main.py

# -*- coding: utf-8 -*-
"""main.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1eP_TTxxIGyv30xDs6dl8i5k1QIXyGvUa
"""

from model import GloVeModel
from dataloader import tokenized_dataLoader
import argparse
from numpy import save, load
from evaluate import are_Similar, get_ClosestWords, analogy
from collections import OrderedDict

def parse_args():
    parser = argparse.ArgumentParser()

    parser.add_argument('--epochs', type=int, default=100)
    parser.add_argument('--embedding_size', type=int, default=100)
    parser.add_argument('--context_size', type=int, default=10)
    parser.add_argument('--mode', type=str, default="train")
    
    parser.add_argument('--word1', type=str, default="man")
    parser.add_argument('--word2', type=str, default="boy")
    parser.add_argument('--word', type=str, default="woman")
    

    args = parser.parse_args()

    
    evaluation_words = OrderedDict([
        ('word1', args.word1),
        ('word2', args.word2),
        ('word', args.word),
    ])

    
    arguments = OrderedDict([
        ('evaluation_words', evaluation_words),
        ('context_size', args.context_size),
        ('embedding_size', args.embedding_size),
        ('mode', args.mode),
    ])

    return arguments

arguments = parse_args()


context_size = arguments['context_size']
embedding_size = arguments['embedding_size']
evaluation_words = arguments['evaluation_words']
mode = arguments['mode']

corpus = tokenized_dataLoader()

model = GloVeModel(embedding_size = embedding_size, context_size = context_size)
model.fit_to_corpus(corpus)
model.train(num_epochs=100)

if(mode == "plotEmbeddings"):
    model.generate_tsne()

if(mode == "help"):
    print("$ python3 main.py --embedding_size 100 --context_size 10\n")
    print("$ python3 main.py --mode \"are_Similar\" --word1 \"man\" --word2 \"boy\"\n")
    print("$ python3 main.py --mode \"get_ClosestWords\" --word \"man\"\n")
    print("$ python3 main.py --mode \"analogy\" --word1 \"man\" --word2 \"boy\" --word \"woman\"\n")
    print("$ python3 main.py --mode \"help\"")
    print("$ python3 main.py --mode \"wordIsInVocab\" --word_ \"man\"")

else:
    if(mode == "are_Similar"):
        word1 = evaluation_words['word1']
        word2 = evaluation_words['word2']

        print(are_Similar(word1, word2, model))

    if(mode == "get_ClosestWords"):
        word = evaluation_words['word']

        print(get_ClosestWords(word, model))

    if(mode == "analogy"):
        word1 = evaluation_words['word1']
        word2 = evaluation_words['word2']
        word3 = evaluation_words['word']

        print(analogy(word1, word2, word3, model))