diff --git a/Dockerfile b/Dockerfile index 34be7a1..80acec7 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1 +1 @@ -from gsiupm/senpy:0.11.4-python2.7 \ No newline at end of file +from gsiupm/senpy:0.20-python3.6 diff --git a/Makefile b/Makefile index 35f0223..2a5c798 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,4 @@ -PYVERSION=2.7 +PYVERSION=3.7 NAME=senpycommunity REPO=gsiupm PLUGINS= $(filter %/, $(wildcard */)) @@ -19,7 +19,7 @@ test-fast: test-fast-/ test: docker-build test-fast -dev: +dev: docker-build docker run -p $(DEV_PORT):5000 $(DOCKER_FLAGS) -ti $(DOCKER_FLAGS) -v $$PWD/$*:/senpy-plugins/ --entrypoint /bin/bash -v $$PWD/data:/data/ --rm $(IMAGEWTAG) .PHONY:: test test-fast dev diff --git a/emotion-anew/emotion-anew.py b/emotion-anew/emotion-anew.py index 37421d5..c0fb9eb 100644 --- a/emotion-anew/emotion-anew.py +++ b/emotion-anew/emotion-anew.py @@ -19,11 +19,11 @@ from nltk.corpus import stopwords from pattern.en import parse as parse_en from pattern.es import parse as parse_es -from senpy.plugins import SentimentPlugin, SenpyPlugin +from senpy.plugins import EmotionPlugin, SenpyPlugin from senpy.models import Results, EmotionSet, Entry, Emotion -class ANEW(SentimentPlugin): +class ANEW(EmotionPlugin): description = "This plugin consists on an emotion classifier using ANEW lexicon dictionary to calculate VAD (valence-arousal-dominance) of the sentence and determinate which emotion is closer to this value. Each emotion has a centroid, calculated according to this article: http://www.aclweb.org/anthology/W10-0208. The plugin is going to look for the words in the sentence that appear in the ANEW dictionary and calculate the average VAD score for the sentence. Once this score is calculated, it is going to seek the emotion that is closest to this value." author = "@icorcuera" version = "0.5.1" @@ -31,6 +31,7 @@ class ANEW(SentimentPlugin): extra_params = { "language": { + "description": "language of the input", "aliases": ["language", "l"], "required": True, "options": ["es","en"], @@ -75,7 +76,7 @@ class ANEW(SentimentPlugin): "neutral": "http://gsi.dit.upm.es/ontologies/wnaffect/ns#neutral-emotion", "sadness": "http://gsi.dit.upm.es/ontologies/wnaffect/ns#sadness" } - onyx__usesEmotionModel = "emoml:big6" + onyx__usesEmotionModel = "emoml:pad" nltk_resources = ['stopwords'] def activate(self, *args, **kwargs): @@ -119,14 +120,13 @@ class ANEW(SentimentPlugin): return s def _extract_ngrams(self, text, lang): - unigrams_lemmas = [] unigrams_words = [] pos_tagged = [] if lang == 'es': - sentences = parse_es(text,lemmata=True).split() + sentences = list(parse_es(text, lemmata=True).split()) else: - sentences = parse_en(text,lemmata=True).split() + sentences = list(parse_en(text, lemmata=True).split()) for sentence in sentences: for token in sentence: @@ -140,19 +140,6 @@ class ANEW(SentimentPlugin): def _find_ngrams(self, input_list, n): return zip(*[input_list[i:] for i in range(n)]) - def _emotion_calculate(self, VAD): - emotion='' - value=10000000000000000000000.0 - for state in self.centroids: - valence=VAD[0]-self.centroids[state]['V'] - arousal=VAD[1]-self.centroids[state]['A'] - dominance=VAD[2]-self.centroids[state]['D'] - new_value=math.sqrt((valence*valence)+(arousal*arousal)+(dominance*dominance)) - if new_value < value: - value=new_value - emotion=state - return emotion - def _extract_features(self, tweet,dictionary,lang): feature_set={} ngrams_lemmas,ngrams_words,pos_tagged = self._extract_ngrams(tweet,lang) @@ -176,14 +163,13 @@ class ANEW(SentimentPlugin): emotion='neutral' else: totalVAD=[totalVAD[0]/matches,totalVAD[1]/matches,totalVAD[2]/matches] - emotion=self._emotion_calculate(totalVAD) - feature_set['emotion']=emotion - feature_set['V']=totalVAD[0] - feature_set['A']=totalVAD[1] - feature_set['D']=totalVAD[2] + feature_set['V'] = totalVAD[0] + feature_set['A'] = totalVAD[1] + feature_set['D'] = totalVAD[2] return