Sequence Model

from io import open
import os, string, random, time, math
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import sys
from sklearn.model_selection import train_test_split

import torch
import torch.nn
import torch.nn as nn
import torch.optim as optim

from IPython.display import clear_output
from tqdm import tqdm

languages = []
data = []
X = []
y = []

with open('/content/drive/My Drive/Dataset/Text_Data/name2lang.txt', 'r') as f: 
    for line in f:
        line = line.split(',')
        name = line[0].strip()
        lang = line[1].strip()
        if not lang in languages:
            languages.append(lang)
        X.append(name)
        y.append(lang)
        data.append((name, lang))

n_languages = len(languages)

#print(languages)

n_languages