def write_mw_prefixed_roots(prefixed_roots, unprefixed_roots, prefix_groups,
sandhi_rules, out_path):
"""Parse the prefixes in a prefix root and write the parsed roots."""
with util.read_csv(prefix_groups) as reader:
prefix_groups = {x['group']: x['prefixes'] for x in reader}
with util.read_csv(unprefixed_roots) as reader:
root_set = {(x['root'], x['hom']) for x in reader}
candidate_homs = [None] + [str(i) for i in range(1, 10)]
sandhi = make_sandhi_object(sandhi_rules)
rows = []
for row in util.read_csv_rows(prefixed_roots):
for group in sandhi.split_off(row['prefixed_root'],
row['unprefixed_root']):
if group in prefix_groups:
basis, hom = row['unprefixed_root'], row['hom']
if (basis, hom) not in root_set:
for x in candidate_homs:
if (basis, x) in root_set:
hom = x
break
if (basis, hom) not in root_set:
continue
rows.append((row['prefixed_root'], prefix_groups[group],
row['unprefixed_root'], hom))
break
labels = ['prefixed_root', 'prefixes', 'unprefixed_root', 'hom']
with util.write_csv(out_path, labels) as write_row:
for row in rows:
write_row(dict(zip(labels, row)))
def write_mw_prefixed_roots(prefixed_roots, unprefixed_roots, prefix_groups,
sandhi_rules, out_path):
"""Parse the prefixes in a prefix root and write the parsed roots."""
with util.read_csv(prefix_groups) as reader:
prefix_groups = {x['group']: x['prefixes'] for x in reader}
with util.read_csv(unprefixed_roots) as reader:
root_set = {(x['root'], x['hom']) for x in reader}
candidate_homs = [None] + [str(i) for i in range(1, 10)]
sandhi = make_sandhi_object(sandhi_rules)
rows = []
for row in util.read_csv_rows(prefixed_roots):
for group in sandhi.split_off(row['prefixed_root'],
row['unprefixed_root']):
if group in prefix_groups:
basis, hom = row['unprefixed_root'], row['hom']
if (basis, hom) not in root_set:
for x in candidate_homs:
if (basis, x) in root_set:
hom = x
break
if (basis, hom) not in root_set:
continue
rows.append((row['prefixed_root'], prefix_groups[group],
row['unprefixed_root'], hom))
break
labels = ['prefixed_root', 'prefixes', 'unprefixed_root', 'hom']
with util.write_csv(out_path, labels) as write_row:
for row in rows:
write_row(dict(zip(labels, row)))
def get_patients():
rows = read_csv_rows('data.csv')
fields = rows.pop(0)
mrn = fields.index('MRN')
patients = {}
for row in rows:
if row[mrn] not in patients:
patients[row[mrn]] = Patient(fields, row)
patients[row[mrn]].add_appt(fields, row)
return patients
def write_prefixed_shs_verbal_indeclinables(final_path, sandhi_rules,
prefixed_roots, root_converter,
out_path):
"""Write prefixed SHS verbal indeclinables."""
sandhi = make_sandhi_object(sandhi_rules)
root_to_prefixed = {}
with util.read_csv(prefixed_roots) as reader:
for row in reader:
root_to_prefixed.setdefault(row['unprefixed_root'], []).append(row)
labels = None
clean_rows = []
with util.read_csv(final_path) as reader:
for row in reader:
root_pair = root_converter.get(row['root'])
if root_pair is None:
continue
root, hom = root_pair
row['root'] = root
for result in root_to_prefixed.get(root, []):
new_row = row.copy()
for field in ['form', 'stem']:
if field in row:
new_row[field] = sandhi.join(
result['prefixes'].split('-') + [new_row[field]])
new_row['root'] = result['prefixed_root']
new_row['hom'] = result['hom']
clean_rows.append(new_row)
labels = reader.fieldnames
labels += ['hom']
old_rows = list(util.read_csv_rows(out_path))
clean_rows.sort(key=lambda x: util.key_fn(x['root']))
with util.write_csv(out_path, labels) as write_row:
for row in old_rows:
write_row(row)
for row in clean_rows:
write_row(row)
def write_prefixed_shs_verbal_data(data_path, prefixed_roots, root_converter,
sandhi_rules, out_path):
"""Write Sanskrit Heritage Site data after converting its roots.
:param data_path: path to the actual verb data
:param out_path:
"""
sandhi = make_sandhi_object(sandhi_rules)
root_to_prefixed = {}
with util.read_csv(prefixed_roots) as reader:
for row in reader:
root_to_prefixed.setdefault(row['unprefixed_root'], []).append(row)
labels = None
clean_rows = []
with util.read_csv(data_path) as reader:
for row in reader:
root_pair = root_converter.get(row['root'])
if root_pair is None:
continue
root, hom = root_pair
for result in root_to_prefixed.get(root, []):
new_row = row.copy()
for field in ['form', 'stem']:
if field in row:
new_row[field] = sandhi.join(
result['prefixes'].split('-') + [new_row[field]])
new_row['root'] = result['prefixed_root']
new_row['hom'] = hom
clean_rows.append(new_row)
labels = reader.fieldnames + ['hom']
old_rows = list(util.read_csv_rows(out_path))
clean_rows.sort(key=lambda x: util.key_fn(x['root']))
with util.write_csv(out_path, labels) as write_row:
for row in old_rows:
write_row(row)
for row in clean_rows:
write_row(row)
def write_prefixed_shs_verbal_data(data_path, prefixed_roots, root_converter,
sandhi_rules, out_path):
"""Write Sanskrit Heritage Site data after converting its roots.
:param data_path: path to the actual verb data
:param out_path:
"""
sandhi = make_sandhi_object(sandhi_rules)
root_to_prefixed = {}
with util.read_csv(prefixed_roots) as reader:
for row in reader:
root_to_prefixed.setdefault(row['unprefixed_root'], []).append(row)
labels = None
clean_rows = []
with util.read_csv(data_path) as reader:
for row in reader:
root_pair = root_converter.get(row['root'])
if root_pair is None:
continue
root, hom = root_pair
for result in root_to_prefixed.get(root, []):
new_row = row.copy()
for field in ['form', 'stem']:
if field in row:
new_row[field] = sandhi.join(
result['prefixes'].split('-') + [new_row[field]])
new_row['root'] = result['prefixed_root']
new_row['hom'] = hom
clean_rows.append(new_row)
labels = reader.fieldnames + ['hom']
old_rows = list(util.read_csv_rows(out_path))
clean_rows.sort(key=lambda x: util.key_fn(x['root']))
with util.write_csv(out_path, labels) as write_row:
for row in old_rows:
write_row(row)
for row in clean_rows:
write_row(row)
def write_prefixed_shs_verbal_indeclinables(final_path, sandhi_rules,
prefixed_roots, root_converter, out_path):
"""Write prefixed SHS verbal indeclinables."""
sandhi = make_sandhi_object(sandhi_rules)
root_to_prefixed = {}
with util.read_csv(prefixed_roots) as reader:
for row in reader:
root_to_prefixed.setdefault(row['unprefixed_root'], []).append(row)
labels = None
clean_rows = []
with util.read_csv(final_path) as reader:
for row in reader:
root_pair = root_converter.get(row['root'])
if root_pair is None:
continue
root, hom = root_pair
row['root'] = root
for result in root_to_prefixed.get(root, []):
new_row = row.copy()
for field in ['form', 'stem']:
if field in row:
new_row[field] = sandhi.join(
result['prefixes'].split('-') + [new_row[field]])
new_row['root'] = result['prefixed_root']
new_row['hom'] = result['hom']
clean_rows.append(new_row)
labels = reader.fieldnames
labels += ['hom']
old_rows = list(util.read_csv_rows(out_path))
clean_rows.sort(key=lambda x: util.key_fn(x['root']))
with util.write_csv(out_path, labels) as write_row:
for row in old_rows:
write_row(row)
for row in clean_rows:
write_row(row)