feature_set - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params text_input = entry.text @@ -196,13 +182,12 @@ class ANEW(SentimentPlugin): emotions.id = "Emotions0" emotion1 = Emotion(id="Emotion0") - emotion1["onyx:hasEmotionCategory"] = self.emotions_ontology[feature_set['emotion']] emotion1["http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence"] = feature_set['V'] emotion1["http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal"] = feature_set['A'] emotion1["http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance"] = feature_set['D'] - emotion1.prov(self) - emotions.prov(self) + emotion1.prov(activity) + emotions.prov(activity) emotions.onyx__hasEmotion.append(emotion1) entry.emotions = [emotions, ] @@ -212,47 +197,64 @@ class ANEW(SentimentPlugin): ontology = "http://gsi.dit.upm.es/ontologies/wnaffect/ns#" test_cases = [ { + 'name': 'anger with VAD=(2.12, 6.95, 5.05)', 'input': 'I hate you', 'expected': { - 'emotions': [{ + 'onyx:hasEmotionSet': [{ 'onyx:hasEmotion': [{ - 'onyx:hasEmotionCategory': ontology + 'anger', + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 6.95, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 5.05, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 2.12, }] }] } }, { 'input': 'i am sad', 'expected': { - 'emotions': [{ + 'onyx:hasEmotionSet': [{ 'onyx:hasEmotion': [{ - 'onyx:hasEmotionCategory': ontology + 'sadness', + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 4.13, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 3.45, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 1.61, + }] }] } }, { + 'name': 'joy', 'input': 'i am happy with my marks', 'expected': { - 'emotions': [{ + 'onyx:hasEmotionSet': [{ 'onyx:hasEmotion': [{ - 'onyx:hasEmotionCategory': ontology + 'joy', + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 6.49, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 6.63, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 8.21, }] }] } }, { + 'name': 'negative-feat', 'input': 'This movie is scary', 'expected': { - 'emotions': [{ + 'onyx:hasEmotionSet': [{ 'onyx:hasEmotion': [{ - 'onyx:hasEmotionCategory': ontology + 'negative-fear', + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 5.8100000000000005, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 4.33, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 5.050000000000001, + }] }] } }, { + 'name': 'negative-fear', 'input': 'this cake is disgusting' , 'expected': { - 'emotions': [{ + 'onyx:hasEmotionSet': [{ 'onyx:hasEmotion': [{ - 'onyx:hasEmotionCategory': ontology + 'negative-fear', + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 5.09, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 4.4, + "http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 5.109999999999999, + }] }] } diff --git a/emotion-anew/emotion-anew.senpy b/emotion-anew/emotion-anew.senpy index 3bfde1b..4718fc6 100644 --- a/emotion-anew/emotion-anew.senpy +++ b/emotion-anew/emotion-anew.senpy @@ -8,5 +8,4 @@ requirements: - scikit-learn - textblob - pattern -- lxml -onyx:usesEmotionModel: "emoml:big6" +- lxml \ No newline at end of file diff --git a/emotion-depechemood/depechemood_plugin.py b/emotion-depechemood/depechemood_plugin.py index 39367e8..d80e748 100644 --- a/emotion-depechemood/depechemood_plugin.py +++ b/emotion-depechemood/depechemood_plugin.py @@ -1,49 +1,56 @@ #!