def normalizedEdgesFrom(self, node):
lst = ADict()
for new_node, edge in self.fsm.edgesFrom(node):
isym = edge[0]
osym = edge[1]
if len(edge) == 2:
weight = 1
else:
weight = edge[2]
lst[new_node, isym, osym] += weight
lst_sum = float(lst.sum())
lst_sum = 1
for (new_node, isym, osym), weight in lst.iteritems():
weight /= lst_sum
yield new_node, isym, osym, weight
def normalizedEdgesFrom(self, node):
lst = ADict()
for new_node, edge in self.fsm.edgesFrom(node):
isym = edge[0]
osym = edge[1]
if len(edge) == 2:
weight = 1
else:
weight = edge[2]
lst[new_node, isym, osym] += weight
lst_sum = float(lst.sum())
lst_sum = 1
for (new_node, isym, osym), weight in lst.iteritems():
weight /= lst_sum
yield new_node, isym, osym, weight
def genStates(self):
processed = set()
backoff_stat = ADict(default=set)
osym_map = SymMap()
osym_map['epsilon'] = 0
pop_Given_C = self.workspace[gmtk.SCPT, 'popGivenC1C2C3C4']
push_Given_C = self.workspace[gmtk.SCPT, 'pushGivenC1C2C3C4']
c1_Given_C234 = self.workspace[gmtk.SCPT, 'concept1GivenC2C3C4']
c1_Given_C23 = self.workspace[gmtk.SCPT, 'concept1GivenC2C3']
c1_Given_C2 = self.workspace[gmtk.DCPT, 'concept1GivenC2']
c1_backoff = self.workspace[gmtk.DT, 'backoffC2C3C4']
c2_Given_C = self.workspace[gmtk.SCPT, 'concept2GivenC3C4']
s1_Given_C1234 = self.workspace[gmtk.SCPT, 's1GivenC1C2C3C4']
s1_Given_C123 = self.workspace[gmtk.SCPT, 's1GivenC1C2C3']
s1_Given_C12 = self.workspace[gmtk.SCPT, 's1GivenC1C2']
s1_Given_C1 = self.workspace[gmtk.DCPT, 's1GivenC1']
s1_Unigram = self.workspace[gmtk.DCPT, 's1Unigram']
s1_backoff = self.workspace[gmtk.DT, 'backoffC1C2C3C4']
s2_Given_C1234 = self.workspace[gmtk.SCPT, 's2GivenC1C2C3C4']
s2_Given_C123 = self.workspace[gmtk.SCPT, 's2GivenC1C2C3']
s2_Given_C12 = self.workspace[gmtk.SCPT, 's2GivenC1C2']
s2_Given_C1 = self.workspace[gmtk.DCPT, 's2GivenC1']
s2_Unigram = self.workspace[gmtk.DCPT, 's2Unigram']
s3_Given_C1234 = self.workspace[gmtk.SCPT, 's3GivenC1C2C3C4']
s3_Given_C123 = self.workspace[gmtk.SCPT, 's3GivenC1C2C3']
s3_Given_C12 = self.workspace[gmtk.SCPT, 's3GivenC1C2']
s3_Given_C1 = self.workspace[gmtk.DCPT, 's3GivenC1']
s3_Unigram = self.workspace[gmtk.DCPT, 's3Unigram']
conceptMap = self.conceptMap
_EMPTY_ = conceptMap[EMPTY_CONCEPT]
_DUMMY_ = conceptMap.get(DUMMY_CONCEPT, None)
allConcepts = sorted(conceptMap.values())
symbols = []
maps = []
maps2 = []
count = 1
pte_map = SymMap()
pte_map2 = SymMap()
if self.pteMap:
pte_symbols = sorted(self.pteMap.values())
for key, value in sorted(self.pteMap.items()):
pte_map[value] = value+count
pte_map2[key] = value+count
count += len(pte_map)
else:
pte_symbols = []
for map in self.symbolMaps:
if map is None:
map = {}
symbols.append(sorted(map.values()))
new_map = SymMap()
new_map2 = SymMap()
for key, value in sorted(map.items()):
new_map[value] = value+count
new_map2[key] = value+count
count += len(new_map)
maps.append(new_map)
maps2.append(new_map2)
s0 = (_EMPTY_,)*4
s0_expanded = False
cutoff_sym = self.cutoff_sym
cutoff_trans = self.cutoff_trans
max_states = self.max_states
logger = self.logger
