def numEmoji(self):
df = pd.DataFrame()
recs = [features.RawSent(r) for r in self.test]
df["numsymbols"] = features.numSymbols(recs, normalize=True)
df["numemoji"] = features.countEmoji(recs, normalize=True)
df.to_csv("symbol&emoji.csv", encoding="utf-8")
def fShallow(self):
normalize = True
recs = [features.RawSent(r) for r in self.test]
self._add_feature("avgwordlen", features.avgWordLen(recs))
self._add_feature("sentlen", features.sentLen(recs))
self._add_feature("numsymbols", features.numSymbols(recs, normalize))
self._add_feature("numcapltrs",
features.numCapLetters(recs, normalize))
self._add_feature("numnumbers", features.numNumbers(recs, normalize))
def fShallow(self):
normalize = True
recs = [r.rawsent for r in self.test]
self._add_feature("sentlen",features.sentLen(recs))
self._add_feature("numnumbers",features.numNumbers(recs, normalize))
self._add_feature("numcapltrs",features.numCapLetters(recs, normalize))
self._add_feature("numsymbols",features.numSymbols(recs, normalize))
self._add_feature("avgwordlen",features.avgWordLen(recs))
self._add_feature("numconns",features.numConnectives(recs))
self._add_feature("fracstopwords",features.fracStopwords(recs))
polarvals = features.mpqaGenInqInfo(recs)
keys = ["mpqageninq-subj","mpqageninq-polarity"]
for (key,vals) in zip(keys,polarvals):
self._add_feature(key,vals)
mrcvals = features.mrcInfo(recs)
keys = ["mrc-fami","mrc-img"]
for (key,vals) in zip(keys,mrcvals):
self._add_feature(key,vals)
idfvals = features.idf(recs)
keys = ["idf-min", "idf-max", "idf-avg"]
for (key,vals) in zip(keys,idfvals):
self._add_feature(key,vals)