/usr/local/bin/python # coding: utf-8 +from future import standard_library +standard_library.install_aliases() + import os import re import sys import string import numpy as np -import pandas as pd from six.moves import urllib from nltk.corpus import stopwords -from senpy import EmotionPlugin, TextBox, models +from senpy import EmotionBox, models def ignore(dchars): deletechars = "".join(dchars) - if sys.version_info[0] >= 3: - tbl = str.maketrans("", "", deletechars) - ignore = lambda s: s.translate(tbl) - else: - def ignore(s): - return string.translate(s, None, deletechars) + tbl = str.maketrans("", "", deletechars) + ignore = lambda s: s.translate(tbl) return ignore -class DepecheMood(TextBox, EmotionPlugin): - '''Plugin that uses the DepecheMood++ emotion lexicon.''' +class DepecheMood(EmotionBox): + ''' + Plugin that uses the DepecheMood emotion lexicon. + + DepecheMood is an emotion lexicon automatically generated from news articles where users expressed their associated emotions. It contains two languages (English and Italian), as well as three types of word representations (token, lemma and lemma#PoS). For English, the lexicon contains 165k tokens, while the Italian version contains 116k. Unsupervised techniques can be applied to generate simple but effective baselines. To learn more, please visit https://github.com/marcoguerini/DepecheMood and http://www.depechemood.eu/ + ''' author = 'Oscar Araque' + name = 'emotion-depechemood' version = '0.1' + requirements = ['pandas'] + nltk_resources = ["stopwords"] + + onyx__usesEmotionModel = 'wna:WNAModel' + + EMOTIONS = ['wna:negative-fear', + 'wna:amusement', + 'wna:anger', + 'wna:annoyance', + 'wna:indifference', + 'wna:joy', + 'wna:awe', + 'wna:sadness'] + + DM_EMOTIONS = ['AFRAID', 'AMUSED', 'ANGRY', 'ANNOYED', 'DONT_CARE', 'HAPPY', 'INSPIRED', 'SAD',] def __init__(self, *args, **kwargs): super(DepecheMood, self).__init__(*args, **kwargs) self.LEXICON_URL = "https://github.com/marcoguerini/DepecheMood/raw/master/DepecheMood%2B%2B/DepecheMood_english_token_full.tsv" - self.EMOTIONS = ['AFRAID', 'AMUSED', 'ANGRY', 'ANNOYED', 'DONT_CARE', 'HAPPY', 'INSPIRED', 'SAD',] - self._mapping = { - 'AFRAID': 'wna:negative-fear', - 'AMUSED': 'wna:amusement', - 'ANGRY': 'wna:anger', - 'ANNOYED': 'wna:annoyance', - 'DONT_CARE': 'wna:indifference', - 'HAPPY': 'wna:joy', - 'INSPIRED': 'wna:awe', - 'SAD': 'wna:sadness', - } self._denoise = ignore(set(string.punctuation)|set('«»')) self._stop_words = [] self._lex_vocab = None @@ -89,19 +96,21 @@ class DepecheMood(TextBox, EmotionPlugin): return S def estimate_all_emotions(self, tokens): - S = {} + S = [] intersection = set(tokens) & self._lex_vocab - for emotion in self.EMOTIONS: + for emotion in self.DM_EMOTIONS: s = self.estimate_emotion(intersection, emotion) - emotion_mapped = self._mapping[emotion] - S[emotion_mapped] = s + S.append(s) return S def download_lex(self, file_path='DepecheMood_english_token_full.tsv', freq_threshold=10): + import pandas as pd + try: file_path = self.find_file(file_path) except IOError: + file_path = self.path(file_path) filename, _ = urllib.request.urlretrieve(self.LEXICON_URL, file_path) lexicon = pd.read_csv(file_path, sep='\t', index_col=0) @@ -110,18 +119,8 @@ class DepecheMood(TextBox, EmotionPlugin): lexicon = lexicon.T.to_dict() return lexicon - def output(self, output, entry, **kwargs): - s = models.EmotionSet() - s.prov__wasGeneratedBy = self.id - entry.emotions.append(s) - for label, value in output.items(): - e = models.Emotion(onyx__hasEmotionCategory=label, - onyx__hasEmotionIntensity=value) - s.onyx__hasEmotion.append(e) - return entry - - def predict_one(self, input, **kwargs): - tokens = self.preprocess(input) + def predict_one(self, features, **kwargs): + tokens = self.preprocess(features[0]) estimation = self.estimate_all_emotions(tokens) return estimation @@ -131,26 +130,41 @@ class DepecheMood(TextBox, EmotionPlugin): 'nif:isString': 'My cat is very happy', }, 'expected': { - 'emotions': [ + 'onyx:hasEmotionSet': [ { - '@type': 'emotionSet', 'onyx:hasEmotion': [ - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:negative-fear', - 'onyx:hasEmotionIntensity': 0.05278117640010922, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:amusement', - 'onyx:hasEmotionIntensity': 