def test_deepmoji_return_attention(): # test the output of the normal model model = deepmoji_emojis(maxlen=30, weight_path=PRETRAINED_PATH) # check correct number of outputs assert 1 == len(model.outputs) # check model outputs come from correct layers assert [['softmax', 0, 0]] == model.get_config()['output_layers'] # ensure that output shapes are correct (assume a 5-example batch of 30-timesteps) input_shape = (5, 30, 2304) assert (5, 2304) == model.layers[6].compute_output_shape(input_shape) # repeat above described tests when returning attention weights model = deepmoji_emojis(maxlen=30, weight_path=PRETRAINED_PATH, return_attention=True) assert 2 == len(model.outputs) assert [['softmax', 0, 0], ['attlayer', 0, 1]] == model.get_config()['output_layers'] assert [(5, 2304), (5, 30)] == model.layers[6].compute_output_shape(input_shape)
def main(): df = pd.read_csv('../data/interim/sentences.csv') maxlen = 30 batch_size = 32 print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) sentences = [] for sent in df.body.tolist(): sent = unicode(str(sent), "utf-8") if sent.strip() == "": sent = 'blank' sent = unicode(str(sent), "utf-8") sentences.append(sent) tokenized, _, _ = st.tokenize_sentences(sentences) # generate full deepmoji features for sentences print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_feature_encoding(maxlen, PRETRAINED_PATH) model.summary() print('Encoding texts with deepmoji features...') encoding = model.predict(tokenized) deepmoji_encodings = pd.DataFrame(encoding) deepmoji_encodings.index = df.post_id deepmoji_post_scores = deepmoji_encodings.groupby('post_id').agg( ['mean', 'max', 'min']) deepmoji_post_scores = flatten_cols(deepmoji_post_scores) deepmoji_post_scores = deepmoji_post_scores.add_prefix('deepmoji_') # generate 64 emoji encodings print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running emoji predictions...') prob = model.predict(tokenized) emoji_scores = pd.DataFrame(prob) emoji_scores = emoji_scores.add_prefix('emoji_') emoji_scores.index = df.post_id emoji_post_scores = emoji_scores.groupby('post_id').agg( ['mean', 'max', 'min']) emoji_post_scores = flatten_cols(emoji_post_scores) print('deepmoji features shape: {}'.format(deepmoji_post_scores.shape)) print('emoji features shape: {}'.format(emoji_post_scores.shape)) total_feats = deepmoji_post_scores.merge(emoji_post_scores, left_index=True, right_index=True) print('total features shape: {}'.format(total_feats.shape)) total_feats.to_csv('../data/interim/all_sent_level_deepmoji.csv')
def scoreTexts(TEST_SENTENCES): global vocabulary, model st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(TEST_SENTENCES) if model == None: model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() prob = model.predict(tokenized) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. scores = [] for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = {} t_score["text"] = t t_prob = prob[i] ind_top = top_elements(t_prob, 5) #t_score["prob"]=sum(t_prob[ind_top]) emoji_score = {} for ind in ind_top: emoji_score[ind] = t_prob[ind] t_score["score"] = emoji_score scores.append(t_score) return scores
def __init__(self): self.maxlen = 30 self.load_mappings() print('Loading model from {}.'.format(PRETRAINED_PATH)) self.model = deepmoji_emojis(self.maxlen, PRETRAINED_PATH) self.model.summary()
def model_deep(language): maxlen = 30 batch_size = 32 #list_new = [] #list_new.append(language) answer = [unicode(item) for item in language] print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(answer) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. print('Writing results to {}'.format(OUTPUT_PATH)) scores = [] for i, t in enumerate(answer): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, 5) t_score.append(sum(t_prob[ind_top])) t_score.extend(ind_top) t_score.extend([t_prob[ind] for ind in ind_top]) scores.append(t_score) print(t_score) with open(OUTPUT_PATH, 'wb') as csvfile: writer = csv.writer(csvfile, delimiter=',', lineterminator='\n') writer.writerow([ 'Text', 'Top5%', 'Emoji_1', 'Emoji_2', 'Emoji_3', 'Emoji_4', 'Emoji_5', 'Pct_1', 'Pct_2', 'Pct_3', 'Pct_4', 'Pct_5' ]) for i, row in enumerate(scores): try: writer.writerow(row) except Exception: print("Exception at row {}!".format(i)) print(scores) return ''.join(str(e) for e in scores)
