nlp-2.py

from keras.preprocessing.sequence import pad_sequences
from keras.layers import Input, Dense, LSTM, Embedding
from keras.layers import Dropout, Activation, Bidirectional, GlobalMaxPool1D
from keras.models import Sequential
from keras import initializers, regularizers, constraints, optimizers, layers
from keras.preprocessing import text, sequence

# set the emotion/sentiment as our target
target = df['emotion']

# use one hot encoding since our target is categorical
y = pd.get_dummies(target).values

# use keras to create a Tokenizer object
tokenizer = text.Tokenizer(num_words=20000)  # limit to the num_words most important ones
tokenizer.fit_on_texts(list(df['tweet_text']))
tokenized_texts = tokenizer.texts_to_sequences(df['tweet_text'])
X = sequence.pad_sequences(tokenized_texts, maxlen=100)