import nltk
import string
import numpy as np
import pandas as pd
from nltk.corpus import stopwords
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers.embeddings import Embedding
np.random.seed(7)
df = pd.read_csv('financial.csv')
def clean(text):
text=text.translate(string.punctuation)
text=text.lower().split()
stops = set(stopwords.words("english"))
text = [w for w in text if not w in stops and len(w) >= 3]
text = text.split()
stemmer = SnowballStemmer('english')
stemmed_words = [stemmer.stem(word) for word in text]
text = " ".join(stemmed_words)
return text
df['text']=df['text'].map(lambda text: clean(text))