def emoji_predict(sen_list, maxlen=30, step=32, model_path='../model/deepmoji_weights.hdf5', vocab_path='../model/vocabulary.json'): model = deepmoji_emojis(maxlen, model_path) model.summary() with open(vocab_path, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen, ignore_sentences_with_only_custom=True) records = [] for i in range(0, len(sen_list), step): if i + step >= len(sen_list): tokenized, _, _ = st.tokenize_sentences(sen_list[i:len(sen_list)]) content = sen_list[i:len(sen_list)] if len(tokenized) != len(content): print('Skip ' + str(i)) continue else: tokenized, _, _ = st.tokenize_sentences(sen_list[i:i + step]) content = sen_list[i:i + step] if len(tokenized) != len(content): print('Skip ' + str(i)) continue prob = model.predict(tokenized) for j in range(len(content)): r = {} r['text'] = [content[j]] t_prob = prob[j] ind_top = top_elements(t_prob, 5) r['confidence'] = (str(sum(t_prob[ind_top]))) r['top5emoji'] = [unicode(emoji_list[ind]) for ind in ind_top] r['top5prob'] = [str(t_prob[ind]) for ind in ind_top] r['prob'] = [str(num) for num in t_prob] records.append(r) if i % 1024 == 0: print('Processing: ' + str(i) + '/' + str(len(sen_list))) return records
def predict_emoji(training_data, maxlen): ''' predicts the emojis commonly associated with the sentences then adds it to the :param sentences: list of sentences to predict :param maxlen: max length of the setences given :return: ''' def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] sentences = training_data['sentence'] print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(sentences) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized, batch_size=500) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. # print('Writing results to {}'.format(OUTPUT_PATH)) # scores = [] # for i, t in enumerate(sentences): # t_tokens = tokenized[i] # t_score = [t] # t_prob = prob[i] # ind_top = top_elements(t_prob, 5) # t_score.append(sum(t_prob[ind_top])) # t_score.extend(ind_top) # t_score.extend([t_prob[ind] for ind in ind_top]) # scores.append(t_score) # print(t_score) return prob
def test_score_emoji(): """ Emoji predictions make sense. """ test_sentences = [ u'I love mom\'s cooking', u'I love how you never reply back..', u'I love cruising with my homies', u'I love messing with yo mind!!', u'I love you and now you\'re just gone..', u'This is shit', u'This is the shit' ] expected = [ np.array([36, 4, 8, 16, 47]), np.array([1, 19, 55, 25, 46]), np.array([31, 6, 30, 15, 13]), np.array([54, 44, 9, 50, 49]), np.array([46, 5, 27, 35, 34]), np.array([55, 32, 27, 1, 37]), np.array([48, 11, 6, 31, 9]) ] def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] # Initialize by loading dictionary and tokenize texts with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, 30) tokenized, _, _ = st.tokenize_sentences(test_sentences) # Load model and run model = deepmoji_emojis(maxlen=30, weight_path=PRETRAINED_PATH) prob = model.predict(tokenized) # Find top emojis for each sentence for i, t_prob in enumerate(prob): assert np.array_equal(top_elements(t_prob, 5), expected[i])
def emoticonit(sen): TEST_SENTENCES = [unicode(sen)] maxlen = 30 batch_size = 32 print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized = st.tokenize_sentences(TEST_SENTENCES) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. scores = [] selected = [] num = 1 for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, num) t_score.append(sum(t_prob[ind_top])) t_score.extend(ind_top) ind = ind_top.tolist() #list for i in range(num): print(emoticons[ind[i]]) selected.append(emoticons[ind[i]]) t_score.extend([t_prob[ind] for ind in ind_top]) scores.append(t_score) print(t_score) return (selected)
def predict_emoji(training_data, maxlen): ''' predicts the emojis commonly associated with the sentences then adds it to the :param sentences: list of sentences to predict :param maxlen: max length of the setences given :return: ''' sentences = training_data print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(sentences) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized, batch_size=100) return prob
most_n: int = 5, min_dist: float = None) -> List[str]: tokenized, _, _ = st.tokenize_sentences([sentence]) prob = deepmoji_model.predict(tokenized) for i, t_prob in enumerate(prob): if min_dist is not None: ids = list(i for i in top_elements(t_prob, most_n) if i in elements_past_min(t_prob, min_dist)) else: ids = list(top_elements(t_prob, most_n)) return list([EMOJI_MAP[emoji_index] for emoji_index in ids]) sentence_tokenizer = SentenceTokenizer(get_vocabulary(), 30) deepmoji_model = deepmoji_emojis( maxlen=30, weight_path=PRETRAINED_PATH, ) deepmoji_model.summary() def sentiment_query(word: str, most_n: int = 5, min_dist: float = None): return get_top_n_emojis(sentence_tokenizer, deepmoji_model, word, most_n=most_n, min_dist=min_dist) sentiment_query("I lost my dog oh no")
