How to predict using multiple saved model?

Question

I am trying to predict the score values from downloaded saved model from this notebook

https://www.kaggle.com/paoloripamonti/twitter-sentiment-analysis/

It contains 4 saved model namely :

1. encoder.pkl
2. model.h5
3. model.w2v
4. tokenizer.pkl

I am using model.h5 my code here is:

from keras.models import load_model
s_model = load_model('model.h5')

#predict the result
result = model.predict("HI my name is Mansi")

But it's unable to predict.

I think the error is because I have to tokenize and encode it first but I don't know how to do that using multiple saved models.

Can anyone guide me through how to predict values and scores using the saved model as mentioned in above notebook.

Answer 1

One should preprocess the text before feeding into the model, following is the minimal working script(adapted from https://www.kaggle.com/paoloripamonti/twitter-sentiment-analysis/ ):

import time
import pickle
from keras.preprocessing.sequence import pad_sequences
from keras.models import load_model

model = load_model('model.h5')
tokenizer = pickle.load(open('tokenizer.pkl', "rb"))
SEQUENCE_LENGTH = 300
decode_map = {0: "NEGATIVE", 2: "NEUTRAL", 4: "POSITIVE"}

POSITIVE = "POSITIVE"
NEGATIVE = "NEGATIVE"
NEUTRAL = "NEUTRAL"
SENTIMENT_THRESHOLDS = (0.4, 0.7)

def decode_sentiment(score, include_neutral=True):
    if include_neutral:        
        label = NEUTRAL
        if score <= SENTIMENT_THRESHOLDS[0]:
            label = NEGATIVE
        elif score >= SENTIMENT_THRESHOLDS[1]:
            label = POSITIVE

        return label
    else:
        return NEGATIVE if score < 0.5 else POSITIVE

def predict(text, include_neutral=True):
    start_at = time.time()
    # Tokenize text
    x_test = pad_sequences(tokenizer.texts_to_sequences([text]), maxlen=SEQUENCE_LENGTH)
    # Predict
    score = model.predict([x_test])[0]
    # Decode sentiment
    label = decode_sentiment(score, include_neutral=include_neutral)

    return {"label": label, "score": float(score),
       "elapsed_time": time.time()-start_at}  

predict("hello")

Test:

predict("hello")

Its output:

{'elapsed_time': 0.6313169002532959,
 'label': 'POSITIVE',
 'score': 0.9836862683296204}