from sklearn.datasets import fetch_20newsgroups
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional

categories = ['sci.space', 'comp.graphics', 'rec.sport.baseball', 'talk.politics.misc',
              'sci.electronics', 'soc.religion.christian', 'rec.autos',
              'talk.politics.mideast', 'comp.sys.mac.hardware', 'misc.forsale']

newsgroups = fetch_20newsgroups(subset='train', categories=categories)
texts = newsgroups.data
labels = newsgroups.target
# len(texts) -> 5750

vocab_size, maxlen = 10000, 200
tokenizer = Tokenizer(num_words=vocab_size)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
padded_sequences = pad_sequences(sequences, maxlen=maxlen, padding='post')

encoder = LabelBinarizer()
one_hot_labels = encoder.fit_transform(labels)

Embedding(input_dim=vocab_size, output_dim=128, input_length=maxlen)

LSTM(units=64, return_sequences=True)
LSTM(units=32, dropout=0.2, recurrent_dropout=0.2)

model_lstm = Sequential()
model_lstm.add(Embedding(input_dim=vocab_size, output_dim=128, input_length=maxlen))
model_lstm.add(LSTM(units=64, return_sequences=True))
model_lstm.add(LSTM(units=32, dropout=0.2, recurrent_dropout=0.2))
model_lstm.add(Dense(10, activation='softmax'))
model_lstm.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model_lstm.fit(padded_sequences, one_hot_labels, epochs=10, batch_size=32, validation_split=0.2)

Epoch 1/10  accuracy: 0.1436  val_accuracy: 0.2157
Epoch 10/10 accuracy: 0.5796  val_accuracy: 0.5191

Bidirectional(LSTM(units=64, dropout=0.2, recurrent_dropout=0.2))

model_bi = Sequential()
model_bi.add(Embedding(input_dim=vocab_size, output_dim=128, input_length=maxlen))
model_bi.add(Bidirectional(LSTM(units=64, dropout=0.2, recurrent_dropout=0.2)))
model_bi.add(Dense(10, activation='softmax'))
model_bi.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model_bi.fit(padded_sequences, one_hot_labels, epochs=10, batch_size=32, validation_split=0.2)

Epoch 1/10  accuracy: 0.1717  val_accuracy: 0.3843
Epoch 5/10  accuracy: 0.9387  val_accuracy: 0.7783
Epoch 10/10 accuracy: 0.9971  val_accuracy: 0.8070

sample_text = ["NASA is planning a mission to Jupiter"]
seq = tokenizer.texts_to_sequences(sample_text)
pad = pad_sequences(seq, maxlen=maxlen, padding='post')

prediction = model_bi.predict(pad)
predicted_class_index = np.argmax(prediction)
print("Actual Category:", newsgroups.target_names[predicted_class_index])
# Predicted class index: 6 -> sci.space (correct!)