def SARIngram()

in metrics/sari/sari.py [0:0]

• 55 lines of code
• 20 McCabe index (conditional complexity)

def SARIngram(sgrams, cgrams, rgramslist, numref):
    rgramsall = [rgram for rgrams in rgramslist for rgram in rgrams]
    rgramcounter = Counter(rgramsall)

    sgramcounter = Counter(sgrams)
    sgramcounter_rep = Counter()
    for sgram, scount in sgramcounter.items():
        sgramcounter_rep[sgram] = scount * numref

    cgramcounter = Counter(cgrams)
    cgramcounter_rep = Counter()
    for cgram, ccount in cgramcounter.items():
        cgramcounter_rep[cgram] = ccount * numref

    # KEEP
    keepgramcounter_rep = sgramcounter_rep & cgramcounter_rep
    keepgramcountergood_rep = keepgramcounter_rep & rgramcounter
    keepgramcounterall_rep = sgramcounter_rep & rgramcounter

    keeptmpscore1 = 0
    keeptmpscore2 = 0
    for keepgram in keepgramcountergood_rep:
        keeptmpscore1 += keepgramcountergood_rep[keepgram] / keepgramcounter_rep[keepgram]
        # Fix an alleged bug [2] in the keep score computation.
        # keeptmpscore2 += keepgramcountergood_rep[keepgram] / keepgramcounterall_rep[keepgram]
        keeptmpscore2 += keepgramcountergood_rep[keepgram]
    # Define 0/0=1 instead of 0 to give higher scores for predictions that match
    #      a target exactly.
    keepscore_precision = 1
    keepscore_recall = 1
    if len(keepgramcounter_rep) > 0:
        keepscore_precision = keeptmpscore1 / len(keepgramcounter_rep)
    if len(keepgramcounterall_rep) > 0:
        # Fix an alleged bug [2] in the keep score computation.
        # keepscore_recall = keeptmpscore2 / len(keepgramcounterall_rep)
        keepscore_recall = keeptmpscore2 / sum(keepgramcounterall_rep.values())
    keepscore = 0
    if keepscore_precision > 0 or keepscore_recall > 0:
        keepscore = 2 * keepscore_precision * keepscore_recall / (keepscore_precision + keepscore_recall)

    # DELETION
    delgramcounter_rep = sgramcounter_rep - cgramcounter_rep
    delgramcountergood_rep = delgramcounter_rep - rgramcounter
    delgramcounterall_rep = sgramcounter_rep - rgramcounter
    deltmpscore1 = 0
    deltmpscore2 = 0
    for delgram in delgramcountergood_rep:
        deltmpscore1 += delgramcountergood_rep[delgram] / delgramcounter_rep[delgram]
        deltmpscore2 += delgramcountergood_rep[delgram] / delgramcounterall_rep[delgram]
    # Define 0/0=1 instead of 0 to give higher scores for predictions that match
    # a target exactly.
    delscore_precision = 1
    if len(delgramcounter_rep) > 0:
        delscore_precision = deltmpscore1 / len(delgramcounter_rep)

    # ADDITION
    addgramcounter = set(cgramcounter) - set(sgramcounter)
    addgramcountergood = set(addgramcounter) & set(rgramcounter)
    addgramcounterall = set(rgramcounter) - set(sgramcounter)

    addtmpscore = 0
    for addgram in addgramcountergood:
        addtmpscore += 1

    # Define 0/0=1 instead of 0 to give higher scores for predictions that match
    # a target exactly.
    addscore_precision = 1
    addscore_recall = 1
    if len(addgramcounter) > 0:
        addscore_precision = addtmpscore / len(addgramcounter)
    if len(addgramcounterall) > 0:
        addscore_recall = addtmpscore / len(addgramcounterall)
    addscore = 0
    if addscore_precision > 0 or addscore_recall > 0:
        addscore = 2 * addscore_precision * addscore_recall / (addscore_precision + addscore_recall)

    return (keepscore, delscore_precision, addscore)