labels = jrs_io.load_labels(open(labels_path))
single_labels = list(set(reduce(lambda l1,l2: l1+l2, (ll for ll in labels))))
#training_labels = labels[:training_size]
n = len(labels)
print n," multi-labels sets loaded (",len(single_labels),"single labels:",single_labels,")..."
print "Sample five labels:", labels[:5]
print "------------------------------------------"
print "Extracting label occurrence vectors"
label2occurrences = dict( (label,label_ocur(labels, label)) for label in single_labels )
#print label2occurrences
print "------------------------------------------"
print "Loading features from file:", features_matrix_path
f = open(features_matrix_path)
features = jrs_io.load_data(f, cast_method = float, numrows = LOAD_MAX_ROWS)
print "","loaded", len(features),"x",len(features[0])
print "------------------------------------------"
print "Calculating and reporting to:", out_path
fout = open(out_path, "w")
for label in single_labels:
print "","considering label:",label
label_occurrences_vector = label2occurrences[label]
indval_colix = []
for colix in xrange(len(features[0])):
indval,precision,recall = INDICATOR(label_occurrences_vector, extract_col(features, colix))
indval_colix.append( (indval,colix,precision,recall) )
fout.write(str(label)+";\t")
print "Loading labels' file:", labels_path
labels = jrs_io.load_labels(open(labels_path))
single_labels = list(set(reduce(lambda l1,l2: l1+l2, (ll for ll in labels))))
n = len(labels)
print n," multi-labels sets loaded (",len(single_labels),"single labels:",single_labels,")..."
print "------------------------------------------"
print "Extracting label occurrence vectors"
label2occurrences = dict( (label,label_ocur(labels, label)) for label in single_labels )
#print label2occurrences
print "------------------------------------------"
print "Loading features from file:", features_matrix_path
f = open(features_matrix_path)
features = jrs_io.load_data(f, cast_method = int, numrows = LOAD_MAX_ROWS)
print "","loaded", len(features),"x",len(features[0])
print "------------------------------------------"
print "Loading features-ind file",featuresind_path
print "Loading negfeaturesind_path file",negfeaturesind_path
f1 = open(featuresind_path)
f2 = open(negfeaturesind_path)
f1lines = f1.readlines()
f2lines = f2.readlines()
if len(f1lines)!=len(f2lines):
print "ERROR. len IND != len NEG-IND"
sys.exit(-1)
for i, (line, line2) in enumerate(izip(f1lines, f2lines)):
label = str(i+1)
print "Loading labels' file:", labels_path
labels = jrs_io.load_labels(open(labels_path))
n = len(labels)
print "",n," labels' sets loaded."
order = range(n)
random.shuffle(order)
print "Random order:", order[:30],"..."
print "Shuffling labels..."
labels_shuffled = [labels[ix] for ix in order]
jrs_io.store_labels(open(labels_path+"_shuffled","w"), labels_shuffled)
print "Loading distances' file:", distance_matrix_path
distances = jrs_io.load_data(open(distance_matrix_path), lambda x: x)
try: print "",len(distances), "x",len(distances[0])
except: pass
print "Extending order..."
order = order + range(n, len(distances))
print "Extended order:", order
print "Shuffling columns"
distances_tmp = []
for row in distances:
new_row = [ row[ix] for ix in order ]
distances_tmp.append(new_row)
print "Shuffling rows"
distances_shuffled = []
print "Loading labels' file:", labels_path
labels = jrs_io.load_labels(open(labels_path))
n = len(labels)
print "", n, " labels' sets loaded."
order = range(n)
random.shuffle(order)
print "Random order:", order[:30], "..."
print "Shuffling labels..."
labels_shuffled = [labels[ix] for ix in order]
jrs_io.store_labels(open(labels_path + "_shuffled", "w"), labels_shuffled)
print "Loading distances' file:", distance_matrix_path
distances = jrs_io.load_data(open(distance_matrix_path), lambda x: x)
try:
print "", len(distances), "x", len(distances[0])
except:
pass
print "Extending order..."
order = order + range(n, len(distances))
print "Extended order:", order
print "Shuffling columns"
distances_tmp = []
for row in distances:
new_row = [row[ix] for ix in order]
distances_tmp.append(new_row)
print " sample counts:", sorted(list(label2count.iteritems()))[:10]
print " sample `friend`-labels:", sorted(list(label2size.iteritems()))[:10]
print " sample pairlabel2count:", sorted(list(
pairlabel2count.iteritems()))[:50]
print "------------------------------------------"
print "------------------------------------------"
print "------------------------------------------"
avg_label_count = float(sum(len(l) for l in labels)) / len(labels)
print "Avg labels per object:", avg_label_count
print "------------------------------------------"
print "Loading distances' file:", distance_matrix_path
distances = jrs_io.load_data(open(distance_matrix_path),
cast_method,
numrows=LOAD_ROWS_FROM_FILE)
try:
print "", len(distances), "x", len(distances[0])
except:
pass
#print "Sample distances:", distances[:5][:5]
print "------------------------------------------"
#KLASYFIKATOR Ensembled Strongest Fractional Knn
print "Building Ensembled Strongest FractionKNN..."
training_single_labels = list(
set(reduce(lambda l1, l2: l1 + l2, (ll for ll in training_labels))))
print " training labels:", training_single_labels
print " extracting submatrix..."
training_distances = jrs_io.extract_submatrix(distances, training_range[0],
print "------------------------------------------"
#print "Building tree using pairlabel2count & label2count"
#outpath = "/tmp/pairlabel2dist_avg_tree"
#pairwisecount_tree(label2count, pairlabel2count, outpath)
#print "------------------------------------------"
print "------------------------------------------"
print "------------------------------------------"
avg_label_count = float(sum(len(l) for l in labels)) / len(labels)
print "Avg labels per object:",avg_label_count
print "------------------------------------------"
print "Loading distances' file:", distance_matrix_path
distances = jrs_io.load_data(open(distance_matrix_path), cast_method, numrows = LOAD_ROWS_FROM_FILE)
try: print "",len(distances), "x",len(distances[0])
except: pass
#print "Sample distances:", distances[:5][:5]
print "------------------------------------------"
#print "Building tree on sample vs. sample distances avg"
#outpath = "training_distances_avg_tree"
#print " extracting submatrix..."
#training_distances = jrs_io.extract_submatrix(distances, training_range[0], training_range[1], training_range[0], training_range[1])
#dist_tree(training_distances, training_labels, outpath)
#dist_tree(distances, labels, outpath)
#print "------------------------------------------"
#print "------------------------------------------"
#print "------------------------------------------"