0.2114806151413433, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:anger', - 'onyx:hasEmotionIntensity': 0.05726119426520887, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:annoyance', - 'onyx:hasEmotionIntensity': 0.12295990731053638, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:indifference', - 'onyx:hasEmotionIntensity': 0.1860159893608025, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:joy', - 'onyx:hasEmotionIntensity': 0.12904050973724163, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:awe', - 'onyx:hasEmotionIntensity': 0.17973650399862967, }, - {'@type': 'emotion', 'onyx:hasEmotionCategory': 'wna:sadness', - 'onyx:hasEmotionIntensity': 0.060724103786128455, }, + { + 'onyx:hasEmotionCategory': 'wna:negative-fear', + 'onyx:hasEmotionIntensity': 0.05278117640010922 + }, + { + 'onyx:hasEmotionCategory': 'wna:amusement', + 'onyx:hasEmotionIntensity': 0.2114806151413433, + }, + { + 'onyx:hasEmotionCategory': 'wna:anger', + 'onyx:hasEmotionIntensity': 0.05726119426520887 + }, + { + 'onyx:hasEmotionCategory': 'wna:annoyance', + 'onyx:hasEmotionIntensity': 0.12295990731053638, + }, + { + 'onyx:hasEmotionCategory': 'wna:indifference', + 'onyx:hasEmotionIntensity': 0.1860159893608025, + }, + { + 'onyx:hasEmotionCategory': 'wna:joy', + 'onyx:hasEmotionIntensity': 0.12904050973724163, + }, + { + 'onyx:hasEmotionCategory': 'wna:awe', + 'onyx:hasEmotionIntensity': 0.17973650399862967, + }, + { + 'onyx:hasEmotionCategory': 'wna:sadness', + 'onyx:hasEmotionIntensity': 0.060724103786128455, + }, ] } ] @@ -164,4 +178,4 @@ if __name__ == '__main__': # sp, app = easy_load() # for plug in sp.analysis_plugins: # plug.test() - easy() + easy_test(debug=False) diff --git a/emotion-wnaffect/emotion-wnaffect.py b/emotion-wnaffect/emotion-wnaffect.py index bc7e57a..2e8840e 100644 --- a/emotion-wnaffect/emotion-wnaffect.py +++ b/emotion-wnaffect/emotion-wnaffect.py @@ -25,6 +25,7 @@ class WNAffect(EmotionPlugin, ShelfMixin): extra_params = { 'language': { "@id": 'lang_wnaffect', + 'description': 'language of the input', 'aliases': ['language', 'l'], 'required': True, 'options': ['en',] @@ -223,7 +224,8 @@ class WNAffect(EmotionPlugin, ShelfMixin): return feature_set - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params text_input = entry['nif:isString'] @@ -262,14 +264,14 @@ class WNAffect(EmotionPlugin, ShelfMixin): 'algorithm': 'emotion-wnaffect'} self.activate() - res = next(self.analyse_entry(Entry(nif__isString="This text make me sad"), params)) texts = {'I hate you': 'anger', 'i am sad': 'sadness', 'i am happy with my marks': 'joy', 'This movie is scary': 'negative-fear'} for text in texts: - response = next(self.analyse_entry(Entry(nif__isString=text), params)) + response = next(self.analyse_entry(Entry(nif__isString=text), + self.activity(params))) expected = texts[text] emotionSet = response.emotions[0] max_emotion = max(emotionSet['onyx:hasEmotion'], key=lambda x: x['onyx:hasEmotionIntensity']) diff --git a/example-plugin/example_plugin.py b/example-plugin/example_plugin.py index ba88d7a..635ea94 100644 --- a/example-plugin/example_plugin.py +++ b/example-plugin/example_plugin.py @@ -1,8 +1,8 @@ -from senpy.plugins import Analysis +from senpy.plugins import AnalysisPlugin from senpy.models import Response, Entry -class ExamplePlugin(Analysis): +class ExamplePlugin(AnalysisPlugin): '''A *VERY* simple plugin that exemplifies the development of Senpy Plugins''' name = "example-plugin" author = "@balkian" @@ -10,6 +10,7 @@ class ExamplePlugin(Analysis): extra_params = { "parameter": { "@id": "parameter", + "description": "this parameter does nothing, it is only an example", "aliases": ["parameter", "param"], "required": True, "default": 42 @@ -17,7 +18,8 @@ class ExamplePlugin(Analysis): } custom_attribute = "42" - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params