agustinustheo

# create bag-of-words
all_words = []

for message in sms_data:
    words = word_tokenize(message)
    for w in words:
        all_words.append(w)
        
all_words = nltk.FreqDist(all_words)

agustinustheo

encoder = LabelEncoder()
Y = encoder.fit_transform(classes)

# Now lets do it for all the messages
messages = list(zip(sms_data, Y))

agustinustheo

# define a seed for reproducibility
seed = 1
np.random.seed = seed
np.random.shuffle(messages)

# call find_features function for each SMS message
featuresets = [(find_features(text), label) for (text, label) in messages]

agustinustheo

# we can split the featuresets into training and testing datasets using sklearn
from sklearn import model_selection

# split the data into training and testing datasets
training = featuresets

# Define models to train
names = ["Logistic Regression"]

classifiers = [

agustinustheo

for name, model in models:
    nltk_model = SklearnClassifier(model)
    classifier = nltk_model.train(training)
    f = open(name + ' Classifier.pickle', 'wb')
    pickle.dump(classifier, f)
    f.close

agustinustheo

classifier_s = open("sms_classifier_pickle/" + name + ' Classifier.pickle', "rb")
sms_classifier = pickle.load(classifier_s)
classifier_s.close()

result = sms_classifier.classify(find_features(preproccess_text('ENTER MESSAGE TO CLASSIFY HERE')))

agustinustheo

import os
import re
import sys
import nltk
import random
import pickle
import numpy as np
import pandas as pd
from sklearn.svm import SVC
from sklearn.naive_bayes import MultinomialNB

agustinustheo

from flask import Flask

app = Flask(__name__)

if __name__ == "__main__":
    app.run(host='0.0.0.0')

agustinustheo

import os
from faunadb import query as q
from faunadb.objects import Ref
from faunadb.client import FaunaClient

def get(index, data):
    try:
        serverClient = FaunaClient(secret=os.environ.get("FAUNA_SERVER_SECRET"))
        res = serverClient.query(q.get(q.match(q.index(index), data)))
        res["data"]["ref_id"] = res["ref"].id()

agustinustheo

def get_multiple(index, data=None):
    try:
        serverClient = FaunaClient(secret=os.environ.get("FAUNA_SERVER_SECRET"))
        res_arr = []
        if data is None:
            res = serverClient.query(   
                q.map_(
                    q.lambda_("data", q.get(q.var("data"))), 
                    q.paginate(q.match(q.index(index)))
                )