forgejoadmin/cubescripts
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Make word_count.py a bit more readable and togglable

Browse source
This commit is contained in:
henriquenakashima 2020-11-23 21:03:00 -05:00
parent d1f6771c92
commit 55dd3e24ea
1 changed files with 34 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

57
word_count.py
View file

@ -71,6 +71,7 @@ def create_cube_json(cards):
string_data = json.dumps(cube_data) string_data = json.dumps(cube_data)
f_cube_json.write(string_data) f_cube_json.write(string_data)
f_cube_json.close() f_cube_json.close()
return TEMP_JSON
def wc_fo(text): def wc_fo(text):
@ -89,8 +90,8 @@ def wc_o(text):
return len(text.split()) return len(text.split())
def word_count(card, full=False): def word_count(card, *, full_oracle):
if full: if full_oracle:
wc = wc_fo wc = wc_fo
else: else:
wc = wc_o wc = wc_o
@ -105,15 +106,15 @@ def word_count(card, full=False):
return wc(text) return wc(text)
def cube_word_count(filename, full=False): def cube_word_count(filename, *, full_oracle):
with open(filename, encoding='utf8') as f: with open(filename, encoding='utf8') as f:
d = json.load(f) d = json.load(f)
wc = [] wc = []
for card in d: for card in d:
words = word_count(card, full) words = word_count(card, full_oracle=full_oracle)
wc += [words] wc += [words]
mean = sum(wc) / len(wc) mean = sum(wc) / len(wc)
if full: if full_oracle:
metric = 'Avg Words/Card (full text)' metric = 'Avg Words/Card (full text)'
else: else:
metric = 'Avg Words/Card (no reminders)' metric = 'Avg Words/Card (no reminders)'
@ -131,17 +132,6 @@ def duplicate_count(filename):
print(f"{len(unique)} unique of {len(d)} total cards") print(f"{len(unique)} unique of {len(d)} total cards")
def print_wordy_cards(filename, n):
# List cards with n or more words
with open(filename, encoding='utf8') as f:
d = json.load(f)
for card in d:
words = word_count(card) # change to word_count(card, True) to count full oracle text
if words >= n:
print(f"{words} words: {card['name']}")
# print(get_text(card) + "\n")
WHEEL = str.maketrans('WUBRG', '01234') WHEEL = str.maketrans('WUBRG', '01234')
@ -149,12 +139,12 @@ def wheel_order(colors):
return colors.translate(WHEEL) return colors.translate(WHEEL)
def print_by_color(filename): def print_by_color(filename, *, rank_cards, full_oracle):
cards_by_color_identity = defaultdict(list) cards_by_color_identity = defaultdict(list)
with open(filename, encoding='utf8') as f: with open(filename, encoding='utf8') as f:
d = json.load(f) d = json.load(f)
for card in d: for card in d:
words = word_count(card) # change to word_count(card, True) to count full oracle text words = word_count(card, full_oracle=full_oracle)
if 'Land' in card['type_line']: if 'Land' in card['type_line']:
identity = 'Non-basic land' identity = 'Non-basic land'
else: else:
@ -168,6 +158,7 @@ def print_by_color(filename):
average_words = total_words / card_count average_words = total_words / card_count
identity_name = 'Non-land colorless' if not identity else identity identity_name = 'Non-land colorless' if not identity else identity
print(f"{identity_name }: average {average_words:.2f} [of {card_count} cards]") print(f"{identity_name }: average {average_words:.2f} [of {card_count} cards]")
if rank_cards:
for card_name, card_words in sorted(card_tuples, key=lambda t: t[1], reverse=True): for card_name, card_words in sorted(card_tuples, key=lambda t: t[1], reverse=True):
print(f'{card_name}: {card_words}') print(f'{card_name}: {card_words}')
print() print()
@ -183,15 +174,29 @@ def get_text(card):
text += face['oracle_text'] + ' ' text += face['oracle_text'] + ' '
return text return text
################################################################################
# Use either line:
cube_name = 'TheElegantCube20201123' # Name must match the *.txt card list file # 1. If you have a .txt of your cube
#cube_list = load_cube_from_txt(cube_name + '.txt') # cube_list = load_cube_from_txt('YourCubeHere.txt')
cube_list = load_cube_from_csv(f'{cube_name}.csv', {'core'}) # 2. If you have a .csv of your cube
# cube_list = load_cube_from_csv('YourCubeHere.csv')
create_cube_json(cube_list) # Comment this out if cubename.json is already created # 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('TheElegantCube20201123.csv', {'core'})
################################################################################
# print_wordy_cards(TEMP_JSON, 0) cube_json_handle = create_cube_json(cube_list)
print_by_color(TEMP_JSON)
cube_word_count(TEMP_JSON) # Average words excluding reminder text # Summary of average words by color
cube_word_count(TEMP_JSON, True) # Average words in full oracle text print_by_color(cube_json_handle, rank_cards=False, full_oracle=True)
# Individual cards by color, ranked by word count
print_by_color(cube_json_handle, rank_cards=True, full_oracle=True)
# Average words excluding reminder text
cube_word_count(cube_json_handle, full_oracle=False)
# Average words in full oracle text
cube_word_count(cube_json_handle, full_oracle=True)