pipeline.py

from transformers import Pipeline
import tensorflow as tf
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.text import tokenizer_from_json
from tensorflow.keras.preprocessing.sequence import pad_sequences
import json
import numpy as np

class NewsClassifierPipeline(Pipeline):
    def __init__(self):
        super().__init__()
        self.model = load_model('news_classifier.h5')
        with open('tokenizer.json') as f:
            tokenizer_data = json.load(f)
            self.tokenizer = tokenizer_from_json(tokenizer_data)

    def preprocess(self, text):
        sequence = self.tokenizer.texts_to_sequences([text])
        padded = pad_sequences(sequence)
        return padded

    def _forward(self, texts):
        processed = self.preprocess(texts)
        predictions = self.model.predict(processed)
        scores = tf.nn.softmax(predictions, axis=1)
        
        predicted_class = np.argmax(predictions)
        score = float(np.max(scores))
        
        label = 'foxnews' if predicted_class == 0 else 'nbc'
        
        return [{'label': label, 'score': score}]

    def postprocess(self, model_outputs):
        return model_outputs