self.log.debug('Analysing with the example.') self.log.debug('The answer to this response is: %s.' % params['parameter']) resp = Response() diff --git a/k8s/senpy-deployment.yaml b/k8s/senpy-deployment.yaml index 6f51ce6..672e43e 100644 --- a/k8s/senpy-deployment.yaml +++ b/k8s/senpy-deployment.yaml @@ -15,11 +15,9 @@ spec: - name: senpy-latest image: $IMAGEWTAG imagePullPolicy: Always - args: - - "--default-plugins" resources: limits: - memory: "512Mi" + memory: "2048Mi" cpu: "1000m" ports: - name: web diff --git a/sentiment-basic/sentiment-basic.py b/sentiment-basic/sentiment-basic.py index 214bd4b..60e2af2 100644 --- a/sentiment-basic/sentiment-basic.py +++ b/sentiment-basic/sentiment-basic.py @@ -12,14 +12,14 @@ from textblob import TextBlob from scipy.interpolate import interp1d from os import path -from senpy.plugins import SentimentPlugin, SenpyPlugin -from senpy.models import Results, Entry, Sentiment +from senpy.plugins import SentimentBox, SenpyPlugin +from senpy.models import Results, Entry, Sentiment, Error if sys.version_info[0] >= 3: unicode = str -class SentimentBasic(SentimentPlugin): +class SentimentBasic(SentimentBox): ''' Sentiment classifier using rule-based classification for Spanish. Based on english to spanish translation and SentiWordNet sentiment knowledge. This is a demo plugin that uses only some features from the TASS 2015 classifier. To use the entirely functional classifier you can use the service in: http://senpy.cluster.gsi.dit.upm.es. ''' @@ -28,10 +28,11 @@ class SentimentBasic(SentimentPlugin): version = "0.1.1" extra_params = { "language": { + "description": "language of the text", "aliases": ["language", "l"], "required": True, - "options": ["en","es", "it", "fr", "auto"], - "default": "auto" + "options": ["en","es", "it", "fr"], + "default": "en" } } sentiword_path = "SentiWordNet_3.0.txt" @@ -40,6 +41,8 @@ class SentimentBasic(SentimentPlugin): minPolarityValue = -1 nltk_resources = ['punkt','wordnet', 'omw'] + with_polarity = False + def _load_swn(self): self.swn_path = self.find_file(self.sentiword_path) swn = SentiWordNet(self.swn_path) @@ -59,128 +62,116 @@ class SentimentBasic(SentimentPlugin): return [t for t in tokens if t not in string.punctuation] def _tokenize(self, text): - data = {} - sentences = nltk.sent_tokenize(text) - for i, sentence in enumerate(sentences): - sentence_ = {} - words = nltk.word_tokenize(sentence) - sentence_['sentence'] = sentence - tokens_ = [w.lower() for w in words] - sentence_['tokens'] = self._remove_punctuation(tokens_) - data[i] = sentence_ - return data + sentence_ = {} + words = nltk.word_tokenize(text) + sentence_['sentence'] = text + tokens_ = [w.lower() for w in words] + sentence_['tokens'] = self._remove_punctuation(tokens_) + return sentence_ def _pos(self, tokens): - for i in tokens: - tokens[i]['tokens'] = self._pos_tagger.tag(tokens[i]['tokens']) + tokens['tokens'] = self._pos_tagger.tag(tokens['tokens']) return tokens - def _compare_synsets(self, synsets, tokens, i): + def _compare_synsets(self, synsets, tokens): for synset in synsets: - for word in tokens[i]['lemmas']: - for lemma in tokens[i]['lemmas'][word]: + for word, lemmas in tokens['lemmas'].items(): + for lemma in lemmas: synset_ = lemma.synset() if synset == synset_: return synset return None - - def analyse_entry(self, entry, params): - language = params.get("language") - text = entry.text + def predict_one(self, features, activity): + language = activity.param("language") + text = features[0] tokens = self._tokenize(text) tokens = self._pos(tokens) sufixes = {'es':'spa','en':'eng','it':'ita','fr':'fra'} - for i in tokens: - tokens[i]['lemmas'] = {} - for w in tokens[i]['tokens']: - lemmas = wn.lemmas(w[0], lang=sufixes[language]) - if len(lemmas) == 0: - continue - tokens[i]['lemmas'][w[0]] = lemmas + tokens['lemmas'] = {} + for