stack = [(0, 0, s0)]
stack_set = set([s0])
state_map = SymMap()
state_map[s0] = 0
_pop_ = self._pop_
interim_counter = 0
n_arcs = 0
while stack:
if max_states is None:
total_states = len(state_map) - interim_counter
else:
total_states = max_states
if logger is not None:
logger.debug(' #states (unexpanded/total) %.2f%%, %d/%d, #arcs %d', 100.*len(processed)/total_states, total_states-len(processed), total_states, n_arcs)
c_t_backoff, c_t_dist, c_t = stack.pop(0)
backoff_stat[c_t_backoff].add(c_t)
if logger is not None:
logger.debug(' %.2f: %s, backoff=%d', c_t_dist, self.strState(c_t), c_t_backoff)
state_c_t = state_map[c_t]
processed.add(c_t)
stack_set.remove(c_t)
ret = []
pop_pmf = list(pop_Given_C[: c_t[0], c_t[1], c_t[2], c_t[3]])
push_pmf = list(push_Given_C[: c_t[0], c_t[1], c_t[2], c_t[3]])
for pop in range(0, MAX_POP+1):
prob_pop = pop_pmf[pop]
if prob_pop <= cutoff_trans:
continue
interim_counter += 1
c_inter = c_t[pop:] + (_EMPTY_, ) * pop
osym = ')'*pop
if not osym:
osym = 'epsilon'
ret.append( (prob_pop, c_t, (c_t, c_inter), _pop_, osym) )
for push in range(0, MAX_PUSH+1):
prob_push = push_pmf[push]
if push == 0:
to_push_all = [()]
else:
to_push_all = cartezian(*[allConcepts]*push)
for to_push in to_push_all:
c_new = (to_push + c_inter)[:DEPTH]
if (c_t == c_new) and not (push == pop == 0):
continue
if _DUMMY_ in c_new[1:]:
continue
# Output symbol
osym = ''
for push_concept in reversed(to_push):
osym += conceptMap.inverse[push_concept]+'('
if not osym:
osym = 'epsilon'
# Smoothing
backoff = c1_backoff[c_new[1], c_new[2], c_new[3]]
if backoff == 0:
c1_pmf = c1_Given_C234[: c_new[1], c_new[2], c_new[3]]
elif backoff == 1:
c1_pmf = c1_Given_C23[: c_new[1], c_new[2]]
else:
c1_pmf = c1_Given_C2[: c_new[1]]
c2_pmf = c2_Given_C[: c_new[2], c_new[3]]
if push == 0:
prob_new_c = 1.0
elif push == 1:
prob_new_c = c1_pmf[to_push[0]]
elif push == 2:
prob_new_c = c1_pmf[to_push[0]] * c2_pmf[to_push[1]]
prob_trans = prob_push * prob_new_c
# Do cut-off
if prob_trans <= cutoff_trans:
continue
# Smoothing
backoff = s1_backoff[c_new[0], c_new[1], c_new[2], c_new[3]]
if backoff == 0:
s_pmf = [list(s1_Given_C1234[: c_new[0], c_new[1], c_new[2], c_new[3]]),
list(s2_Given_C1234[: c_new[0], c_new[1], c_new[2], c_new[3]]),
list(s3_Given_C1234[: c_new[0], c_new[1], c_new[2], c_new[3]])]
elif backoff == 1:
s_pmf = [list(s1_Given_C123[: c_new[0], c_new[1], c_new[2]]),
list(s2_Given_C123[: c_new[0], c_new[1], c_new[2]]),
list(s3_Given_C123[: c_new[0], c_new[1], c_new[2]])]
elif backoff == 2:
s_pmf = [list(s1_Given_C12[: c_new[0], c_new[1]]),
list(s2_Given_C12[: c_new[0], c_new[1]]),
list(s3_Given_C12[: c_new[0], c_new[1]])]
elif backoff == 3:
s_pmf = [list(s1_Given_C1[: c_new[0]]),
list(s2_Given_C1[: c_new[0]]),
list(s3_Given_C1[: c_new[0]])]
else:
s_pmf = [list(s1_Unigram),
list(s2_Unigram),
list(s3_Unigram)]
if c_new not in processed and c_new not in stack_set:
stack_set.add(c_new)
c_new_dist = (c_t_dist-log(prob_trans))
insort(stack, (backoff, c_t_dist-log(prob_trans), c_new))
c_next = (c_t, c_inter)
