SMS Spam Detection

Data Input and Cleaning.py

#Get Sms Dataset
sms = pd.read_csv('Spam SMS Collection', sep='\t', names=['label','message'])
sms.drop_duplicates(inplace=True)
sms.reset_index(drop=True, inplace=True)

#Cleaning the messages
corpus = []
ps = PorterStemmer()
for i in range(0,sms.shape[0]):
    message = re.sub(pattern='[^a-zA-Z]', repl=' ', string=sms.message[i]) #Cleaning special character from the message
    message = message.lower() #Converting the entire message into lower case
    words = message.split() # Tokenizing the review by words
    words = [word for word in words if word not in set(stopwords.words('english'))] #Removing the stop words
    words = [ps.stem(word) for word in words] #Stemming the words
    message = ' '.join(words) #Joining the stemmed words
    corpus.append(message) #Building a corpus of messages