Below is the full code:

import spacy
from tensorflow.keras.utils import to_categorical
from keras.preprocessing.text import Tokenizer
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense,LSTM,Embedding

def read_file(filepath):    
    with open(filepath) as f:
        str_text = f.read()
    
    return str_text

moby_text = read_file('moby_dick.txt')

nlp = spacy.load('en_core_web_sm')
doc = nlp(moby_text)

#getting tokens using list comprehension
tokens = [token.text.lower() for token in doc]

#cleaning text
tokens = [token for token in tokens if token not in '\n\n \n\n\n!"-#$%&()--.* ,-/:;<=>?@[\\]^_`{|}~\t\n ']

train_len = 10 1 # 10 i/p and 1 o/p
text_sequences = []
for i in range(train_len,len(tokens)):
    seq = tokens[i-train_len:i]
    text_sequences.append(seq)
tokenizer = Tokenizer()
tokenizer.fit_on_texts(text_sequences)
sequences = tokenizer.texts_to_sequences(text_sequences) 

for i in sequences[0]:
    print(f'{i} : {tokenizer.index_word[i]}')

sequences = np.array(sequences)
vocabulary_size = len(tokenizer.word_counts)



def create_model(vocabulary_size, seq_len):
    
    model = Sequential()
    model.add(Embedding(vocabulary_size, 25, input_length=seq_len))
    model.add(LSTM(100,return_sequences=True))
    model.add(LSTM(100))
    model.add(Dense(100,activation='relu'))
    model.add(Dense(vocabulary_size, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    model.summary()
    return model

X = sequences[:,:-1]
y = sequences[:,-1]
y = to_categorical(y, num_classes=vocabulary_size)

Here in the to_categorical I'm getting the error. I don't understand why? and after reading so many articles I still don't get how to solve it.

IndexError: index 2718 is out of bounds for axis 1 with size 2718

error

seq_len = X.shape[1]
model = create_model(vocabulary_size, seq_len)
model.fit(X, y,  epochs=100,verbose=1)

I don't understand the error. I have searched the error and tried different ways to solve it but I can't find anything to solve it. Also, I guess this is because the indices for lists start at 0. And I have done

Y = Y - 1
y = to_categorical(y, num_classes=vocabulary_size)

but this doesn't work because it gives error in the model. So I am back to square one.

Node: 'sequential/embedding/embedding_lookup'
indices[13,9] = 2718 is not in [0, 2718)
     [[{{node sequential/embedding/embedding_lookup}}]] [Op:__inference_train_function_5647]

So how can I solve it? Can someone please help me out? Thank you!!!

CodePudding user response：

The Tokenizer doesn't use 0, it starts counting with 1:

0 is a reserved index that won't be assigned to any word.

Try this:

vocabulary_size = len(tokenizer.word_counts)   1