def _getEmoticonsStats(messages):
numEmoticons = 0
if len(messages) == 0:
return numEmoticons
# emoticons = mio.getSetFromFile(mio.getResourcesPath() + "\emoticonList.txt")
for m in messages:
mEmoticons = statsUtil.getEmoticonsFromText(m.text)
numEmoticons += len(mEmoticons)
return numEmoticons
def _getEmoticonsStats(messages):
numEmoticons = 0
if len(messages) == 0:
return numEmoticons
#emoticons = mio.getSetFromFile(mio.getResourcesPath() + "\emoticonList.txt")
for m in messages:
mEmoticons = statsUtil.getEmoticonsFromText(m.text)
numEmoticons += len(mEmoticons)
return numEmoticons
def _generateEmoticonsStatsBy(self, groupByColumns=[]):
res = self.df.rename(columns={'text':'text'})
#grouped = res.groupby(['sender'] + groupByColumns, as_index=False)
res = res.groupby(['sender'] + groupByColumns, as_index=False).agg({'text' : lambda x: " ".join(x)})
res['lenMsgs'] = res['text'].apply(lambda x: len(x))
res['numEmoticons'] = res['text'].apply(lambda x: len(statsUtil.getEmoticonsFromText(x)))
res.drop('text', axis=1, inplace=True)
if groupByColumns:
tot = res.groupby(groupByColumns, as_index=False).sum()
tot['sender'] = "total"
res = pd.concat([res, tot])
res['emoticonsRatio'] = res['numEmoticons']/res['lenMsgs']
return res[['numEmoticons', 'emoticonsRatio', 'lenMsgs']]
else:
res.set_index(['sender'], inplace=True)
res.loc['total'] = res.sum()
res['emoticonsRatio'] = res['numEmoticons']/res['lenMsgs']
return res[['numEmoticons', 'emoticonsRatio', 'lenMsgs']]