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 extract_curr_level_labels(frecords):
'''
Extract labels that sit in frecords
'''
code_generator = lambda: gen_lmc(frecords)
return get_labels_min_occurence(
code_generator,
1) #get all the labels, regardless of their occurences counts
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 "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
#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)
from tools.pickle_tools import read_pickle
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("training distance...")
train_generator = lambda: train_generator_list
if distancetype=='jac':
from mlknn.jaccard_distance import JaccardDistance
zbldistance = JaccardDistance(train_generator, elements_count-int(elements_count/10), distancetrainingsteps)
else:
from mlknn.txt_cosine_distance import TxtCosineDistance
zbldistance = TxtCosineDistance(distancetype)
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("Training MLKNN...")
from time import time
start = time()
mlknn_single = MlKnnFractional(train_generator, zbldistance, find_closest_points,
k, get_labels_of_record)
PRINTER("Time taken for training:"+str(start-time()))
from tools.pickle_tools import save_pickle
PRINTER("MLKNN: pickling the classifier...")
save_pickle(mlknn_single, save_classifier_path)
load_test_generator = sys.argv[8]
except:
print '8th argument expected: load_test_generator parameter'
sys.exit(1)
PRINTER('Loading training list...')
from tools.pickle_tools import read_pickle
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)
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
def extract_curr_level_labels(frecords):
"""
Extract labels that sit in frecords
"""
code_generator = lambda: gen_lmc(frecords)
return get_labels_min_occurence(code_generator, 1) # get all the labels, regardless of their occurences counts
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
#split into training and testing samples
print "splitting into training and testing..."
train_inds, test_inds = randomly_divide(elements_count,
int(elements_count / 10))
