def get_invalid_matches(manifest, input):
"""util function to return any invalid matches when running through a test file"""
normalizer = Normalizer()
normalizer.read_manifest(manifest)
samples = read_input(input)
matched = normalize_samples(normalizer, samples, verbose=False)
invalid_matches = [match for match in matched if match['expected'] != match['output']]
return invalid_matches
def check_data(manifest, sample):
normalizer = Normalizer()
normalizer.read_manifest(manifest)
with open(sample, 'r') as f:
sample_file = f.read().strip()
if len(sample_file) > 1:
for line in sample_file.split('\n')[1:]:
# line in the manifest: section_id,section_name,row_id,row_name
line = line.strip()
elements = line.split(',')
section_name = elements[0]
row_name = elements[1]
# [(section_id, row_id, bool), number of matches, different section ids we have seen, different row_id we have seen]
# data example: [(None, None, False), 3, set([170, 11, 118]), set([7])]
data = normalizer.normalize_raw(section_name, row_name)
# We are looking for matches that result in `False` but are not caused by
# database returning multiple entries or row_name value passed as a range
count = 0
if data[0][2] == False and data[1] <= 1 and '-' not in row_name:
count += 1
print data, section_name, row_name, row_name.isdigit()
print 'BAD MATCH: ', count
assert count == 0
description='grader for seatgeek SectionNormalization code test')
parser.add_argument('--manifest',
default=None,
help='path to manifest file')
parser.add_argument('--input', default=None, help='path to input file')
parser.add_argument('--section',
default=None,
help='section input (for testing)')
parser.add_argument('--row', default=None, help='row input (for testing)')
args = parser.parse_args()
assert args.manifest
normalizer = Normalizer()
normalizer.read_manifest(args.manifest)
if args.section and args.row:
section_id, row_id, valid = normalizer.normalize(
args.section, args.row)
print """
Input:
[section] {}\t[row] {}
Output:
[section_id] {}\t[row_id] {}
Valid?:
{}
""".format(args.section, args.row, section_id, row_id, valid)
elif args.input:
samples = read_input(args.input)
import csv
from normalizer import Normalizer
normalizer = Normalizer()
normalizer.read_manifest('../../manifests/citifield_sections.csv')
# normalizer.read_manifest('../../manifests/dodgerstadium_sections.csv')
inp = []
correct = []
# with open('../../samples/dodgertest.csv') as file:
with open('../../samples/metstest.csv') as file:
reader = csv.reader(file)
for line in reader:
inp.append({'section': line[0], 'row': line[1]})
if line[4].strip() == 'True':
correct.append({
'section_id': line[2],
'row_id': line[3],
'valid': True
})
else:
correct.append({
'section_id': line[2],
'row_id': line[3],
'valid': False
})
inp = inp[1:]
correct = correct[1:]
assert len(inp) == len(correct)