if pte_symbols and c_inter == (_EMPTY_,)*4 and push != 0:
for pte_sym in pte_symbols:
prob_ptesym = 1.0
pte_sym = pte_map[pte_sym]
pte_osym = pte_map2.inverse[pte_sym]
ret.append( (prob_trans*prob_ptesym, c_next, c_new, pte_sym, pte_osym) )
prob_trans = 1.0
c_next = c_new
for sym, map, pmf in zip(symbols, maps, s_pmf):
if map is None:
continue
for isym in sym:
prob_isym = pmf[isym]
# Do cut-off
if prob_isym <= cutoff_sym:
continue
else:
isym = map[isym]
ret.append( (prob_trans*prob_isym, c_next, c_new, isym, osym) )
# For symbols other than the first
prob_trans = 1.0
c_next = c_new
osym = 'epsilon'
for prob, c_t, c_new, isym, osym in ret:
state_c_new = state_map.add(c_new)
state_c_t = state_map.add(c_t)
osym = osym_map.add(osym)
n_arcs += 1
yield state_c_t, state_c_new, isym, osym, prob
if max_states is not None and len(processed) >= max_states:
break
self.stateMap = self.convertStateMap(state_map)
self.osymMap = osym_map
self.isymMaps = maps2
self.ipteMap = pte_map2
backoff_stat = ADict((k, len(v)) for (k,v) in backoff_stat.iteritems())
if logger is not None:
logger.debug('Backoff statistics:')
logger.debug('===================')
total = backoff_stat.sum()
for key, value in sorted(backoff_stat.items()):
logger.debug(' backoff=%d: #%d (%.2f%%)', key, value, 100.*value/total)
def sresults(self,
files,
fw=sys.stdout,
only=[],
skip=[],
twoside=False,
groupby='none'):
"""Print HResults-like statistics of system's output
"""
if not only:
only = None
if not skip:
skip = None
tH = tD = tS = tI = tN = 0
uH = uN = 0
tHit = ADict()
tMiss = ADict()
tFA = ADict()
strftime = time.strftime('%a, %d %b %Y %H:%M:%S')
fw.write(
'----------------------- Semantics Scores --------------------------\n'
)
for fn1, fn2 in self.genFnPairs(files, twoside):
forest1, forest2 = self.loadForestFiles((fn1, fn2), only, skip)
fw.write(
'====================== CDC Results Analysis =======================\n'
)
fw.write(' Date: %s\n' % strftime)
fw.write(' Ref : %s\n' % fn1)
fw.write(' Rec : %s\n' % fn2)
fw.write(
'-------------------------- File Results ---------------------------\n'
)
processor = self.forestProcessor(forest1, forest2)
H = N = D = I = S = 0
last_group = None
for fn, tree1, tree2, dist, script in processor:
new_group = self.groupMapping(fn, groupby)
if last_group is None:
last_group = new_group
if new_group != last_group:
# Doslo ke zmene skupiny, vypisu charakteristiky
if N != 0:
Corr = (float(H) / N) * 100.
Acc = (float(H - I) / N) * 100.
else:
Corr = Acc = 0.
fw.write('%s: %6.2f(%6.2f) [H=%4d, D=%3d, S=%3d, I=%3d, N=%3d]\n' % \
(last_group, Corr, Acc, H, D, S, I, N))
tH += H
tD += D
tS += S
tI += I
tN += N
if S == 0 and I == 0 and D == 0:
assert H == N
uH += 1
uN += 1
# Vynulovani prubeznych skupinovych charakteristik
H = N = D = I = S = 0
# Nastaveni nove skupiny
last_group = new_group
lH, lD, lI, lS = script.HDIS
H += lH
D += lD
I += lI
S += lS
N += script.numConcepts[0]
hit, miss, fa = script.hitMissFA
tHit += hit
tMiss += miss
tFA += fa
else:
# Vypsani za posledni skupinu
if N != 0:
Corr = (float(H) / N) * 100.
