Move .csvs to subdirectory, refactor cube_json.py out of word_count.py

This commit is contained in:
henriquenakashima 2020-11-29 15:24:37 -05:00
parent 7226fc3b17
commit 32f8c20b2e
8 changed files with 110 additions and 95 deletions

View file

@ -1,6 +1,8 @@
import json
import os
import cube_json
import word_count
def get_keywords(card):
if 'keywords' in card.keys():
@ -40,10 +42,12 @@ def keyword_report(k_dict):
print(f'\nTotal unique keywords: {len(k_dict)}')
# ### Example use: print a keyword report for a cards.json file ###
# filename = f'cubes/CoreTheElegantCube.json'
# k_dict = keyword_count(filename)
# keyword_report(k_dict)
if __name__ == '__main__':
### Example use: print a keyword report for a cards.json file ###
# cube_list = cube_json.load_cube_from_csv('cube_csvs/TheElegantCube_2020-11-17_5.0.4.csv', {'core'})
# cube_json_filename = cube_json.create_cube_json(cube_list, 'cubes/TheElegantCube_2020-11-17_5.0.4.json')
# keyword_dict = keyword_count(cube_json_filename)
# keyword_report(keyword_dict)
# ### Example use: count keywords in a list of cube.json files ###
@ -73,3 +77,5 @@ def keyword_report(k_dict):
# output_file.write(f'{code},{len(k_dict)}\n')
# output_file.close()
# f.close()
pass

View file

Can't render this file because it has a wrong number of fields in line 2.

View file

Can't render this file because it has a wrong number of fields in line 2.

View file

Can't render this file because it has a wrong number of fields in line 2.

41
cube_json.py Normal file
View file

@ -0,0 +1,41 @@
import csv
import json
from word_count import EXPECTED_HEADER, COLUMNS, TEMP_JSON, is_actual_mtg_card
def load_cube_from_csv(filename, tag_filter=None):
cards = []
with open(filename) as f:
reader = csv.reader(f)
header_line = next(reader)
assert header_line == EXPECTED_HEADER
for line in reader:
card = line[COLUMNS['Name']]
# Export CSV is broken on CubeCobra because Image Back URL is always just one double quotes character.
tags = [t.strip() for t in line[COLUMNS['Tags']].split(', ')]
if tag_filter is None or any(t in tag_filter for t in tags):
cards.append(card)
return cards
def create_cube_json(cards, output_filename=TEMP_JSON):
# Call this once to create a smaller JSON file from the full card list
# Visit https://scryfall.com/docs/api/bulk-data and look for "Oracle Cards" file;
# Download and rename it to 'oracle_cards.json'
with open('oracle_cards.json', encoding='utf8') as f_oracle_cards:
d = json.load(f_oracle_cards)
f_cube_json = open(output_filename, 'w+', encoding='utf8')
cube_data = []
for card in d:
if card['name'] in cards:
for i in range(cards.count(card['name'])):
cube_data += [card]
elif 'card_faces' in card.keys() and is_actual_mtg_card(card):
for face in card['card_faces']:
if face['name'] in cards:
cube_data += [card]
string_data = json.dumps(cube_data)
f_cube_json.write(string_data)
f_cube_json.close()
return output_filename

File diff suppressed because one or more lines are too long

View file

@ -8,7 +8,7 @@ OUTPUT_POOL_SIZE = 360
CARDS_FROM_OCCASIONAL = 48
CARDS_FROM_CORE = OUTPUT_POOL_SIZE - CARDS_FROM_OCCASIONAL
CSV_FILENAME = 'TheElegantCube20201102.csv'
CSV_FILENAME = 'cube_csvs/TheElegantCube_2020-11-17_5.0.4.csv'
OUTPUT_FILENAME = 'cards_in_draft.txt'
EXPECTED_HEADER = [
'Name',

View file

@ -1,8 +1,8 @@
import csv
import json
from collections import defaultdict
from pprint import pp
import cube_json
def load_cube_from_txt(filename):
@ -37,48 +37,11 @@ EXPECTED_HEADER = [
]
COLUMNS = {column_name: i for i, column_name in enumerate(EXPECTED_HEADER)}
def load_cube_from_csv(filename, tag_filter=None):
cards = []
with open(filename) as f:
reader = csv.reader(f)
header_line = next(reader)
assert header_line == EXPECTED_HEADER
for line in reader:
card = line[COLUMNS['Name']]
# Export CSV is broken on CubeCobra because Image Back URL is always just one double quotes character.
tags = [t.strip() for t in line[COLUMNS['Tags']].split(', ')]
if tag_filter is None or any(t in tag_filter for t in tags):
cards.append(card)
return cards
def is_actual_mtg_card(card_dict):
return card_dict['set_type'] not in {'memorabilia', 'funny', 'token'}
def create_cube_json(cards):
# Call this once to create a smaller JSON file from the full card list
# Visit https://scryfall.com/docs/api/bulk-data and look for "Oracle Cards" file;
# Download and rename it to 'oracle_cards.json'
with open('oracle_cards.json', encoding='utf8') as f_oracle_cards:
d = json.load(f_oracle_cards)
output_filename = TEMP_JSON
f_cube_json = open(output_filename, 'w+', encoding='utf8')
cube_data = []
for card in d:
if card['name'] in cards:
for i in range(cards.count(card['name'])):
cube_data += [card]
elif 'card_faces' in card.keys() and is_actual_mtg_card(card):
for face in card['card_faces']:
if face['name'] in cards:
cube_data += [card]
string_data = json.dumps(cube_data)
f_cube_json.write(string_data)
f_cube_json.close()
return TEMP_JSON
def create_all_cards_json():
with open('oracle_cards.json', encoding='utf8') as f_oracle_cards:
d = json.load(f_oracle_cards)
@ -196,6 +159,7 @@ def get_text(card):
text += face['oracle_text'] + ' '
return text
if __name__ == '__main__':
################################################################################
full_oracle = False
@ -204,17 +168,17 @@ full_oracle = False
# Use either line:
# 1. If you have a .txt of your cube
# cube_list = load_cube_from_txt('YourCubeHere.txt')
# cube_list = cube_json.load_cube_from_txt('YourCubeHere.txt')
# 2. If you have a .csv of your cube
# cube_list = load_cube_from_csv('YourCubeHere.csv')
# cube_list = cube_json.load_cube_from_csv('YourCubeHere.csv')
# 3. If you have a .csv of your cube and want to consider only cards with a certain tag
cube_list = load_cube_from_csv('TheElegantCube_2020-11-17_5.0.4.csv', {'core'})
################################################################################
cube_list = cube_json.load_cube_from_csv('cube_csvs/TheElegantCube_2020-11-17_5.0.4.csv', {'core'})
################################################################################
# Calculate average of a cube
cube_json_handle = create_cube_json(cube_list)
cube_json_handle = cube_json.create_cube_json(cube_list)
# Summary of average words by color
print_by_color(cube_json_handle, rank_cards=False, full_oracle=full_oracle)
@ -229,9 +193,12 @@ cube_word_count(cube_json_handle, full_oracle=False)
cube_word_count(cube_json_handle, full_oracle=True)
################################################################################
# Calculate average of all Magic cards
# card_db_json_handle = create_all_cards_json()
# print_by_color(card_db_json_handle, rank_cards=True, full_oracle=full_oracle)
# cube_word_count(card_db_json_handle, full_oracle=full_oracle)
################################################################################
pass