Edmond Yoo
2018-08-26 b88a7221000facda2fd81330417958adcc17dc3c
Aggregating card images, importing texture images for background
3 files modified
1 files added
13566 ■■■■■ changed files
card_detector.py 1 ●●●● patch | view | raw | blame | history
data/all_cards.csv 13461 ●●●●● patch | view | raw | blame | history
fetch_data.py 36 ●●●●● patch | view | raw | blame | history
generate_data.py 68 ●●●●● patch | view | raw | blame | history
card_detector.py
@@ -4,6 +4,7 @@
import math
from screeninfo import get_monitors
def detect_a_card(img, thresh_val=80, blur_radius=None, dilate_radius=None, min_hyst=80, max_hyst=200,
                  min_line_length=None, max_line_gap=None, debug=False):
    dim_img = (len(img[0]), len(img)) # (width, height)
data/all_cards.csv
Diff too large
fetch_data.py
@@ -2,12 +2,14 @@
import json
import pandas as pd
import re
import os
def fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+format:modern+lang:en+frame:2003',
                         csv_name=''):
    has_more = True
    cards = []
    # get cards dataset as a json from the query
    while has_more:
        res_file_dir, http_message = request.urlretrieve(url)
        with open(res_file_dir) as res_file:
@@ -18,23 +20,21 @@
                url = res_json['next_page']
            print(len(cards))
    # Convert them into a dataframe, and truncate unnecessary columns
    df = pd.DataFrame.from_dict(cards)
    df['image'] = ''
    for ind, row in df.iterrows():
        df.set_value(ind, 'image', row['image_uris']['png'])
    if csv_name != '':
        df = df[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', 'image_uris',
                 'image', 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name',
                 'power', 'toughness']]
        df.to_csv(csv_name, sep=';')
                 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name', 'power',
                 'toughness']]
        df.to_csv(csv_name, sep=';')  # Comma doesn't work, since some columns are saved as a dict
    return cards
    return df
# Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py)
def get_valid_filename(s):
    """
    NOTE: Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py)
    Return the given string converted to a string that can be used for a clean
    filename. Remove leading and trailing spaces; convert other spaces to
    underscores; and remove anything that is not an alphanumeric, dash,
@@ -46,14 +46,26 @@
    return re.sub(r'(?u)[^-\w.]', '', s)
def fetch_cards_image(cards_json, out_dir, size='large'):
    for card in cards_json:
        request.urlretrieve(card['image_uris'][size], '%s\%s' % (out_dir, card['name']))
def fetch_cards_image(df, out_dir='', size='png'):
    for ind, row in df.iterrows():
        png_url = row['image_uris'][size]
        if out_dir == '':
            out_dir = 'data/png/%s' % row['set']
        if not os.path.exists(out_dir):
            os.makedirs(out_dir)
        img_name = '%s/%s_%s.png' % (out_dir, row['collector_number'], get_valid_filename(row['name']))
        request.urlretrieve(png_url, filename=img_name)
        print(img_name)
    pass
def main():
    fetch_all_cards_text(csv_name='data/all_cards.csv')
    df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+set:rtr+lang:en',
                              csv_name='data/all_cards.csv')
    fetch_cards_image(df)
    pass
if __name__ == '__main__':
    main()
    pass
generate_data.py
New file
@@ -0,0 +1,68 @@
from glob import glob
import matplotlib.pyplot as plt
import matplotlib.image as mpimage
import pickle
import math
import random
import os
# Referenced from geaxgx's playing-card-detection: https://github.com/geaxgx/playing-card-detection
class Backgrounds:
    def __init__(self, images=None, dumps_dir='data/dtd/images'):
        if images is not None:
            self._images = images
        else:  # load from pickle
            if not os.path.exists(dumps_dir):
                print('Warning: directory for dump %s doesn\'t exist' % dumps_dir)
                return
            self._images = []
            for dump_name in glob(dumps_dir + '/*.pck'):
                with open(dump_name, 'rb') as dump:
                    print('Loading ' + dump_name)
                    images = pickle.load(dump)
                    self._images += images
            if len(self._images) == 0:
                self._images = load_dtd()
        print('# of images loaded: %d' % len(self._images))
    def get_random(self, display=False):
        bg = self._images[random.randint(0, len(self._images) - 1)]
        if display:
            plt.show(bg)
        return bg
def load_dtd(dtd_dir='data/dtd/images', dump_it=True, dump_batch_size=1000):
    if not os.path.exists(dtd_dir):
        print('Warning: directory for DTD 5s doesn\'t exist.' % dtd_dir)
        print('You can download the dataset using this command:'
              '!wget https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz')
        return []
    bg_images = []
    # Search the directory for all images, and append them
    for subdir in glob(dtd_dir + "/*"):
        for f in glob(subdir + "/*.jpg"):
            bg_images.append(mpimage.imread(f))
    print("# of images loaded :", len(bg_images))
    # Save them as a pickle if necessary
    if dump_it:
        for i in range(math.ceil(len(bg_images) / dump_batch_size)):
            dump_name = '%s/dtd_dump_%d.pck' % (dtd_dir, i)
            with open(dump_name, 'wb') as dump:
                print('Dumping ' + dump_name)
                pickle.dump(bg_images[i * dump_batch_size:(i + 1) * dump_batch_size], dump)
    return bg_images
def main():
    #bg_images = load_dtd()
    bg = Backgrounds()
    bg.get_random(display=True)
    return
if __name__ == '__main__':
    main()