From 7226fc3b179a881e07f5bb968ced58611bd481ee Mon Sep 17 00:00:00 2001
From: Dan Niemitalo <dniemitalo@linnmar.k12.ia.us>
Date: Sun, 29 Nov 2020 13:27:14 -0600
Subject: [PATCH] Analyze keywords in cards.json files

Count unique keywords in sets and cubes. Output csv files included.
---
 analyze_keywords.py        |  37 +++++++++++-
 cube_keyword_frequency.csv |  25 ++++++++
 set_keyword_frequency.csv  | 120 +++++++++++++++++++++++++++++++++++++
 3 files changed, 179 insertions(+), 3 deletions(-)
 create mode 100644 cube_keyword_frequency.csv
 create mode 100644 set_keyword_frequency.csv

diff --git a/analyze_keywords.py b/analyze_keywords.py
index c03f82e..3890111 100644
--- a/analyze_keywords.py
+++ b/analyze_keywords.py
@@ -1,4 +1,5 @@
 import json
+import os
 
 
 def get_keywords(card):
@@ -39,6 +40,36 @@ def keyword_report(k_dict):
     print(f'\nTotal unique keywords: {len(k_dict)}')
 
 
-filename = f'scryfall/sets/ZNR.json'
-k_dict = keyword_count(filename)
-keyword_report(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)
+
+
+# ### Example use: count keywords in a list of cube.json files ###
+# output = open('cube_keyword_frequency.csv', 'w+')
+# all_cube_files = os.listdir('cubes')
+# output_file = open('cube_keyword_frequency.csv', 'w+')
+# output_file.write('Cube,Keywords\n')
+# for filename in all_cube_files:
+#     if filename.endswith('json'):
+#         k_dict = keyword_count('cubes/' + filename)
+#         output_file.write(f"{filename.strip('json')},{len(k_dict)}\n")
+#         print(filename, len(k_dict))
+# output_file.close()
+
+
+# ### Example use: find keyword count in each set ###
+# f = open('set_codes.txt')
+# codes = [line.strip() for line in f.readlines()]
+# output_file = open('set_keyword_frequency.csv', 'w+')
+# output_file.write('Set,Keywords\n')
+# for code in codes:
+#     if code == 'CON':
+#         code = 'CON_'
+#     filename = f'scryfall/sets/{code}.json'
+#     k_dict = keyword_count(filename)
+#     print(f'{code}: {len(k_dict)}')
+#     output_file.write(f'{code},{len(k_dict)}\n')
+# output_file.close()
+# f.close()
diff --git a/cube_keyword_frequency.csv b/cube_keyword_frequency.csv
new file mode 100644
index 0000000..60146bf
--- /dev/null
+++ b/cube_keyword_frequency.csv
@@ -0,0 +1,25 @@
+Cube,Keywords
+AlchemistsCrucible31.,62
+BeginnerCube.,17
+CasualChampionsCube.,71
+CoreResonanceBasic.,16
+CoreSetArchytas.,16
+CoreTheElegantCube.,70
+EvolvingWildsCube.,65
+GraveyardComboCube.,60
+Highball.,63
+kirblinxs_type_4_communal_stack.,85
+NoFreeLunches.,68
+NonblueGridMOriginsV3.,30
+OLDGraveyardComboCube.,64
+OPCube2020.,23
+penny_pincher_20inventors_fair.,57
+igh_a_cube.,66
+Simplicity.,21
+TheBlackCube.,74
+TheCoolSide.,62
+TheElegantCube.,107
+TheGameNightCube.,17
+TheGrandOdyssey.,17
+TheNoobCube.,26
+WheelofChange.,64
diff --git a/set_keyword_frequency.csv b/set_keyword_frequency.csv
new file mode 100644
index 0000000..f4e50d6
--- /dev/null
+++ b/set_keyword_frequency.csv
@@ -0,0 +1,120 @@
+Set,Keywords
+2ED,13
+3ED,14
+4ED,15
+5ED,18
+6ED,15
+7ED,14
+8ED,14
+9ED,17
+10E,22
+M10,19
+M11,19
+M12,17
+M13,21
+M14,19
+M15,20
+ORI,21
+M19,16
+M20,19
+M21,22
+POR,10
+P02,10
+PTK,10
+S99,9
+ARN,8
+ATQ,8
+LEG,17
+DRK,12
+FEM,9
+HML,11
+ICE,16
+ALL,13
+MIR,19
+VIS,18
+WTH,17
+TMP,18
+STH,10
+EXO,12
+USG,18
+ULG,12
+UDS,14
+MMQ,18
+NEM,12
+PCY,13
+INV,17
+PLS,10
+APC,11
+ODY,19
+TOR,16
+JUD,15
+ONS,15
+LGN,15
+SCG,20
+MRD,17
+DST,18
+5DN,20
+CHK,22
+BOK,15
+SOK,18
+RAV,22
+GPT,18
+DIS,17
+CSP,13
+TSP,26
+PLC,24
+FUT,50
+LRW,25
+MOR,22
+SHM,22
+EVE,24
+ALA,22
+CON_,25
+ARB,30
+ZEN,23
+WWK,16
+ROE,23
+SOM,21
+MBS,27
+NPH,22
+ISD,22
+DKA,23
+AVR,24
+RTR,23
+GTC,23
+DGM,30
+THS,24
+BNG,20
+JOU,22
+KTK,24
+FRF,21
+DTK,24
+BFZ,23
+OGW,22
+SOI,24
+EMN,25
+KLD,19
+AER,19
+AKH,23
+HOU,23
+XLN,22
+RIX,23
+DOM,22
+GRN,22
+RNA,23
+WAR,19
+ELD,20
+THB,20
+IKO,17
+ZNR,20
+MMA,38
+MM2,37
+EMA,28
+MM3,25
+IMA,29
+A25,31
+UMA,31
+2XM,52
+MH1,58
+CMR,42
+JMP,20