def categorize_resume():
resume_ids = fetch_resume_ids()
normalizer = Normalizer()
categories = []
print(resume_ids)
for resume_id in resume_ids:
skills = fetch_skills(resume_id)
output_group = [0, 0, 0, 0]
cat = fetch_category(resume_id)
print('category from db....')
print(cat)
print(skills)
skills = normalizer.interpolate_skills(skills)
lack = 0
input_size = 5
grouped_skills = group_list(skills, 5)
for group in grouped_skills:
skills = numpy.array([group])
outputs = classifier.classify(skills)
index = numpy.argmax(outputs)
category = get_job_description(index)
print('\n')
print(outputs)
output_group.append(outputs)
print(category)
counter = 0
out = outputs[0]
for item in out:
output_group[counter] += item
# output_group[counter] = output_group[counter] / (grouped_skills.index(group) + 1)
# print(output_group[counter])
counter += 1
if counter == 4:
counter = 0
# print(output_group)
# print(len(output_group))
output_group = output_group[0:4]
index = get_max(output_group)
category = get_job_description(index)
'''
Converts the output to probabiilty
and appends it to the category string
'''
sum_output = sum(output_group[0:4])
for output in output_group[0:4]:
output = (output / sum_output) * 100
str_out = str(output)
category = category + ',' + str_out
categories.append(category)
update_resume_category(category, resume_id)
print('\n')
print(output_group[0:4])
print('\nFinal-Output: ' + category)
print('\n****\n')
return categories
