Created
January 14, 2020 16:13
-
-
Save adammcmaster/de82785145e091134e297d5baea4ff29 to your computer and use it in GitHub Desktop.
A script to produce an AutoML training file from Zooniverse classifications for P4 Ridges
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import csv | |
| import json | |
| import os | |
| import re | |
| subject_sets = { | |
| '7585', | |
| '7870', | |
| '7888', | |
| '8385', | |
| '9845', | |
| '13286', | |
| } | |
| workflow_id = '2627' | |
| GCS_PATH_PREFIX = 'gs://golden-toolbox-239212-vcm/' | |
| RIDGE_THRESHOLD = 0.75 | |
| FILE_PATH = os.path.join(os.environ['HOME'], 'Downloads') | |
| subjects = {} | |
| print('Loading subjects') | |
| with open(os.path.join(FILE_PATH, 'planet-four-ridges-subjects.csv')) as subj_file: | |
| r = csv.DictReader(subj_file) | |
| for row in r: | |
| if not row['subject_set_id'] in subject_sets: | |
| continue | |
| location = re.sub(r'^https://', GCS_PATH_PREFIX, json.loads(row['locations']).values()[0]) | |
| subjects[row['subject_id']] = { | |
| 'location': location, | |
| 'yes_votes': 0.0, | |
| 'no_votes': 0.0, | |
| } | |
| print('Counting votes from classifications') | |
| with open(os.path.join(FILE_PATH, 'polygonal-ridge-workflow-classifications.csv')) as class_file: | |
| r = csv.DictReader(class_file) | |
| for row in r: | |
| if ( | |
| row['workflow_id'] != workflow_id | |
| or row['subject_ids'] not in subjects | |
| ): | |
| continue | |
| annotations = json.loads(row['annotations']) | |
| for annotation in annotations: | |
| if annotation['task'] == 'T0' and annotation['value']: | |
| if annotation['value'].lower() == 'yes': | |
| subjects[row['subject_ids']]['yes_votes'] += 1.0 | |
| elif annotation['value'].lower() == 'no': | |
| subjects[row['subject_ids']]['no_votes'] += 1.0 | |
| break | |
| print('Outputting results') | |
| with open(os.path.join(FILE_PATH, 'planet-four-ridges-automl.csv'), 'w') as out_file: | |
| w = csv.writer(out_file) | |
| for subject_id, subject in subjects.iteritems(): | |
| vote_total = subject['yes_votes'] + subject['no_votes'] | |
| if vote_total == 0: | |
| continue | |
| yes_proportion = subject['yes_votes'] / vote_total | |
| if yes_proportion >= RIDGE_THRESHOLD: | |
| subject_class = 'ridge' | |
| else: | |
| subject_class = 'no_ridge' | |
| w.writerow((subject['location'], subject_class)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment