def __init__(self, config, model_path='./runs/1539678339/checkpoints/model-200', word_to_index='./vocabs/word_to_index.json', index_to_label='./vocabs/index_to_label.json'): self.word_to_index = load_json(word_to_index) self.index_to_label = load_json(index_to_label) graph = tf.Graph() with graph.as_default(): session_conf = tf.ConfigProto( allow_soft_placement=config['allow_soft_placement'], log_device_placement=config['log_device_placement']) self.sess = tf.Session(config=session_conf) with self.sess.as_default(): # Load the saved meta graph and restore variables saver = tf.train.import_meta_graph( "{}.meta".format(model_path)) saver.restore(self.sess, model_path) # Get the placeholders from the graph by name self.input_x = graph.get_operation_by_name( "input_x").outputs[0] self.dropout_keep_prob = graph.get_operation_by_name( "dropout_keep_prob").outputs[0] # Tensors we want to evaluate self.predictions = graph.get_operation_by_name( "output/predictions").outputs[0]
def __init__(self, config, model_path='./runs/1548754630/checkpoints/model-1500', word2index='./vocabs/word2index.json', index2label='./vocabs/index2label.json'): self.word2index = load_json(word2index) self.index2label = load_json(index2label) graph = tf.Graph() with graph.as_default(): session_conf = tf.ConfigProto( allow_soft_placement=config['allow_soft_placement'], log_device_placement=config['log_device_placement']) self.sess = tf.Session(config=session_conf) with self.sess.as_default(): # 使用as_default(),当退出上下文的时候会话不会关闭 # load model saver = tf.train.import_meta_graph( '{}.meta'.format(model_path)) saver.restore(self.sess, model_path) # get the placeholders from graph by name self.input_x = graph.get_operation_by_name( 'input_x').outputs[0] self.dropout_keep_prob = graph.get_operation_by_name( 'dropout_keep_prob').outputs[0] # tensors we want to evaluate self.predictions = graph.get_operation_by_name( 'output/predictions').outputs[0]
def generating_training_time_series(lower_range, upper_range): # Read stream data _main_stream = dh.load_json(PATH + 'james.json') # All main stream data. #reply_stream = dh.load_json('james_reply.json') # All reply stream data. _reply_stream = [ dh.load_json(PATH + "james/{}.json".format(i)) for i in range(len(_main_stream)) ] # main posts time series main_stream_time_series = dh.main_stream_time_lists( _main_stream)[lower_range:upper_range] reply_stream_time_series = dh.reply_stream_time_lists( _reply_stream)[lower_range:upper_range] return main_stream_time_series, reply_stream_time_series
def load_data_all(): # glyce embedding fin = "../data/wvec.hf" init_vec = load_hdf(fin) # char vec from training fin = "../data/trn_wvec.hf" train_vec = load_hdf(fin) # glyce char2vec idx fdic = "../data/dictionary.json" fdic = load_json(fdic) init_ch2idx = fdic["char2idx"] # char2vec idx from training ch2idx = load_json("../md/char2idx.json") return init_ch2idx, init_vec, ch2idx, train_vec
def doc2vec(fci): dic = load_json(fci) init_ch2idx, init_vec, ch2idx, train_vec = load_data_all() raw_dic, dic = make_data(dic, ch2idx, train_vec, init_ch2idx, init_vec) fout = "../data/char2vec_with_glyce.pickle" write2pickle(fout, dic) fout = "../data/char2vec_raw.pickle" write2pickle(fout, raw_dic)
def generating_reply_time_series(upper_range, number): # Read stream data _main_stream = dh.load_json(PATH + 'james.json') # All main stream data. #reply_stream = dh.load_json('james_reply.json') # All reply stream data. _reply_stream = [ dh.load_json(PATH + "james/{}.json".format(i)) for i in range(len(_main_stream)) ] # main posts time series main_stream_time_series = dh.main_stream_time_lists( _main_stream)[upper_range:upper_range + number] reply_stream_time_series = dh.reply_stream_time_lists( _reply_stream)[upper_range:upper_range + number] for i in range(len(reply_stream_time_series)): temp = np.array(reply_stream_time_series[i]) reply_stream_time_series[i] = temp[np.where( temp < main_stream_time_series[-1])] return main_stream_time_series, reply_stream_time_series
text_list[i] = '' return text_list def searchkw(text_list, kw_lists): """Search for targeted elements in the list based on the lw_lists""" mentions_list = [] for i, x in enumerate(text_list): if any(n in x.lower() for n in kw_lists): mentions_list.append(i) return mentions_list main_stream = dh.load_json("data/Avengers/avengers.json") texts = generate_text(main_stream) mentions = searchkw(texts, ['lbj', 'lebron', 'lebron james']) # Get all posts related to James james_dataframe = main_stream.iloc[mentions] james_main_id = list(james_dataframe.sub_id) # Generate James related james_reply_stream = pd.DataFrame([]) for i in range(8): df = dh.load_json('data/NBA_1904/reply_stream_{}.json'.format(i+1)) for i in range(len(df)): if df.iloc[i].link_id in james_main_id: