def set_tokens(self):
if self.corpus is None:
self.tokens = None
return
self.tokens = WordPunctTokenizer()(self.corpus).tokens
self.n_tokens = sum(map(len, self.tokens))
self.n_types = len(set(chain.from_iterable(self.tokens)))
def set_tokens(self):
if self.corpus is None:
self.tokens = None
return
tokenizer = WordPunctTokenizer()
self.tokens = tokenizer(self.corpus.documents)
self.n_tokens = sum(map(len, self.tokens))
self.n_types = len(set(chain.from_iterable(self.tokens)))
def _compute_indices(self): # type: () -> Optional[None, list]
if self.corpus is None:
self.indices = None
return
if self.corpus and not self.corpus.has_tokens():
preprocessor = Preprocessor(tokenizer=WordPunctTokenizer())
preprocessor(self.corpus)
self.indices = [ConcordanceIndex(doc, key=lambda x: x.lower())
for doc in self.corpus.tokens]
def transform(self, corpus):
scores = []
corpus = WordPunctTokenizer()(corpus)
for doc in corpus.tokens:
pos_words = sum(word in self.positive for word in doc)
neg_words = sum(word in self.negative for word in doc)
scores.append([100 * (pos_words - neg_words) / max(len(doc), 1)])
X = np.array(scores).reshape((-1, len(self.sentiments)))
# set compute values
shared_cv = SharedTransform(self)
cv = [
VectorizationComputeValue(shared_cv, col)
for col in self.sentiments
]
corpus = corpus.extend_attributes(X,
self.sentiments,
compute_values=cv)
return corpus
from orangecontrib.text.preprocess import (FrequencyFilter,
LowercaseTransformer,
WordPunctTokenizer)
__all__ = ['Preprocessor', 'base_preprocessor']
# don't use anything that requires NLTK data to assure async download
BASE_TOKENIZER = WordPunctTokenizer()
BASE_TRANSFORMERS = [LowercaseTransformer()]
class Preprocessor:
"""Holds document processing objects.
Attributes:
transformers (List([BaseTransformer]): transforms strings
tokenizer (BaseTokenizer): tokenizes string
normalizer (BaseNormalizer): normalizes tokens
filters (List[BaseTokenFilter]): filters unneeded tokens
"""
def __init__(self,
transformers=None,
tokenizer=None,
normalizer=None,
filters=None,
ngrams_range=None,
pos_tagger=None):
if callable(transformers):
transformers = [transformers]