def find(self, refs, tagged_sentences):
ref_dict = {} # reference map by sentence index
for prp, fullname, index in refs:
if index not in ref_dict:
ref_dict[index] = [prp, fullname, index]
else:
ref_dict[index].append([prp, fullname, index])
names = utils.get_names_dict(utils.people)
# TODO:
# find PRP/name, VRB, PRP/name for - 1
# memory for people: name/name/name/... (they did) - 2
interact = []
for index, sentence in enumerate(tagged_sentences):
chunked_sentence = regexp.CustomChunker().parse(sentence)
retaged_sentence = utils.retag_chunked(chunked_sentence)
new_tagged_sentence = utils.mark_sentence_names(retaged_sentence, names)
# find prepositions, replace with real names and print what they did
who, what, prp, seq = [], [], [], []
prp_counter = 0
for (word, tag, piece, pt) in new_tagged_sentence:
reset = True
w = word.lower()
if tag.startswith("PRP"): # this is a reference
if (w in ("he", "she", "his", "him", "her", "i", "me", "our")):
if index in ref_dict:
who.append(ref_dict[index][1]) # PRP-person mapping exists
prp.append(word)
else:
who.append(None) # PRP exists without mapped person
prp.append(word)
elif w in names:
# this word belongs to a person name, there's no PRP for it
who.append(word)
prp.append(None)
elif piece in ('TARINYS'): #TODO: add some details to extracted actions
reset = False
seq.append(word)
if reset and len(seq) > 0: # join neighbouring verbs if possible
what.append(" ".join(seq))
seq = []
if len(who) > 1 and len(what) > 0: # only show people & their interactions that include an action
# capitalize each person name/surname first letter
for i, boo in enumerate(who):
if boo:
who[i] = " ".join([part[0].upper()+part[1:] for part in boo.split(" ")])
interact.append({'who':who, 'prp': prp, 'what':what})
return interact
def find(self, people, sentences, tagged_sentences):
# create a all possible lowercase names & drink beer later :P
names = utils.get_names_dict(people)
# find names in text and mark them with special symbols & append additional data
new_tagged_sentences = []
for index, sentence in enumerate(tagged_sentences):
sent = []
for word, tag in sentence:
key = word.lower()
if key in names:
sent.append((word.lower(), tag, '+', names[key])) # add `+` to a name & include data
else:
sent.append((word.lower(), tag, 'o', None)) # not a name - mark as `o`
new_tagged_sentences.append(sent)
# store references as lists: [PRP, fullname, sentence_index]
refs = []
# store last he & she while scanning sentences,
# if unknown sex name is found - store it also (determine type on first PRP found)
last_he = [None, 0] # store as: [people_data, word_index_in_text]
last_she = [None, 0]
last_unknown = [None, 0]
word_index = 0
for index, sentence in enumerate(new_tagged_sentences):
for element in sentence:
word, tag, flag, data = element # unpack all data
word_index += 1 # increase processed words index
if tag.startswith("PRP") and len(word) <= 5 and (word not in ("it", "our", "their", "us", "its", "we", "they")): # a determined reference was found!
### unknown sex resolver
if last_unknown[0]: # if we have an unknown name without sex, then assign the next first found sex to it
gender = self.get_gender(word)
print "Last unknown person -", last_unknown[0]['fullname'], "- was assigned sex:", gender
last_unknown[0]['sex'] = gender
# the hack has been fixed :P
if gender == "male":
if last_he[0]: # last `he` exists
if last_he[1] < last_unknown[1]: # override if unknown is newer
last_he = last_unknown
else:
last_he = last_unknown # override as no `he` exists
elif gender == "female":
if last_she[0]:
if last_she[1] < last_unknown[1]:
last_she = last_unknown
else:
last_she = last_unknown
if gender in ("male", "female"): # clear only if actualy determined
last_unknown = [None, 0] # clear
#### determine the person mentioned
#print "*"*80
matched = None
if word in ("he", "his", "him") and last_he[0]: # male
matched = last_he
elif word in ("she", "her") and last_she[0]: # female
matched = last_she
elif word in ("i", "me", "our"): # cannot determine sex - as multi
if last_he[0] and last_she[0]: # we have both sex types in memory, choose the last one mentioned
if last_he[1] > last_she[1]: # he is more fresh
matched = last_he
else: # she is more fresh
matched = last_she
elif last_he[0]: # we have only `he` in memory
matched = last_he
elif last_she[0]: # we have only `she` in memory
matched = last_she
if matched: # refresh index - this person has been just mentioned
matched[1] = word_index
#print "REF[", word, "] is -", matched[0]['fullname'], "- in sentence Nr.", index
refs.append([word, matched[0]['fullname'], index])
else:
#print "REF[", word, "] is", "UNKNOWN", "in sentence Nr.", index
refs.append([word, "?", index])
#print "\t", sentences[index] # show the corresponding sentence with the match
elif flag == "+": # a word is a name, so put it into memory
if data["sex"] == "male":
last_he = [data, word_index]
elif data["sex"] == "female":
last_she = [data, word_index]
elif data['sex'] == "?":
last_unknown = [data, word_index]
return refs
def find(self, people, sentences, tagged_sentences):
# create a all possible lowercase names & drink beer later :P
names = utils.get_names_dict(people)
# find names in text and mark them with special symbols & append additional data
new_tagged_sentences = []
for index, sentence in enumerate(tagged_sentences):
sent = []
for word, tag in sentence:
key = word.lower()
if key in names:
sent.append(
(word.lower(), tag, '+',
names[key])) # add `+` to a name & include data
else:
sent.append((word.lower(), tag, 'o',
None)) # not a name - mark as `o`
new_tagged_sentences.append(sent)
# store references as lists: [PRP, fullname, sentence_index]
refs = []
# store last he & she while scanning sentences,
# if unknown sex name is found - store it also (determine type on first PRP found)
last_he = [None, 0] # store as: [people_data, word_index_in_text]
last_she = [None, 0]
last_unknown = [None, 0]
word_index = 0
for index, sentence in enumerate(new_tagged_sentences):
for element in sentence:
word, tag, flag, data = element # unpack all data
word_index += 1 # increase processed words index
if tag.startswith("PRP") and len(word) <= 5 and (word not in (
"it", "our", "their", "us", "its", "we",
"they")): # a determined reference was found!