Acc = (float(H - I) / N) * 100.
else:
Corr = Acc = 0.
fw.write('%s: %6.2f(%6.2f) [H=%4d, D=%3d, S=%3d, I=%3d, N=%3d]\n' % \
(last_group, Corr, Acc, H, D, S, I, N))
tH += H
tD += D
tS += S
tI += I
tN += N
if S == 0 and I == 0 and D == 0:
assert H == N
uH += 1
uN += 1
tCorr = 100. * tH / tN
tAcc = 100. * (tH - tI) / tN
uS = uN - uH
uCorr = 100. * uH / uN
fw.write(
'------------------------ Concept Results --------------------------\n'
)
allConcepts = (tHit + tMiss + tFA).keys()
allResults = []
for concept in sorted(allConcepts):
C = float(tHit[concept])
FA = float(tFA[concept])
M = float(tMiss[concept])
if C + FA > 0:
Prec = C / (C + FA) * 100
else:
Prec = 0
if C + M > 0:
Recall = C / (C + M) * 100
else:
Recall = 0
if Prec + Recall > 0:
F = 2 * Prec * Recall / (Prec + Recall)
else:
F = 0
allResults.append((F, concept, Prec, Recall, C, M, FA))
for F, concept, Prec, Recall, C, M, FA in sorted(allResults,
reverse=True):
fw.write('%-15s: F=%6.2f, P=%6.2f, R=%6.2f [C=%d, M=%d, FA=%d]\n' %
(concept, F, Prec, Recall, C, M, FA))
tC = float(tHit.sum())
tM = float(tMiss.sum())
tFA = float(tFA.sum())
tPrec = tC / (tC + tFA) * 100
tRecall = tC / (tC + tM) * 100
tF = 2 * tPrec * tRecall / (tPrec + tRecall)
fw.write(
'------------------------ Overall Results --------------------------\n'
)
fw.write('UTTR: %%Correct=%.2f [H=%d, S=%d, N=%d]\n' %
(uCorr, uH, uS, uN))
fw.write('CONC: F=%.2f, P=%.2f, R=%.2f [C=%d, M=%d, FA=%d]\n' %
(tF, tPrec, tRecall, tC, tM, tFA))
fw.write(
' %%Corr=%.2f, Acc=%.2f [H=%d, D=%d, S=%d, I=%d, N=%d]\n' %
(tCorr, tAcc, tH, tD, tS, tI, tN))
fw.write(
'===================================================================\n'
)
ret = {}
ret['cCorr'] = tCorr
ret['cAcc'] = tAcc
ret['cH'] = tH
ret['cD'] = tD
ret['cS'] = tS
ret['cI'] = tI
ret['cN'] = tN
ret['uCorr'] = uCorr
ret['uH'] = uH
ret['uS'] = uS
ret['uN'] = uN
ret['Prec'] = tPrec
ret['Recall'] = tRecall
ret['F'] = tF
return ret
def genStates(self):
processed = set()
backoff_stat = ADict(default=set)
osym_map = SymMap()
osym_map['epsilon'] = 0
pop_Given_C = self.workspace[gmtk.SCPT, 'popGivenC1C2C3C4']
push_Given_C = self.workspace[gmtk.SCPT, 'pushGivenC1C2C3C4']
c1_Given_C234 = self.workspace[gmtk.SCPT, 'concept1GivenC2C3C4']
c1_Given_C23 = self.workspace[gmtk.SCPT, 'concept1GivenC2C3']
c1_Given_C2 = self.workspace[gmtk.DCPT, 'concept1GivenC2']
c1_backoff = self.workspace[gmtk.DT, 'backoffC2C3C4']
c2_Given_C = self.workspace[gmtk.SCPT, 'concept2GivenC3C4']
s1_Given_C1234 = self.workspace[gmtk.SCPT, 's1GivenC1C2C3C4']
s1_Given_C123 = self.workspace[gmtk.SCPT, 's1GivenC1C2C3']
s1_Given_C12 = self.workspace[gmtk.SCPT, 's1GivenC1C2']
s1_Given_C1 = self.workspace[gmtk.DCPT, 's1GivenC1']
s1_Unigram = self.workspace[gmtk.DCPT, 's1Unigram']
s1_backoff = self.workspace[gmtk.DT, 'backoffC1C2C3C4']
s2_Given_C1234 = self.workspace[gmtk.SCPT, 's2GivenC1C2C3C4']
s2_Given_C123 = self.workspace[gmtk.SCPT, 's2GivenC1C2C3']
s2_Given_C12 = self.workspace[gmtk.SCPT, 's2GivenC1C2']
s2_Given_C1 = self.workspace[gmtk.DCPT, 's2GivenC1']
s2_Unigram = self.workspace[gmtk.DCPT, 's2Unigram']
s3_Given_C1234 = self.workspace[gmtk.SCPT, 's3GivenC1C2C3C4']
s3_Given_C123 = self.workspace[gmtk.SCPT, 's3GivenC1C2C3']
s3_Given_C12 = self.workspace[gmtk.SCPT, 's3GivenC1C2']