def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] maxlen = 30 batch_size = 32 print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(TEST_SENTENCES) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. print('Writing results to {}'.format(OUTPUT_PATH)) scores = [] for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, 5)
# model = torchmoji_feature_encoding(PRETRAINED_PATH, return_attention=True) # print(model) # # print('Encoding texts..') # encoding, att_weights = model(tokenized) # att_weights = att_weights.cpu().data.numpy() def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] print('Loading emoji pred model from {}.'.format(PRETRAINED_PATH), file=sys.stdout) model = deepmoji_emojis(maxlen, PRETRAINED_PATH, return_attention=True) model.summary() print('Running predictions.', file=sys.stdout) prob, att_weights = model.predict(tokenized) emojis = [] for prob in [prob]: # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the torchMoji repo. for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, 5) tmp = map(lambda x: EMOJIS[x], ind_top)
def __init__(self, maxlen): self.model = deepmoji_emojis(maxlen, PRETRAINED_PATH) self.maxlen = maxlen
def start(r, auth, keyword, max_items): api = tweepy.API(auth) para = "" happy_counter = 0 sad_counter = 0 fear_counter = 0 angry_counter = 0 love_counter = 0 happy_buffer = [] sad_buffer = [] fear_buffer = [] angry_buffer = [] love_buffer = [] happy_phrases = [] sad_phrases = [] fear_phrases = [] angry_phrases = [] love_phrases = [] happy_para = '' sad_para = '' fear_para = '' angry_para = '' love_para = '' happy_location = [] sad_location = [] fear_location = [] angry_location = [] love_location = [] def check_token(token): for i in class_tokens: if token in class_tokens[i]: return i return -1 TEST_SENTENCES = [] LOCATIONS = [] for tweet in tweepy.Cursor(api.search, q=keyword, count=100, lang='en', include_entities=False, tweet_mode='extended').items(max_items): location = tweet.user.location if not location: location = "" else: if "," in location: location = location[0:location.index(",")] location = location.strip() LOCATIONS.append(location) # print('Location :' , location) temp = tweet._json.get('full_text') if temp.startswith("RT"): try: temp = tweet._json.get('retweeted_status').get('full_text') except: temp = tweet._json.get('full_text') else: temp = tweet._json.get('full_text') temp = temp.replace("RT ", "").replace("!", "").replace( "..", "").replace("$", "").replace("%", "").replace("&", "").replace( "~", "").replace("-", "").replace("+", "").replace("#", "").replace( "\\n", "").replace("\\", "").replace("|", "") temp = " ".join(filter(lambda x: x[0] != '@', temp.split())) temp = re.sub(r'https\S+', "", temp) temp = temp.strip() para = para + temp TEST_SENTENCES.append(temp) print('Locations :', LOCATIONS) r.extract_keywords_from_text(para) # r.get_ranked_phrases_with_scores() ranked_phrases = r.get_ranked_phrases() for i in range(0, len(ranked_phrases)): ranked_phrases[i] = ranked_phrases[i].replace(",", "").replace( "'", "").replace("(", "").replace(')', "").replace('.', "").replace( '`', "").replace('!', "") ranked_phrases[i] = re.sub(' +', ' ', ranked_phrases[i]).strip() top_keywords = ranked_phrases[:] for i in range(0, len(ranked_phrases)): t1 = ranked_phrases[i].split() if len(t1) > 3: top_keywords.remove(ranked_phrases[i]) # print(TEST_SENTENCES) def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] maxlen = 30 batch_size = 32 # print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(TEST_SENTENCES) # print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) #model.summary() # print('Running predictions.') prob = model.predict(tokenized) # Find top emojis for each sentence. Emoji ids (0-63) # correspond to the mapping in emoji_overview.png # at the root of the DeepMoji repo. # print('Writing results to {}'.format(OUTPUT_PATH)) scores = [] for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, 5) t_score.append(sum(t_prob[ind_top])) t_score.append(ind_top) t_score.append([t_prob[ind] for ind in