w in tokens['tokens']: + lemmas = wn.lemmas(w[0], lang=sufixes[language]) + if len(lemmas) == 0: + continue + tokens['lemmas'][w[0]] = lemmas if language == "en": trans = TextBlob(unicode(text)) else: - trans = TextBlob(unicode(text)).translate(from_lang=language,to='en') + try: + trans = TextBlob(unicode(text)).translate(from_lang=language,to='en') + except Exception as ex: + raise Error('Could not translate the text from "{}" to "{}": {}'.format(language, + 'en', + str(ex))) useful_synsets = {} - for s_i, t_s in enumerate(trans.sentences): - useful_synsets[s_i] = {} - for w_i, t_w in enumerate(trans.sentences[s_i].words): - synsets = wn.synsets(trans.sentences[s_i].words[w_i]) - if len(synsets) == 0: - continue - eq_synset = self._compare_synsets(synsets, tokens, s_i) - useful_synsets[s_i][t_w] = eq_synset + for w_i, t_w in enumerate(trans.sentences[0].words): + synsets = wn.synsets(trans.sentences[0].words[w_i]) + if len(synsets) == 0: + continue + eq_synset = self._compare_synsets(synsets, tokens) + useful_synsets[t_w] = eq_synset + scores = {} scores = {} - for i in tokens: - scores[i] = {} - if useful_synsets != None: - for word in useful_synsets[i]: - if useful_synsets[i][word] is None: - continue - temp_scores = self._swn.get_score(useful_synsets[i][word].name().split('.')[0].replace(' ',' ')) - for score in temp_scores: - if score['synset'] == useful_synsets[i][word]: - t_score = score['pos'] - score['neg'] - f_score = 'neu' - if t_score > 0: - f_score = 'pos' - elif t_score < 0: - f_score = 'neg' - score['score'] = f_score - scores[i][word] = score - break - p = params.get("prefix", None) + if useful_synsets != None: + for word in useful_synsets: + if useful_synsets[word] is None: + continue + temp_scores = self._swn.get_score(useful_synsets[word].name().split('.')[0].replace(' ',' ')) + for score in temp_scores: + if score['synset'] == useful_synsets[word]: + t_score = score['pos'] - score['neg'] + f_score = 'neu' + if t_score > 0: + f_score = 'pos' + elif t_score < 0: + f_score = 'neg' + score['score'] = f_score + scores[word] = score + break + g_score = 0.5 + for i in scores: n_pos = 0.0 n_neg = 0.0 - for w in scores[i]: - if scores[i][w]['score'] == 'pos': + for w in scores: + if scores[w]['score'] == 'pos': n_pos += 1.0 - elif scores[i][w]['score'] == 'neg': + elif scores[w]['score'] == 'neg': n_neg += 1.0 inter = interp1d([-1.0, 1.0], [0.0, 1.0]) + try: g_score = (n_pos - n_neg) / (n_pos + n_neg) g_score = float(inter(g_score)) except: if n_pos == 0 and n_neg == 0: g_score = 0.5 - if g_score >= 0.5: - polarity = 'marl:Positive' - polarity_value = 1 - elif g_score < 0.5: - polarity = 'marl:Negative' - polarity_value = -1 - else: - polarity = 'marl:Neutral' - polarity_value = 0 - opinion = Sentiment(id="Opinion0"+'_'+str(i), - marl__hasPolarity=polarity, - marl__polarityValue=polarity_value) - - opinion.prov(self) - entry.sentiments.append(opinion) - - yield entry + + if g_score > 0.5: # Positive + return [1, 0, 0] + elif g_score < 0.5: # Negative + return [0, 0, 1] + else: + return [0, 1, 0] + test_cases = [ { - 'input': u'Odio ir al cine', + 'input': 'Odio ir al cine', 'params': {'language': 'es'}, 'polarity': 'marl:Negative' }, { - 'input': u'El cielo está nublado', + 'input': 'El cielo está nublado', 'params': {'language': 'es'}, - 'polarity': 'marl:Positive' + 'polarity': 'marl:Neutral' }, { - 'input': u'Esta tarta está muy buena', + 'input': 'Esta tarta está muy buena', 'params': {'language': 'es'}, - 'polarity': 'marl:Negative' + 'polarity': 'marl:Negative' # SURPRISINGLY! } ] diff --git a/sentiment-meaningCloud/meaningcloud_plugin.py b/sentiment-meaningCloud/meaningcloud_plugin.py index d06fc94..d3b6213 100644 --- a/sentiment-meaningCloud/meaningcloud_plugin.py +++ b/sentiment-meaningCloud/meaningcloud_plugin.py @@ -21,7 +21,7 @@ class MeaningCloudPlugin(SentimentPlugin): When