yogeshnile

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "VisualEditor0",
            "Effect": "Allow",
            "Action": [
                "ce:GetCostAndUsageWithResources",
                "ce:GetCostAndUsage"
            ],

yogeshnile

yogeshnile

app = Flask(__name__)

@app.route('/')
def home():
	return render_template('index.html')

@app.route('/result', methods=['POST','GET'])
def predict():
    if request.method == 'POST':
        message = request.form['message']

yogeshnile

def predict_spam(sample_message):
    sample_message = re.sub(pattern='[^a-zA-Z]',repl=' ', string = sample_message)
    sample_message = sample_message.lower()
    sample_message_words = sample_message.split()
    sample_message_words = [word for word in sample_message_words if not word in set(stopwords.words('english'))]
    ps = PorterStemmer()
    final_message = [ps.stem(word) for word in sample_message_words]
    final_message = ' '.join(final_message)
    temp = cv.transform([final_message]).toarray()
    return classifier.predict(temp)

yogeshnile

#Import Pickle file
file_name = "Spam_sms_prediction.pkl"
classifier = pickle.load(open(file_name, 'rb'))

file_name = "corpus.pkl"
corpus = pickle.load(open(file_name, 'rb'))

#Creating the Bag of Words model
cv = CountVectorizer(max_features=2500)
X = cv.fit_transform(corpus).toarray()

yogeshnile

#train_test_split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=0)

#Fitting Naive Bayes to the Training set
classifier = MultinomialNB(alpha=0.1)
classifier.fit(X_train, y_train)

#Save Model
file_name = "Spam_sms_prediction.pkl"

yogeshnile

#Save corpus for use in deployment
file_name = "corpus.pkl"
pickle.dump(corpus, open(file_name, 'wb'))

#Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features=2500)
X = cv.fit_transform(corpus).toarray()

#Extracting dependent variable from the dataset

yogeshnile

#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