base.py

import sys
import argparse
import logging
from logging import critical, error, info, warning, debug

import numpy as np
import seaborn as sn
import pandas as pd
import random

from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.feature_extraction import DictVectorizer


import nltk
from nltk.probability import FreqDist
import matplotlib.pyplot as plt


def parse_arguments():
    """Read arguments from a command line"""
    parser = argparse.ArgumentParser(description='Please add arguments')
    parser.add_argument('-v', '--verbose', metavar='verbosity', type=int, default=3,
        help='Verbosity of logging: 0 -critical, 1 -error, 2 -warning, 3 -info, 4 -debug')
    parser.add_argument('--input', metavar='FILE', required=True,
        help='txt file containing the data')
    parser.add_argument('--binary', action='store_true',
        help='Set if you want binary classification')

    args = parser.parse_args()
    verbose = {0: logging.CRITICAL, 1: logging.ERROR, 2: logging.WARNING, 3: logging.INFO, 4: logging.DEBUG}
    logging.basicConfig(format='%(message)s', level=verbose[args.verbose], stream=sys.stdout)

    return args


def main():
    """Main function where the pipeline will be put together."""

if __name__ == '__main__':
    args = parse_arguments()
    if args.input:
        main()