def filtered_tokens(self):
# using lemmatized words
from msgvis.apps.base.utils import get_stoplist
tokens = map(lambda x: x.tweet_word.text, self.tweetword_connections.all())
stop_words = set(get_stoplist()+['ive', 'wasnt', 'didnt', 'dont'])
tokens = filter(lambda x: x not in stop_words, tokens)
tokens = filter(lambda x: (len(x) > 2) and not (x.startswith('http') and len(x) > 4), tokens)
return tokens
def filtered_tokens(self):
# using lemmatized words
from msgvis.apps.base.utils import get_stoplist
tokens = map(lambda x: x.tweet_word.text,
self.tweetword_connections.all())
stop_words = set(get_stoplist() + ['ive', 'wasnt', 'didnt', 'dont'])
tokens = filter(lambda x: x not in stop_words, tokens)
tokens = filter(
lambda x:
(len(x) > 2) and not (x.startswith('http') and len(x) > 4), tokens)
return tokens
def default_feature_context(name, dataset_id):
dataset = Dataset.objects.get(pk=dataset_id)
queryset = dataset.message_set.all()#filter(language__code='en')
filters = [
set(get_stoplist()),
['ive', 'wasnt', 'didnt', 'dont'],
LambdaWordFilter(lambda word: word == 'rt' or len(word) <= 2),
LambdaWordFilter(lambda word: word.startswith('http') and len(word) > 4)
]
return FeatureContext(name=name, queryset=queryset,
tokenizer=TweetParserTokenizer,
lemmatizer=None,#WordNetLemmatizer(),
filters=filters,
minimum_frequency=4)
def default_feature_context(name, dataset_id):
dataset = Dataset.objects.get(pk=dataset_id)
queryset = dataset.message_set.all() #filter(language__code='en')
filters = [
set(get_stoplist()), ['ive', 'wasnt', 'didnt', 'dont'],
LambdaWordFilter(lambda word: word == 'rt' or len(word) <= 2),
LambdaWordFilter(
lambda word: word.startswith('http') and len(word) > 4)
]
return FeatureContext(
name=name,
queryset=queryset,
tokenizer=TweetParserTokenizer,
lemmatizer=None, #WordNetLemmatizer(),
filters=filters,
minimum_frequency=4)
