jss367

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

jss367

import re
from urllib import request

# Now let's grab some text from Great Expectations
url = 'http://www.gutenberg.org/files/1400/1400-0.txt'
response = request.urlopen(url)
raw = response.read().decode('utf8')

# Here is some text we'll start with
text = raw[886:1091]

jss367

def dict_sort(dictionary, descending=False):
    dict_to_list = [(dictionary[key], key) for key in dictionary]
    dict_to_list.sort(descending=reverse)
    return dict_to_list

jss367

# Let's make a single function to determine the parts of speech

import re
import nltk
import os
#from collections import Counter # Is this used?

# First we break the text into tokens
def tokinze_text(raw_text):
    tokens = nltk.word_tokenize(raw_text)

jss367

def grayscale(image, algorithm='luminosity'):
    """
    The algorithms are based on those used in GIMP. They are 'lightness', 'average', and 'luminosity'. Luminosity is the default
    """
    l, w, color_space = image.shape
    num_pxls = l*w
    assert (color_space == 3), "The image must have three dimensions of color: red, green, and blue"
    # Extract the individual colors
    red = image[:,:,0]
    green = image[:,:,1]

jss367

import re

test_cases = ['04/30/2009', '06/20/95', '8/2/69', '1/25/2011', '9/3/2002', '4-13-82', 'Mar-02-2009', 'Jan 20, 1974',
        'March 20, 1990', 'Dec. 21, 2001', 'May 25 2009', '01 Mar 2002', '2 April 2003', '20 Aug. 2004',
        '20 November, 1993', 'Aug 10th, 1994', 'Sept 1st, 2005', 'Feb. 22nd, 1988', 'Sept 2002', 'Sep 2002',
        'December, 1998', 'Oct. 2000', '6/2008', '12/2001', '1998', '2002']

# Create a dictionary to convert from month names to numbers (e.g. Jan = 01)
month_dict = dict(jan='01', feb='02', mar='03', apr='04', may='05', jun='06', jul='07', aug='08', sep='09',
                  oct='10', nov='11', dec='12')

jss367

# Find the internal structure of a list or numpy array
def shape(lst):
    ob_type = type(lst)
    if ob_type == np.ndarray:
        print("The size is " + str(lst.shape))
    length = len(lst)
    shp = tuple(shape(sub) if isinstance(sub, list) else 0 for sub in lst)
    if any(x != 0 for x in shp):
        return length, shp
    else:

jss367

# if you want to change the path
# you'll need to:
# export DETECTRON2_DATASETS=/home/jsimonelli/data/detectron2
# or 
# import os
# os.environ['DETECTRON2_DATASETS'] = '/home/jsimonelli/data/detectron2'

# detectron2 expects it to be in a folder called coco
mkdir coco
cd coco

jss367

import mimetypes
image_extensions = set(k for k, v in mimetypes.types_map.items() if v.startswith('image'))

jss367

# Sometimes I make functions that can either allow an object or a list of objects.
# To do this I check if an input is an object and, if so, wrap it in a list.
# Here's a simple way to do that.

def _isArrayLike(obj):
    return hasattr(obj, '__iter__') and hasattr(obj, '__len__')
    
objs = objs if _isArrayLike(objs) else [objs]

#Another option is to do the opposite check: