def group_words(csv):
"[[str]]-> {str:{str:{str:[float]}}} ie {Word:{Segment:{Feature:[Value]}}}"
segment_name = lambda s: s[:re.search('[0-9]', s).end()]
segment = fnc.pipe(car, dropwhile(str.islower), segment_name)
feature = lambda s: s[re.search('[0-9]', s).end():]
fillsegments = curried(dct.map_items)(makesegment)
features = carcdr(lambda title, data:(feature(title), map(float, data)))
phones = lambda l: dct.map(dict, dct.collapse(l, segment, features))
words = dct.collapse(cdr(csv),
fnc.pipe(car, takewhile(str.islower)),
fnc.ident)
return dct.map(fnc.pipe(phones, fillsegments), words)
def groupedSites(path, sites):
"path*[site] -> {site:[filename]}"
corpora = dct.collapse(filter(visible, os.listdir(path)),
keymap=lambda f: findif(f.startswith, sites))
if None in corpora:
# print ("Missing:", corpora[None])
del corpora[None]
return corpora
def sentences(lines):
#@typecheck([str], [(str, [object])], n=int)
def parseloop(lines, n=0):
return [(clean(lines[0]),
parseloop(lines[1:], n=n+1) if lines[1:] else [])
for lines in splitby(lambda line:n==indent(line), lines, True)]
return dct.collapse(filter(None, splitby(elem('<sent>'), lines, first=True)),
pipe(car, speaker_code),
pipe(cdr, cur(filter, useful), parseloop, car))
def classify(row):
"[[lev.Rule]] -> {utf-8-char:set<lev.Rule>}"
return dct.map(
set, dct.collapse(filter(negate(self_sub), concat(row)), keymap=lambda rule: rule.src) # collapse_envs,
)
