show predictions for each model

    #predicted label

    pred_y = []

    pred_y.append(pla.predict([preprocess.extract(message)])[0])

    pred_y.append(sgd.predict([preprocess.extract(message)])[0])

    pred_y.append(nn.predict([preprocess.extract(message)])[0])

    pred_y.append(tree.predict([preprocess.extract(message)])[0])

    pred_y.append('spam' if pla.predict([preprocess.extract(message)])[0] == 1 else 'ham')

    pred_y.append('spam' if sgd.predict([preprocess.extract(message)])[0] == 1 else 'ham')

    pred_y.append('spam' if nn.predict([preprocess.extract(message)])[0] == 1 else 'ham')

    pred_y.append('spam' if tree.predict([preprocess.extract(message)])[0] == 1 else 'ham')

    print(pred_y, '\n')

    """

    print(pred_y)

    """

    return str(pred_y.count(1)) + ' out of 4 models predict this message to be spam.'

    #return str(pred_y.count(1)) + ' out of 4 models predict this message to be spam.'

    return str(pred_y.count('spam')) + ' out of 4 models predict this message to be spam.<br><br>Perceptron: ' + pred_y[0] + '<br>Stochastic Gradient Descent: ' + pred_y[1] + '<br>Neural Network: ' + pred_y[2] + '<br>Decision Tree: ' + pred_y[3] + '<br><br>'

def getPerformanceMetrics():

features = []

#read in training and testing data

#kaggle and UCI contain the same data

def read_data():

    return data

def clean_text(text):

    #remove html tags

    clean = re.sub('<[^<]+?>', '', text)

### create features from training data

### input - spam/ham training set

### returns a list of feature words

def define_features(data, num_features=1000):

    #create list of text and labels

    text =  data['text'].tolist()

### creates a feature vector from a message

### input - list of feature words and an sms message

### returns a feature vector of 1 if feature is found in text and 0 if feature is not

def extract(message):

    global features

### creates a feature matrix from a data set

### input - list of feature words and data set to extract features from

### returns a numpy matrix containing a feature vector for each message, also returns an array of correct labels

def prepare(data):

    #create list of text and labels

    text =  data['text'].tolist()

    return np.array(matrix), target

# for API

def loadXY(refresh_data=False):

    if not os.path.isfile('X0.joblib') or not os.path.isfile('X1.joblib') or not os.path.isfile('Y.joblib') or refresh_data:

        print('Reading data...')

        data = read_data()

        #extract features from training data

        print('Defining features...')

        define_features(data)

        print('Preprocessing data...')

        #create feature matrix for training and testing data

        X, Y = prepare(data)

        dump(X[:25000, :], 'X0.joblib')

app = Flask(__name__)

CORS(app)

#import json

# Endpoint to load index.html

@app.route('/')

@app.route('/predict', methods=["POST"])

def predict():

    json = request.get_json()

    #message = json.loads(request.get_json())

    print(json)

    message = json['message']

    #response = json.dumps({'prediction': 'spam'})

    response = {'prediction': ml.makePrediction(message)}

    return response

spam,Larry,

spam,free sex for drugs,