you had obtained the meaningCloud API Key, you have to provide it to the plugin, using param apiKey. Example request: - http://senpy.cluster.gsi.dit.upm.es/api/?algo=meaningCloud&language=en&apiKey=&input=I%20love%20Madrid. + http://senpy.cluster.gsi.dit.upm.es/api/?algo=meaningCloud&language=en&apiKey=YOUR_API_KEY&input=I%20love%20Madrid. ''' name = 'sentiment-meaningcloud' author = 'GSI UPM' @@ -31,12 +31,14 @@ class MeaningCloudPlugin(SentimentPlugin): extra_params = { "language": { + "description": "language of the input", "aliases": ["language", "l"], "required": True, "options": ["en","es","ca","it","pt","fr","auto"], "default": "auto" }, "apikey":{ + "description": "API key for the meaningcloud service. See https://www.meaningcloud.com/developer/login", "aliases": ["apiKey", "meaningcloud-key", "meaningcloud-apikey"], "required": True } @@ -55,7 +57,8 @@ class MeaningCloudPlugin(SentimentPlugin): polarityValue = 1 return polarity, polarityValue - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params txt = entry['nif:isString'] api = 'http://api.meaningcloud.com/' @@ -129,7 +132,9 @@ class MeaningCloudPlugin(SentimentPlugin): sementity = sent_entity['sementity'].get('type', None).split(">")[-1] entity['@type'] = "ODENTITY_{}".format(sementity) entity.prov(self) - entry.entities.append(entity) + if 'senpy:hasEntity' not in entry: + entry['senpy:hasEntity'] = [] + entry['senpy:hasEntity'].append(entity) for topic in api_response_topics['concept_list']: if 'semtheme_list' in topic: @@ -139,7 +144,9 @@ class MeaningCloudPlugin(SentimentPlugin): concept['@type'] = "ODTHEME_{}".format(theme['type'].split(">")[-1]) concept['fam:topic-reference'] = "http://dbpedia.org/resource/{}".format(theme['type'].split('>')[-1]) entry.prov(self) - entry.topics.append(concept) + if 'senpy:hasTopic' not in entry: + entry['senpy:hasTopic'] = [] + entry['senpy:hasTopic'].append(concept) yield entry test_cases = [ @@ -160,11 +167,11 @@ class MeaningCloudPlugin(SentimentPlugin): }, 'input': 'Hello World Obama', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Neutral'}], - 'entities': [ + 'senpy:hasEntity': [ {'itsrdf:taIdentRef': 'http://dbpedia.org/resource/Obama'}], - 'topics': [ + 'senpy:hasTopic': [ {'fam:topic-reference': 'http://dbpedia.org/resource/Astronomy'}] }, 'responses': [ diff --git a/sentiment-taiger/taiger3c_plugin.py b/sentiment-taiger/taiger3c_plugin.py index 1278be5..8f0d2cd 100644 --- a/sentiment-taiger/taiger3c_plugin.py +++ b/sentiment-taiger/taiger3c_plugin.py @@ -43,7 +43,8 @@ class TaigerPlugin3cats(SentimentPlugin): raise ValueError('unknown polarity: {}'.format(value)) return polarity, value - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params txt = entry['nif:isString'] api = TAIGER_ENDPOINT @@ -89,7 +90,7 @@ class TaigerPlugin3cats(SentimentPlugin): }, 'input': 'I hate to say this', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Negative'}], }, 'responses': [ @@ -116,7 +117,7 @@ class TaigerPlugin3cats(SentimentPlugin): }, 'input': 'This is amazing', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Positive'}], }, 'responses': [ @@ -143,7 +144,7 @@ class TaigerPlugin3cats(SentimentPlugin): }, 'input': 'The pillow is in the wardrobe', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Neutral'}], }, 'responses': [ diff --git a/sentiment-taiger/taiger_plugin.py b/sentiment-taiger/taiger_plugin.py index 7395d5a..d3168e8 100644 --- a/sentiment-taiger/taiger_plugin.py +++ b/sentiment-taiger/taiger_plugin.py @@ -38,7 +38,8 @@ class TaigerPlugin(SentimentPlugin): polarity = 'marl:Positive' return polarity - def analyse_entry(self, entry, params): + def analyse_entry(self, entry, activity): + params = activity.params txt = entry['nif:isString'] api = TAIGER_ENDPOINT @@ -77,7 +78,6 @@ class TaigerPlugin(SentimentPlugin): 'expanded-jsonld': 0, 'informat': 'text', 