def removeNegationsPipeline(sentence: str, contractions: dict):
'''takes in a sentence and returns a pos_tagged list of the words with
contractions removed
Parameters
----------
sentence:str
sentence we wish to remove the negations out of
contractions: dict
dictionary that maps contractions to their expansions
Returns
-------
list:
list of wordnet part_of_speech tokens each of which are in the form
(word, part of speech, version)
'''
tokens = tp.tokenize_words(sentence)
tokens = expandContractions(tokens, contractions)
pos_tokens = tp.simple_pos_tag(tokens)
pos_tokens = tp.remove_pos_stopwords(pos_tokens)
return removeNegations(pos_tokens)
def swn_pipeline(s: str, label_diff_thresh=0, contractions=None, emoti_dict=None, special={}, count_nouns=True):
"""pipline that takes in a sentence string and returns the appropriate label:
Parameters
----------
s: str
sentence to find the sentiment of
DEFAULTS:
label_diff_thresh:int = 0
how far we want the positive and negative score to differ to be considered
not neutral
contractions: dict
dictionary of contractions mapped to their expanded forms
emoti_dict: dict
dictionary of emoticons mapped to their label
special: dict
dictionary of specialized lexicon to score words on top of SentiWordNet
count_nouns=true: determines whether or not to include nouns in the scoring
Returns
-------
tuple(str, list)
tuple where first item is sentiment label of s (-1, 0, or 1)
and second item is a list of the words with their scores
"""
##preliminary pre processing (emoticons, phrases, etc)
s = extra_preprocessing(s, emoti_dict)
# if got a lable
if s == "0" or s == "1" or s == "-1":
return (s, [])
##text processing
if contractions is None: # if not want to remove contractions
tokens = tp.tokenize_words(s)
pos_tokens = tp.simple_pos_tag(tokens)
pos_tokens = tp.remove_pos_stopwords(pos_tokens)
else: # if want to remove negation contractions
pos_tokens = rneg.removeNegationsPipeline(s, contractions)
return swn_label(pos_tokens, diff_thresh=label_diff_thresh, special=special, count_nouns=count_nouns)