def to_html_differences(f, name, combined):
"file*str*{char:[int]} "
print >> f, """<h1>%s</h1>""" % name
print >> f, "<table border=1 cellspacing=0 bordercolor='black'><tr><th>Char</th><th>All</th>",
print >> f, "".join("<th>%s</th>" % f[21:24] for f in fs[1:]), "<th>Avg</th></tr>"
for char, counts in combined.items():
print >> f, "<tr><td>%s</td>" % char,
print >> f, "".join("<td>%s</td>" % c for c in counts),
print >> f, "<td>%.2f</td></tr>" % avg(counts[1:])
print >> f, "</table>"
def groupavg((c1,c2)):
"group average"
return avg(map(compose(edges.__getitem__, frozenset),
cross(flatten(c1), flatten(c2))))
def sed_avg_total((region1, region2)):
"([[{str:[float]}]],[[{str:[float]}]]) -> float"
return lst.avg(map(sed_avg, region1, region2)) / 2
def sed_avg(ws1, ws2):
"[{str:[float]}]*[{str:[float]}] -> float"
segs1,segs2 = (concat(transpose_word(ws1)), concat(transpose_word(ws1)))
return lst.avg(map(fnc.uncurry(feature_sub), lst.cross(segs1, segs2)))
def analyse(regions, avgs=None):
keys = lst.all_pairs(sorted(regions.keys()))
regions = lst.all_pairs(flatten(regions))
avgregions = lst.avg(map(sed_avg_total, regions))
return dict(zip(keys, map(sed_distance(avgregions), regions)))
avgregions = lst.avg(map(sed_avg_total, regions))
return dict(zip(keys, map(sed_distance(avgregions), regions)))
def feature_sub(seg1, seg2):
"({str:float}*{str:float}) -> float"
return (len(set(seg1) ^ set(seg2))
+ sum(abs(f1-f2) for f1,f2 in dct.zip(seg1,seg2).values()))
@curried
def sed_distance(avg, (region1, region2)):
"float*([[{str:[float]}]],[[{str:[float]}]])->float"
return sum(map(sed_levenshtein(avg), zip(region1, region2)))
def transpose_word(word):
"[{str:[float]}] -> [[{str:float}]]"
def transpose_segment(seg):
return [dict(zip(seg.keys(), ns)) for ns in lst.transpose(seg.values())]
return lst.transpose(map(transpose_segment, word))
@curried
def sed_levenshtein(avg,(ws1,ws2)):
"float*([{str:[float]}],[{str:[float]}])->float"
def levenshtein((w1, w2)):
return lev._levenshtein(w1, w2, avg,
(lambda _:avg,lambda _:avg,feature_sub))[-1][-1]
return lst.avg(map(levenshtein,
lst.cross(transpose_word(ws1), transpose_word(ws2))))
def sed_avg(ws1, ws2):
"[{str:[float]}]*[{str:[float]}] -> float"
segs1,segs2 = (concat(transpose_word(ws1)), concat(transpose_word(ws1)))
return lst.avg(map(fnc.uncurry(feature_sub), lst.cross(segs1, segs2)))
def sed_avg_total((region1, region2)):
"([[{str:[float]}]],[[{str:[float]}]]) -> float"
return lst.avg(map(sed_avg, region1, region2)) / 2
def variance(freqs):
average = avg(cdr(freqs))
return sum((average - c) ** 2 for c in cdr(freqs)) / average
def lst_except(l, *ns):
"""Totally inefficient! You have been warned, dude!
(requiring ns to be ordered could help a lot if I actually cared)"""
acc = []
for i, x in enumerate(l):
if i not in ns:
acc.append(x)
return acc
def find_collapsed(f, collapsed):
"{char:[int]} -> [(char,int)] (sorted)"
return sorted(dct.map(f, collapsed).items(), key=snd, reverse=True)
diff = lambda freqs: avg([freqs[2], freqs[8]]) - avg(lst_except(freqs, 0, 2, 8))
def variance(freqs):
average = avg(cdr(freqs))
return sum((average - c) ** 2 for c in cdr(freqs)) / average
find_difference = cur(find_collapsed, diff)
find_variance = cur(find_collapsed, variance)
def to_html_group_differences(f, name, differences):
print >> f, "<h1>%s</h1>" % name
print >> f, "<table border=1 cellspacing=0 bordercolor='black'><tr><td></td><th>Char</th><th>Variance</th>",
for i, (sub, variance) in enumerate(differences):