s3_Given_C1 = self.workspace[gmtk.DCPT, 's3GivenC1']
s3_Unigram = self.workspace[gmtk.DCPT, 's3Unigram']
conceptMap = self.conceptMap
_EMPTY_ = conceptMap[EMPTY_CONCEPT]
_DUMMY_ = conceptMap.get(DUMMY_CONCEPT, None)
allConcepts = sorted(conceptMap.values())
symbols = []
maps = []
maps2 = []
count = 1
pte_map = SymMap()
pte_map2 = SymMap()
if self.pteMap:
pte_symbols = sorted(self.pteMap.values())
for key, value in sorted(self.pteMap.items()):
pte_map[value] = value + count
pte_map2[key] = value + count
count += len(pte_map)
else:
pte_symbols = []
for map in self.symbolMaps:
if map is None:
map = {}
symbols.append(sorted(map.values()))
new_map = SymMap()
new_map2 = SymMap()
for key, value in sorted(map.items()):
new_map[value] = value + count
new_map2[key] = value + count
count += len(new_map)
maps.append(new_map)
maps2.append(new_map2)
s0 = (_EMPTY_, ) * 4
s0_expanded = False
cutoff_sym = self.cutoff_sym
cutoff_trans = self.cutoff_trans
max_states = self.max_states
logger = self.logger
stack = [(0, 0, s0)]
stack_set = set([s0])
state_map = SymMap()
state_map[s0] = 0
_pop_ = self._pop_
interim_counter = 0
n_arcs = 0
while stack:
if max_states is None:
total_states = len(state_map) - interim_counter
else:
total_states = max_states
if logger is not None:
logger.debug(
' #states (unexpanded/total) %.2f%%, %d/%d, #arcs %d',
100. * len(processed) / total_states,
total_states - len(processed), total_states, n_arcs)
c_t_backoff, c_t_dist, c_t = stack.pop(0)
backoff_stat[c_t_backoff].add(c_t)
if logger is not None:
logger.debug(' %.2f: %s, backoff=%d', c_t_dist,
self.strState(c_t), c_t_backoff)
state_c_t = state_map[c_t]
processed.add(c_t)
stack_set.remove(c_t)
ret = []
pop_pmf = list(pop_Given_C[:c_t[0], c_t[1], c_t[2], c_t[3]])
push_pmf = list(push_Given_C[:c_t[0], c_t[1], c_t[2], c_t[3]])
for pop in range(0, MAX_POP + 1):
prob_pop = pop_pmf[pop]
if prob_pop <= cutoff_trans:
continue
interim_counter += 1
c_inter = c_t[pop:] + (_EMPTY_, ) * pop
osym = ')' * pop
if not osym:
osym = 'epsilon'
ret.append((prob_pop, c_t, (c_t, c_inter), _pop_, osym))
for push in range(0, MAX_PUSH + 1):
prob_push = push_pmf[push]
if push == 0:
to_push_all = [()]
else:
to_push_all = cartezian(*[allConcepts] * push)
for to_push in to_push_all:
c_new = (to_push + c_inter)[:DEPTH]
if (c_t == c_new) and not (push == pop == 0):
continue
if _DUMMY_ in c_new[1:]:
continue
# Output symbol
osym = ''
for push_concept in reversed(to_push):
osym += conceptMap.inverse[push_concept] + '('
if not osym:
osym = 'epsilon'
# Smoothing
backoff = c1_backoff[c_new[1], c_new[2], c_new[3]]
if backoff == 0:
c1_pmf = c1_Given_C234[:c_new[1], c_new[2],
c_new[3]]
elif backoff == 1:
c1_pmf = c1_Given_C23[:c_new[1], c_new[2]]
else:
c1_pmf = c1_Given_C2[:c_new[1]]
c2_pmf = c2_Given_C[:c_new[2], c_new[3]]
if push == 0:
prob_new_c = 1.0
elif push == 1:
prob_new_c = c1_pmf[to_push[0]]
elif push == 2:
prob_new_c = c1_pmf[to_push[0]] * c2_pmf[
to_push[1]]
prob_trans = prob_push * prob_new_c
# Do cut-off
if prob_trans <= cutoff_trans:
continue
# Smoothing
backoff = s1_backoff[c_new[0], c_new[1], c_new[2],
c_new[3]]
if backoff == 0:
s_pmf = [
list(s1_Given_C1234[:c_new[0], c_new[1],
c_new[2], c_new[3]]),
list(s2_Given_C1234[:c_new[0], c_new[1],
