def eval():
start = time.clock()
print "Calculating predictions of ",len(testing_labels)," labels' sets..."
predicted_labels = jrs_multilabel_classifier.classify_multilabel(testing2training_distances, training_labels, multilabel_classifier)
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(testing_labels, predicted_labels)
print " accuracy:", accuracy,"\n precision:", precision,"\n recall:", recall,"\n fmeasure:", fmeasure
lcount = [len(ll) for ll in predicted_labels]
print " avg labels in predicted:", float(sum(lcount))/(len(lcount))
print " done in", (time.clock() - start), "sec..."
return predicted_labels
def eval():
start = time.clock()
print "Calculating predictions of ", len(
testing_labels), " labels' sets..."
predicted_labels = jrs_multilabel_classifier.classify_multilabel(
testing2training_distances, training_labels,
multilabel_classifier)
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(
testing_labels, predicted_labels)
print " accuracy:", accuracy, "\n precision:", precision, "\n recall:", recall, "\n fmeasure:", fmeasure
lcount = [len(ll) for ll in predicted_labels]
print " avg labels in predicted:", float(
sum(lcount)) / (len(lcount))
print " done in", (time.clock() - start), "sec..."
return predicted_labels
def eval():
start = time.clock()
print "Calculating predictions of ",len(testing_labels)," labels' sets..."
predicted_labels = jrs_multilabel_classifier.classify_multilabel(testing2training_distances, training_labels, multilabel_classifier)
try:
print testing_labels[:10],"\n", predicted_labels[:10]
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(testing_labels, predicted_labels)
except:
print "[knn] Error in jrs_evaluation.jrs_evaluate(testing_labels, predicted_labels):",testing_labels, predicted_labels
print " accuracy:", accuracy,"\n precision:", precision,"\n recall:", recall,"\n fmeasure:", fmeasure
lcount = [len(ll) for ll in predicted_labels]
#print " avg labels in predicted:", float(sum(lcount))/(len(lcount))
#accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(filter_out_labels(testing_labels), filter_out_labels(predicted_labels))
#print " postfiltering-accuracy:", accuracy,"\n postfiltering-precision:", precision,"\n postfiltering-recall:", recall,"\n postfiltering-fmeasure:", fmeasure
print " done in", (time.clock() - start), "sec..."
return predicted_labels
def eval(testing2training_distances, training_labels, testing_labels, multilabel_classifier):
predicted_labels = jrs_multilabel_classifier.classify_multilabel(testing2training_distances, training_labels, multilabel_classifier)
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(testing_labels, predicted_labels)
return fmeasure
print "------------------------------------------"
print "Classifying file:", features_matrix_path
f = open(features_matrix_path)
predicted_labels = []
for i,line in enumerate(f.xreadlines()):
if i%1000==0: print "",i,"..."
row = [int(x) for x in line.split()]
ll = []
for label,feature_ixs in label2feature_ixs.iteritems():
says_yes = sum(row[ix]>0 for ix in feature_ixs)
if says_yes >= len(feature_ixs)*MIN_FRACTION_OF_VOTES:
ll.append(label)
ll = sorted(ll)
predicted_labels.append(ll)
print "",i," oracle",labels[i]," pred",ll
print "","len=",len(labels[:(i+1)]), len(predicted_labels)
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(labels[:(i+1)], predicted_labels)
print "\t\t\t\t\t","%.2f" %precision,"%.2f" %recall,"%.2f" %fmeasure
print "------------------------------------------"
accuracy, precision, recall, hammingloss, subset01loss, fmeasure = jrs_evaluation.jrs_evaluate(labels, predicted_labels)
print "\t\t\t\t\t","%.2f" %precision,"%.2f" %recall,"%.2f" %fmeasure
print "Wrining results to", out_path
jrs_io.store_labels(open(out_path,"w"), predicted_labels)
