| from transformers import AutoTokenizer,TFAutoModelForMaskedLM,TFAutoModelForSequenceClassification | |
| import tensorflow as tf | |
| import numpy as np | |
| def get_model(model): | |
| DROP_OUT = 0.1 | |
| input_ids = tf.keras.Input(shape=(None, ),dtype='int32',name='input_ids') | |
| token_type_ids = tf.keras.Input(shape=(None, ),dtype='int32',name='token_type_ids') | |
| attention_mask = tf.keras.Input(shape=(None, ), dtype='int32',name='attention_mask') | |
| transformer = model(input_ids,attention_mask, token_type_ids,output_hidden_states=True) | |
| cls = transformer.hidden_states[-1][:,0,:] | |
| drop_out = tf.keras.layers.Dropout(DROP_OUT)(cls) | |
| sentiment = tf.keras.layers.Dense(768,activation='relu',name='sentiment')(drop_out) | |
| sentiment = tf.keras.layers.Dense(768,activation='relu',name='sentiment2')(sentiment) | |
| sentiment = tf.keras.layers.Dense(768,activation='relu',name='sentiment3')(sentiment) | |
| sentiment = tf.keras.layers.Dense(4,activation='softmax',name='sentiment_out')(sentiment) | |
| speech_act = tf.keras.layers.Dense(768,activation='relu',name='speech_act')(drop_out) | |
| speech_act = tf.keras.layers.Dense(768,activation='relu',name='speech_act2')(speech_act) | |
| speech_act = tf.keras.layers.Dense(768,activation='relu',name='speech_act3')(speech_act) | |
| speech_act = tf.keras.layers.Dense(6,activation='softmax',name='speech_act_out')(speech_act) | |
| sarcasm = tf.keras.layers.Dense(768,activation='relu',name='sarcasm')(drop_out) | |
| sarcasm = tf.keras.layers.Dense(768,activation='relu',name='sarcasm2')(sarcasm) | |
| sarcasm = tf.keras.layers.Dense(768,activation='relu',name='sarcasm3')(sarcasm) | |
| sarcasm = tf.keras.layers.Dense(2,activation='softmax',name='sarcasm_out')(sarcasm) | |
| output = tf.keras.layers.Concatenate(axis = -1)([sentiment,speech_act,sarcasm]) | |
| Fmodel = tf.keras.Model(inputs=[input_ids,token_type_ids, attention_mask], outputs=output) | |
| Fmodel.load_weights('model_cls_weights.h5') | |
| return Fmodel | |
| def classify(texts,model,tokenizer): | |
| speech_act_decoder = {0:'Expression',1:'Assertion',2:'Question',3:'Recommendation',4:'Request',5:'Miscellaneous'} | |
| sentiment_decoder = {0:'Positive',1:'Neutral',2:'Negative',3:'Mixed'} | |
| sarcasm_decoder = {0:'Not Sarcastic',1:'Sarcastic'} | |
| tokens = tokenizer(texts,return_tensors='tf',padding=True) | |
| preds = model.predict(list(dict(tokens).values()),verbose=0) | |
| sen_func = np.vectorize(lambda x : sentiment_decoder[x]) | |
| sentiment = sen_func(preds[:,0:4].argmax(axis=1)) | |
| sar_func = np.vectorize(lambda x : sarcasm_decoder[x]) | |
| sarcasm = sar_func(preds[:,10:].argmax(axis=1)) | |
| speech_func = np.vectorize(lambda x: speech_act_decoder[x]) | |
| speech_act = speech_func(preds[:,4:10].argmax(axis=1)) | |
| res = [] | |
| if isinstance(texts,list): | |
| for i in range(len(texts)): | |
| res.append({"text":texts[i],"sentiment":sentiment[i],"speech_act":speech_act[i],"sarcasm":sarcasm[i]}) | |
| return res | |
| else: | |
| res.append({"text":texts,"sentiment":sentiment[0],"speech_act":speech_act[0],"sarcasm":sarcasm[0]}) | |
| return res |