c_new[2], c_new[3]]),
list(s3_Given_C1234[:c_new[0], c_new[1],
c_new[2], c_new[3]])
]
elif backoff == 1:
s_pmf = [
list(s1_Given_C123[:c_new[0], c_new[1],
c_new[2]]),
list(s2_Given_C123[:c_new[0], c_new[1],
c_new[2]]),
list(s3_Given_C123[:c_new[0], c_new[1],
c_new[2]])
]
elif backoff == 2:
s_pmf = [
list(s1_Given_C12[:c_new[0], c_new[1]]),
list(s2_Given_C12[:c_new[0], c_new[1]]),
list(s3_Given_C12[:c_new[0], c_new[1]])
]
elif backoff == 3:
s_pmf = [
list(s1_Given_C1[:c_new[0]]),
list(s2_Given_C1[:c_new[0]]),
list(s3_Given_C1[:c_new[0]])
]
else:
s_pmf = [
list(s1_Unigram),
list(s2_Unigram),
list(s3_Unigram)
]
if c_new not in processed and c_new not in stack_set:
stack_set.add(c_new)
c_new_dist = (c_t_dist - log(prob_trans))
insort(
stack,
(backoff, c_t_dist - log(prob_trans), c_new))
c_next = (c_t, c_inter)
if pte_symbols and c_inter == (
_EMPTY_, ) * 4 and push != 0:
for pte_sym in pte_symbols:
prob_ptesym = 1.0
pte_sym = pte_map[pte_sym]
pte_osym = pte_map2.inverse[pte_sym]
ret.append((prob_trans * prob_ptesym, c_next,
c_new, pte_sym, pte_osym))
prob_trans = 1.0
c_next = c_new
for sym, map, pmf in zip(symbols, maps, s_pmf):
if map is None:
continue
for isym in sym:
prob_isym = pmf[isym]
# Do cut-off
if prob_isym <= cutoff_sym:
continue
else:
isym = map[isym]
ret.append((prob_trans * prob_isym, c_next,
c_new, isym, osym))
# For symbols other than the first
prob_trans = 1.0
c_next = c_new
osym = 'epsilon'
for prob, c_t, c_new, isym, osym in ret:
state_c_new = state_map.add(c_new)
state_c_t = state_map.add(c_t)
osym = osym_map.add(osym)
n_arcs += 1
yield state_c_t, state_c_new, isym, osym, prob
if max_states is not None and len(processed) >= max_states:
break
self.stateMap = self.convertStateMap(state_map)
self.osymMap = osym_map
self.isymMaps = maps2
self.ipteMap = pte_map2
backoff_stat = ADict(
(k, len(v)) for (k, v) in backoff_stat.iteritems())
if logger is not None:
logger.debug('Backoff statistics:')
logger.debug('===================')
total = backoff_stat.sum()
for key, value in sorted(backoff_stat.items()):
logger.debug(' backoff=%d: #%d (%.2f%%)', key, value,
100. * value / total)
def sresults(self, files, fw=sys.stdout, only=[], skip=[], twoside=False, groupby='none'):
"""Print HResults-like statistics of system's output
"""
if not only:
only = None
if not skip:
skip = None
tH = tD = tS = tI = tN = 0
uH = uN = 0
tHit = ADict()
tMiss = ADict()
tFA = ADict()
strftime = time.strftime('%a, %d %b %Y %H:%M:%S')
fw.write('----------------------- Semantics Scores --------------------------\n')
for fn1, fn2 in self.genFnPairs(files, twoside):
forest1, forest2 = self.loadForestFiles((fn1, fn2), only, skip)
fw.write('====================== CDC Results Analysis =======================\n')
fw.write(' Date: %s\n' % strftime)
fw.write(' Ref : %s\n' % fn1)
fw.write(' Rec : %s\n' % fn2)
fw.write('-------------------------- File Results ---------------------------\n')
processor = self.forestProcessor(forest1, forest2)
H = N = D = I = S = 0
last_group = None
for fn, tree1, tree2, dist, script in processor:
new_group = self.groupMapping(fn, groupby)
if last_group is None:
last_group = new_group
if new_group != last_group:
# Doslo ke zmene skupiny, vypisu charakteristiky
if N != 0:
Corr = (float(H)/N)*100.
Acc = (float(H-I)/N)*100.
else:
Corr = Acc = 0.
fw.write('%s: %6.2f(%6.2f) [H=%4d, D=%3d, S=%3d, I=%3d, N=%3d]\n' % \
(last_group, Corr, Acc, H, D, S, I, N))
tH += H; tD += D; tS += S;
tI += I; tN += N
if S == 0 and I == 0 and D == 0:
assert H == N
uH += 1
uN += 1
# Vynulovani prubeznych skupinovych charakteristik
H = N = D = I = S = 0
# Nastaveni nove skupiny
last_group = new_group
lH, lD, lI, lS = script.HDIS
H += lH
D += lD
I += lI
S += lS
N += script.numConcepts[0]
hit, miss, fa = script.hitMissFA
tHit += hit
tMiss += miss
tFA += fa
else:
# Vypsani za posledni skupinu
if N != 0:
Corr = (float(H)/N)*100.
Acc = (float(H-I)/N)*100.
else:
Corr = Acc = 0.
fw.write('%s: %6.2f(%6.2f) [H=%4d, D=%3d, S=%3d, I=%3d, N=%3d]\n' % \
(last_group, Corr, Acc, H, D, S, I, N))
tH += H; tD += D; tS += S;
tI += I; tN += N
if S == 0 and I == 0 and D == 0:
assert H == N
uH += 1
uN += 1
tCorr = 100. * tH / tN
tAcc = 100. * (tH - tI) / tN
uS = uN - uH
uCorr = 100. * uH / uN
fw.write('------------------------ Concept Results --------------------------\n')
allConcepts = (tHit+tMiss+tFA).keys()
allResults = []
for concept in sorted(allConcepts):
C = float(tHit[concept])
FA = float(tFA[concept])
M = float(tMiss[concept])
if C+FA > 0:
Prec = C / (C+FA) * 100
else:
Prec = 0
if C+M > 0:
Recall = C / (C+M) * 100
else:
Recall = 0
if Prec+Recall > 0:
F = 2*Prec*Recall/(Prec+Recall)
else:
F = 0
allResults.append((F, concept, Prec, Recall, C, M, FA))
for F, concept,Prec, Recall, C, M, FA in sorted(allResults, reverse=True):
fw.write('%-15s: F=%6.2f, P=%6.2f, R=%6.2f [C=%d, M=%d, FA=%d]\n' % (concept, F, Prec, Recall, C, M, FA))
tC = float(tHit.sum())
tM = float(tMiss.sum())
tFA = float(tFA.sum())
tPrec = tC / (tC+tFA) * 100
tRecall = tC / (tC+tM) * 100
tF = 2*tPrec*tRecall/(tPrec+tRecall)
fw.write('------------------------ Overall Results --------------------------\n')
fw.write('UTTR: %%Correct=%.2f [H=%d, S=%d, N=%d]\n' % (uCorr, uH, uS, uN))
fw.write('CONC: F=%.2f, P=%.2f, R=%.2f [C=%d, M=%d, FA=%d]\n' % (tF, tPrec, tRecall, tC, tM, tFA))
fw.write(' %%Corr=%.2f, Acc=%.2f [H=%d, D=%d, S=%d, I=%d, N=%d]\n' % (tCorr, tAcc, tH, tD, tS, tI, tN))
fw.write('===================================================================\n')
ret = {}
ret['cCorr'] = tCorr
ret['cAcc'] = tAcc
ret['cH'] = tH
ret['cD'] = tD
ret['cS'] = tS
ret['cI'] = tI
ret['cN'] = tN
ret['uCorr'] = uCorr
ret['uH'] = uH
ret['uS'] = uS
ret['uN'] = uN
ret['Prec'] = tPrec
ret['Recall'] = tRecall
ret['F'] = tF
return ret