### unknown sex resolver
if last_unknown[
0]: # if we have an unknown name without sex, then assign the next first found sex to it
gender = self.get_gender(word)
print "Last unknown person -", last_unknown[0][
'fullname'], "- was assigned sex:", gender
last_unknown[0]['sex'] = gender
# the hack has been fixed :P
if gender == "male":
if last_he[0]: # last `he` exists
if last_he[1] < last_unknown[
1]: # override if unknown is newer
last_he = last_unknown
else:
last_he = last_unknown # override as no `he` exists
elif gender == "female":
if last_she[0]:
if last_she[1] < last_unknown[1]:
last_she = last_unknown
else:
last_she = last_unknown
if gender in (
"male",
"female"): # clear only if actualy determined
last_unknown = [None, 0] # clear
#### determine the person mentioned
#print "*"*80
matched = None
if word in ("he", "his", "him") and last_he[0]: # male
matched = last_he
elif word in ("she", "her") and last_she[0]: # female
matched = last_she
elif word in ("i", "me",
"our"): # cannot determine sex - as multi
if last_he[0] and last_she[
0]: # we have both sex types in memory, choose the last one mentioned
if last_he[1] > last_she[1]: # he is more fresh
matched = last_he
else: # she is more fresh
matched = last_she
elif last_he[0]: # we have only `he` in memory
matched = last_he
elif last_she[0]: # we have only `she` in memory
matched = last_she
if matched: # refresh index - this person has been just mentioned
matched[1] = word_index
#print "REF[", word, "] is -", matched[0]['fullname'], "- in sentence Nr.", index
refs.append([word, matched[0]['fullname'], index])
else:
#print "REF[", word, "] is", "UNKNOWN", "in sentence Nr.", index
refs.append([word, "?", index])
#print "\t", sentences[index] # show the corresponding sentence with the match
elif flag == "+": # a word is a name, so put it into memory
if data["sex"] == "male":
last_he = [data, word_index]
elif data["sex"] == "female":
last_she = [data, word_index]
elif data['sex'] == "?":
last_unknown = [data, word_index]
return refs
def find(self, refs, tagged_sentences):
ref_dict = {} # reference map by sentence index
for prp, fullname, index in refs:
if index not in ref_dict:
ref_dict[index] = [prp, fullname, index]
else:
ref_dict[index].append([prp, fullname, index])
names = utils.get_names_dict(utils.people)
# TODO:
# find PRP/name, VRB, PRP/name for - 1
# memory for people: name/name/name/... (they did) - 2
interact = []
for index, sentence in enumerate(tagged_sentences):
chunked_sentence = regexp.CustomChunker().parse(sentence)
retaged_sentence = utils.retag_chunked(chunked_sentence)
new_tagged_sentence = utils.mark_sentence_names(
retaged_sentence, names)
# find prepositions, replace with real names and print what they did
who, what, prp, seq = [], [], [], []
prp_counter = 0
for (word, tag, piece, pt) in new_tagged_sentence:
reset = True
w = word.lower()
if tag.startswith("PRP"): # this is a reference
if (w in ("he", "she", "his", "him", "her", "i", "me",
"our")):
if index in ref_dict:
who.append(ref_dict[index]
[1]) # PRP-person mapping exists
prp.append(word)
else:
who.append(
None) # PRP exists without mapped person
prp.append(word)
elif w in names:
# this word belongs to a person name, there's no PRP for it
who.append(word)
prp.append(None)
elif piece in ('TARINYS'
): #TODO: add some details to extracted actions
reset = False
seq.append(word)
if reset and len(
seq) > 0: # join neighbouring verbs if possible
what.append(" ".join(seq))
seq = []
if len(who) > 1 and len(
what
) > 0: # only show people & their interactions that include an action
# capitalize each person name/surname first letter
for i, boo in enumerate(who):
if boo:
who[i] = " ".join([
part[0].upper() + part[1:]
for part in boo.split(" ")
])
interact.append({'who': who, 'prp': prp, 'what': what})
return interact
