abehmiel

from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img

datagen = ImageDataGenerator(
        rotation_range=40,
        width_shift_range=0.2,
        height_shift_range=0.2,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True,
        fill_mode='nearest')

abehmiel

# -*- coding: utf-8 -*-
"""
@author: Faron
"""
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
from datetime import datetime

'''

abehmiel

from bs4 import BeautifulSoup
from glob import glob
from os import makedirs
from os.path import join
from urllib.parse import urljoin
import requests

CBS_HOME_URL = 'https://www.cbscorporation.com/'
YEARS = {'2009': '7', '2010': '4', '2011': '11', '2012': '9',
        '2013': '9', '2014': '9', '2015': '4', '2016': '6', '2017': '5'}

abehmiel

from bs4 import BeautifulSoup
from glob import glob
from os import makedirs
from os.path import join
from urllib.parse import urljoin
import requests

FOX_HOME_URL = 'http://press.foxnews.com/press-archive/'
YEARS = ['2011', '2012', '2013', '2014', '2015', '2016', '2017']
MONTHS = ['january', 'february', 'march', 'april', 'may', 'june',

abehmiel

"""
Because this code take so long to run as-coded below, I recommended to follow it
up with a check for file duplicates (fdupes -dN in linux seems to work)

After downloading, you can combine them into a single corpus file by concatenating:
find . -name "*.txt" -exec cat '{}' ';' > dirty.txt

Then you can use whatever means you wish to clean up the text and remove unicode symbols
and so on
"""

abehmiel

# test_prime.py
# from James Routley's blog: https://jamesroutley.co.uk/tech/2017/08/09/parameterise-python-tests.html
import pytest

from prime import is_prime


@pytest.mark.parametrize("x,output", [
    (-1, False),
    (0, False),

abehmiel

Transforming Code into Beautiful, Idiomatic Python

Notes from Raymond Hettinger's talk at pycon US 2013 video, slides.

The code examples and direct quotes are all from Raymond's talk. I've reproduced them here for my own edification and the hopes that others will find them as handy as I have!

Looping over a range of numbers

for i in [0, 1, 2, 3, 4, 5]:

abehmiel

""" GCD/ LCD """

# greatest common divisor
from fractions import gcd
gcd(x,y)

# least common multiple
def lcm(x, y):
    """ This function takes two
    integers and returns the L.C.M. """

abehmiel

from bs4 import BeautifulSoup
import requests

# for cleaning:
import re
import string
import nltk
from itertools import chain

def scrape_buzzfeed_article(url):

abehmiel

Keybase proof

I hereby claim:

• I am abehmiel on github.
• I am abehmiel (https://keybase.io/abehmiel) on keybase.
• I have a public key whose fingerprint is 9268 F147 2D66 ED22 5564 4480 AB82 9B94 356E D366

To claim this, I am signing this object: