The function takes in a string, and set a dataset online as a variable. It will then check which information does the string match the most.

import nltk
import os
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.classify.scikitlearn import SklearnClassifier
from sklearn.naive_bayes import MultinomialNB,BernoulliNB
from sklearn.linear_model import LogisticRegression,SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC

def classify(text):
  data = []
  if not os.path.isfile('data/data.txt'):
    with open('data/data.txt', 'wb') as csvfile:
      writer = csv.writer(csvfile)
      writer.writerow(('keywords', 'category'))
  with open('data/data.txt', 'rb') as csvfile:
    reader = csv.reader(csvfile)
    for row in reader:
      data.append(row)
  train_set = []
  for row in data:
    keywords = row[0