'prefix': '', - 'plugin_type': 'analysisPlugin', 'urischeme': 'RFC5147String', 'outformat': 'json-ld', 'conversion': 'full', @@ -87,7 +87,7 @@ class TaigerPlugin(SentimentPlugin): }, 'input': 'I hate to say this', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Negative'}], }, 'responses': [ @@ -109,7 +109,6 @@ class TaigerPlugin(SentimentPlugin): 'expanded-jsonld': 0, 'informat': 'text', 'prefix': '', - 'plugin_type': 'analysisPlugin', 'urischeme': 'RFC5147String', 'outformat': 'json-ld', 'conversion': 'full', @@ -119,7 +118,7 @@ class TaigerPlugin(SentimentPlugin): }, 'input': 'This is amazing', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Positive'}], }, 'responses': [ @@ -141,7 +140,6 @@ class TaigerPlugin(SentimentPlugin): 'expanded-jsonld': 0, 'informat': 'text', 'prefix': '', - 'plugin_type': 'analysisPlugin', 'urischeme': 'RFC5147String', 'outformat': 'json-ld', 'conversion': 'full', @@ -151,7 +149,7 @@ class TaigerPlugin(SentimentPlugin): }, 'input': 'The pillow is in the wardrobe', 'expected': { - 'sentiments': [ + 'marl:hasOpinion': [ {'marl:hasPolarity': 'marl:Neutral'}], }, 'responses': [ diff --git a/sentiment-vader/vader_plugin.py b/sentiment-vader/vader_plugin.py index ec66017..3b06f0c 100644 --- a/sentiment-vader/vader_plugin.py +++ b/sentiment-vader/vader_plugin.py @@ -1,12 +1,12 @@ # -*- coding: utf-8 -*- from vaderSentiment import sentiment -from senpy.plugins import SentimentPlugin, SenpyPlugin +from senpy.plugins import SentimentBox, SenpyPlugin from senpy.models import Results, Sentiment, Entry import logging -class VaderSentimentPlugin(SentimentPlugin): +class VaderSentimentPlugin(SentimentBox): ''' Sentiment classifier using vaderSentiment module. Params accepted: Language: {en, es}. The output uses Marl ontology developed at GSI UPM for semantic web. ''' @@ -16,6 +16,7 @@ class VaderSentimentPlugin(SentimentPlugin): version = "0.1.1" extra_params = { "language": { + "description": "language of the input", "@id": "lang_rand", "aliases": ["language", "l"], "default": "auto", @@ -23,55 +24,32 @@ class VaderSentimentPlugin(SentimentPlugin): }, "aggregate": { + "description": "Show only the strongest sentiment (aggregate) or all sentiments", "aliases": ["aggregate","agg"], - "options": ["true", "false"], + "options": [True, False], "default": False } } requirements = {} - def analyse_entry(self, entry, params): + _VADER_KEYS = ['pos', 'neu', 'neg'] + binary = False - self.log.debug("Analysing with params {}".format(params)) - text_input = entry.text - aggregate = params['aggregate'] + def predict_one(self, features, activity): + text_input = ' '.join(features) + scores = sentiment(text_input) - score = sentiment(text_input) + sentiments = [] + for k in self._VADER_KEYS: + sentiments.append(scores[k]) - opinion0 = Sentiment(id= "Opinion_positive", - marl__hasPolarity= "marl:Positive", - marl__algorithmConfidence= score['pos'] - ) - opinion0.prov(self) - opinion1 = Sentiment(id= "Opinion_negative", - marl__hasPolarity= "marl:Negative", - marl__algorithmConfidence= score['neg'] - ) - opinion1.prov(self) - opinion2 = Sentiment(id= "Opinion_neutral", - marl__hasPolarity = "marl:Neutral", - marl__algorithmConfidence = score['neu'] - ) - opinion2.prov(self) + if activity.param('aggregate'): + m = max(sentiments) + sentiments = [k if k==m else None for k in sentiments] - if aggregate == 'true': - res = None - confident = max(score['neg'],score['neu'],score['pos']) - if opinion0.marl__algorithmConfidence == confident: - res = opinion0 - elif opinion1.marl__algorithmConfidence == confident: - res = opinion1 - elif opinion2.marl__algorithmConfidence == confident: - res = opinion2 - entry.sentiments.append(res) - else: - entry.sentiments.append(opinion0) - entry.sentiments.append(opinion1) - entry.sentiments.append(opinion2) - - yield entry + return sentiments test_cases = []