ind_top]) t_score.append('' + LOCATIONS[i]) scores.append(t_score) # print(t_score) # print('Scores skjdvbkjsdbvjk : ' , scores[0]) for i, row in enumerate(scores): try: # print(row[0]) # print('row 2') # print(row[2][0]) # if (row[2] in class_tokens] temp = check_token(row[2][0]) # print(temp) if temp == 'sad': sad_counter = 1 + sad_counter sad_buffer.append(row[0]) sad_para = sad_para + row[0] sad_location.append(row[4]) elif temp == 'happy': happy_counter = 1 + happy_counter # print("happy counter"); # print(happy_counter); happy_buffer.append(row[0]) happy_para = happy_para + row[0] happy_location.append(row[4]) elif temp == 'fear': fear_counter = 1 + fear_counter fear_buffer.append(row[0]) fear_para = fear_para + row[0] fear_location.append(row[4]) elif temp == 'angry': angry_counter = 1 + angry_counter angry_buffer.append(row[0]) angry_para = angry_para + row[0] angry_location.append(row[4]) elif temp == 'love': love_counter = 1 + love_counter love_buffer.append(row[0]) love_para = love_para + row[0] love_location.append(row[4]) except Exception: pass # print("Exception at row {}!".format(i)) # print("Angry buffer : " , angry_buffer) # print("Sad buffer : " , sad_buffer) r.extract_keywords_from_text(happy_para) happy_phrases = r.get_ranked_phrases()[0:3] r.extract_keywords_from_text(sad_para) sad_phrases = r.get_ranked_phrases()[0:3] r.extract_keywords_from_text(fear_para) fear_phrases = r.get_ranked_phrases()[0:3] r.extract_keywords_from_text(angry_para) angry_phrases = r.get_ranked_phrases()[0:3] r.extract_keywords_from_text(love_para) love_phrases = r.get_ranked_phrases()[0:3] # print("Phrases " , happy_phrases) # print("Angry Locations : " , angry_location) return happy_buffer, sad_buffer, fear_buffer, love_buffer, angry_buffer, happy_phrases, sad_phrases, fear_phrases, love_phrases, angry_phrases, happy_location, sad_location, fear_location, love_location, angry_location, top_keywords[: 10]
""" import sys import os from os.path import abspath, dirname sys.path.insert(0, dirname(dirname(abspath(__file__)))) import json import csv import numpy as np from deepmoji.sentence_tokenizer import SentenceTokenizer from deepmoji.model_def import deepmoji_emojis from deepmoji.global_variables import PRETRAINED_PATH, VOCAB_PATH maxlen = 30 batch_size = 32 model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] def model_predict(TEST_SENTENCES): print(TEST_SENTENCES) # print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) tokenized, _, _ = st.tokenize_sentences(TEST_SENTENCES)
def analyse_text_chunk(text_chunk): OUTPUT_PATH = 'test_sentences.csv' json_file = 'test_sentences.json' TEST_SENTENCES = sent_tokenize(text_chunk) def top_elements(array, k): ind = np.argpartition(array, -k)[-k:] return ind[np.argsort(array[ind])][::-1] maxlen = 30 batch_size = 32 print('Tokenizing using dictionary from {}'.format(VOCAB_PATH)) with open(VOCAB_PATH, 'r') as f: vocabulary = json.load(f) st = SentenceTokenizer(vocabulary, maxlen) tokenized, _, _ = st.tokenize_sentences(TEST_SENTENCES) print('Loading model from {}.'.format(PRETRAINED_PATH)) model = deepmoji_emojis(maxlen, PRETRAINED_PATH) model.summary() print('Running predictions.') prob = model.predict(tokenized) print('Writing results to {}'.format(OUTPUT_PATH)) scores = [] for i, t in enumerate(TEST_SENTENCES): t_tokens = tokenized[i] t_score = [t] t_prob = prob[i] ind_top = top_elements(t_prob, 5) t_score.append(sum(t_prob[ind_top])) t_score.extend(ind_top) t_score.extend([t_prob[ind] for ind in ind_top]) scores.append(t_score) #print(t_score) with open(OUTPUT_PATH, 'w') as csvfile: writer = csv.writer(csvfile, delimiter=',', lineterminator='\n') writer.writerow([ 'Text', 'Top5%', 'Emoji_1', 'Emoji_2', 'Emoji_3', 'Emoji_4', 'Emoji_5', 'Pct_1', 'Pct_2', 'Pct_3', 'Pct_4', 'Pct_5' ]) for i, row in enumerate(scores): try: writer.writerow(row) except Exception: print("Exception at row {}!".format(i)) csv_rows = [] with open(OUTPUT_PATH, 'r') as csvfile: reader = csv.DictReader(csvfile) title = reader.fieldnames for row in reader: csv_rows.extend( [{title[i]: row[title[i]] for i in range(len(title))}]) # Convert csv data into json and write it # format = 'pretty' # with open(json_file, "w") as f: # if format == "pretty": # f.write(json.dumps(csv_rows, sort_keys=False, indent=4, separators=(',', ': '), # ensure_ascii=False)) # else: # f.write(json.dumps(data)) return json.dumps(csv_rows, sort_keys=False, indent=4, separators=(',', ': '), ensure_ascii=False)