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
try:
simmatrix_path = sys.argv[1]
except:
print "Argument expected: similarity matrix path"
sys.exit(-1)
print simmatrix_path
from data_io import matrix_io
(rows, cols, simmatrix) = matrix_io.fread_smatrix(
simmatrix_path) #, datareader=matrix_io.__read_ftabs__, maxrows=1000
print "matrix size=", len(simmatrix), "x", len(simmatrix[0])
print simmatrix[0][:10]
print simmatrix[1][:10]
print simmatrix[2][:10]
print simmatrix[3][:10]
print simmatrix[4][:10]
print "Selected k=", number_of_clusters(simmatrix,
xrange(2, len(simmatrix)))
from __future__ import division from itertools import izip import sys sys.path.append(r'../') from data_io.matrix_io import fread_smatrix filename = sys.argv[1] (rows, cols, data) = fread_smatrix(filename) print "(rows, cols, data):", (rows, cols, data)
