def load(self, path=None):
_Sentiment.load(self, path)
# Map "verschrikkelijk" to adverbial "verschrikkelijke" (+1%)
if not path:
for w, pos in list(dict.items(self)):
if "JJ" in pos:
p, s, i = pos["JJ"]
self.annotate(attributive(w), "JJ", p, s, i)
def load(self, path=None):
_Sentiment.load(self, path)
# Map "verschrikkelijk" to adverbial "verschrikkelijke" (+1%)
if not path:
for w, pos in list(dict.items(self)):
if "JJ" in pos:
p, s, i = pos["JJ"]
self.annotate(attributive(w), "JJ", p, s, i)
def modality(sentence, type=EPISTEMIC):
""" Returns the sentence's modality as a weight between -1.0 and +1.0.
Currently, the only type implemented is EPISTEMIC.
Epistemic modality is used to express possibility (i.e. how truthful is what is being said).
"""
if isinstance(sentence, str):
try:
# A Sentence is expected but a string given.
# Attempt to parse the string on-the-fly.
from pattern.en import parse, Sentence
sentence = Sentence(parse(sentence))
except ImportError:
pass
S, n, m = sentence, 0.0, 0
if not (hasattr(S, "words") and hasattr(S, "parse_token")):
raise TypeError("%s object is not a parsed Sentence" %
repr(S.__class__.__name__))
if type == EPISTEMIC:
r = S.string.rstrip(" .!")
for k, v in epistemic_weaseling.items():
for phrase in v:
if phrase in r:
n += k
m += 2
for i, w in enumerate(S.words):
for type, dict, weight in (("MD", epistemic_MD,
4), ("VB", epistemic_VB,
2), ("RB", epistemic_RB,
2), ("JJ", epistemic_JJ, 1),
("NN", epistemic_NN,
1), ("CC", epistemic_CC_DT_IN,
1), ("DT", epistemic_CC_DT_IN, 1),
("IN", epistemic_CC_DT_IN,
1), ("PRP", epistemic_PRP,
1), ("PRP$", epistemic_PRP, 1),
("WP", epistemic_PRP, 1)):
# "likely" => weight 1, "very likely" => weight 2
if i > 0 and s(S[i - 1]) in MODIFIERS:
weight += 1
# likely" => score 0.25 (neutral inclining towards positive).
if w.type and w.type.startswith(type):
for k, v in dict.items():
# Prefer lemmata.
if (w.lemma or s(w)) in v:
# Reverse score for negated terms.
if i > 0 and s(S[i - 1]) in ("not", "n't", "never",
"without"):
k = -k * 0.5
n += weight * k
m += weight
break
# Numbers, citations, explanations make the sentence more factual.
if w.type in ("CD", "\"", "'", ":", "("):
n += 0.75
m += 1
if m == 0:
return 1.0 # No modal verbs/adverbs used, so statement must be true.
return max(-1.0, min(n / (m or 1), +1.0))
def modality(sentence, type=EPISTEMIC):
""" Returns the sentence's modality as a weight between -1.0 and +1.0.
Currently, the only type implemented is EPISTEMIC.
Epistemic modality is used to express possibility (i.e. how truthful is what is being said).
"""
if isinstance(sentence, str):
try:
# A Sentence is expected but a string given.
# Attempt to parse the string on-the-fly.
from pattern.en import parse, Sentence
sentence = Sentence(parse(sentence))
except ImportError:
pass
S, n, m = sentence, 0.0, 0
if not (hasattr(S, "words") and hasattr(S, "parse_token")):
raise TypeError("%s object is not a parsed Sentence" % repr(S.__class__.__name__))
if type == EPISTEMIC:
r = S.string.rstrip(" .!")
for k, v in epistemic_weaseling.items():
for phrase in v:
if phrase in r:
n += k
m += 2
for i, w in enumerate(S.words):
for type, dict, weight in (
( "MD", epistemic_MD, 4),
( "VB", epistemic_VB, 2),
( "RB", epistemic_RB, 2),
( "JJ", epistemic_JJ, 1),
( "NN", epistemic_NN, 1),
( "CC", epistemic_CC_DT_IN, 1),
( "DT", epistemic_CC_DT_IN, 1),
( "IN", epistemic_CC_DT_IN, 1),
("PRP" , epistemic_PRP, 1),
("PRP$", epistemic_PRP, 1),
( "WP" , epistemic_PRP, 1)):
# "likely" => weight 1, "very likely" => weight 2
if i > 0 and s(S[i - 1]) in MODIFIERS:
weight += 1
# likely" => score 0.25 (neutral inclining towards positive).
if w.type and w.type.startswith(type):
for k, v in dict.items():
# Prefer lemmata.
if (w.lemma or s(w)) in v:
# Reverse score for negated terms.
if i > 0 and s(S[i - 1]) in ("not", "n't", "never", "without"):
k = -k * 0.5
n += weight * k
m += weight
break
# Numbers, citations, explanations make the sentence more factual.
if w.type in ("CD", "\"", "'", ":", "("):
n += 0.75
m += 1
if m == 0:
return 1.0 # No modal verbs/adverbs used, so statement must be true.
return max(-1.0, min(n / (m or 1), +1.0))
def load(self, path=None):
_Sentiment.load(self, path)
# Map "terrible" to adverb "terribly" (+1% accuracy)
if not path:
for w, pos in list(dict.items(self)):
if "JJ" in pos:
if w.endswith("y"):
w = w[:-1] + "i"
if w.endswith("le"):
w = w[:-2]
p, s, i = pos["JJ"]
self.annotate(w + "ly", "RB", p, s, i)
def load(self, path=None):
_Sentiment.load(self, path)
# Map "terrible" to adverb "terribly" (+1% accuracy)
if not path:
for w, pos in list(dict.items(self)):
if "JJ" in pos:
if w.endswith("y"):
w = w[:-1] + "i"
if w.endswith("le"):
w = w[:-2]
p, s, i = pos["JJ"]
self.annotate(w + "ly", "RB", p, s, i)
def load(self, path=None):
_Sentiment.load(self, path)
# Map "précaire" to "precaire" (without diacritics, +1% accuracy).
if not path:
for w, pos in list(dict.items(self)):
w0 = w
if not w.endswith((u"à", u"è", u"é", u"ê", u"ï")):
w = w.replace(u"à", "a")
w = w.replace(u"é", "e")
w = w.replace(u"è", "e")
w = w.replace(u"ê", "e")
w = w.replace(u"ï", "i")
if w != w0:
for pos, (p, s, i) in pos.items():
self.annotate(w, pos, p, s, i)
def load(self, path=None):
_Sentiment.load(self, path)
# Map "précaire" to "precaire" (without diacritics, +1% accuracy).
if not path:
for w, pos in list(dict.items(self)):
w0 = w
if not w.endswith(("à", "è", "é", "ê", "ï")):
w = w.replace("à", "a")
w = w.replace("é", "e")
w = w.replace("è", "e")
w = w.replace("ê", "e")
w = w.replace("ï", "i")
if w != w0:
for pos, (p, s, i) in pos.items():
self.annotate(w, pos, p, s, i)