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 variance(freqs):
average = avg(cdr(freqs))
return sum((average - c) ** 2 for c in cdr(freqs)) / average
