Split analyze_keywords.py into multiple scripts

analyze_all_set_keywords.py

@@ -0,0 +1,19 @@
+"""Find keyword count in each set.
+"""
+
+import keyword_stats
+
+if __name__ == '__main__':
+    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_stats.keyword_count(filename)
+        print(f'{code}: {len(k_dict)}')
+        output_file.write(f'{code},{len(k_dict)}\n')
+    output_file.close()
+    f.close()

analyze_cube_keywords.py

@@ -0,0 +1,11 @@
+"""Print a keyword report for a cards.json file
+"""
+
+import cube_json
+import keyword_stats
+
+if __name__ == '__main__':
+    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_stats.keyword_count(cube_json_filename)
+    keyword_stats.keyword_report(keyword_dict)

analyze_keywords.py

@@ -1,81 +0,0 @@
-import json
-import os
-
-import cube_json
-import word_count
-
-def get_keywords(card):
-    if 'keywords' in card.keys():
-        return card['keywords']
-    elif 'card_faces' in card:
-        keywords = []
-        for face in card['card_faces']:
-            if 'keywords' in face:
-                keywords += face['keywords']
-        return keywords
-    else:
-        return []
-
-
-def keyword_count(filename):
-    # json file must contain a list of Scryfall card objects
-    f = open(filename, encoding='utf8')
-    d = json.load(f)
-    keywords = []
-    for card in d:
-        keywords += get_keywords(card)
-    f.close()
-    k_unique = set(keywords)
-    k_dict = {}
-    for keyword in k_unique:
-        k_dict[keyword] = keywords.count(keyword)
-    return k_dict
-
-
-def keyword_report(k_dict):
-    k_lists = []
-    for keyword in k_dict:
-        k_lists += [[k_dict[keyword], keyword]]
-    k_lists = sorted(k_lists, reverse=True)
-    for n, keyword in k_lists:
-        print(keyword, n)
-    print(f'\nTotal unique keywords: {len(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 ###
-    # 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()
-
-    pass

analyze_multiple_cubes_keywords.py

@@ -0,0 +1,20 @@
+"""Count keywords in a list of cube.json files.
+"""
+import json
+import os
+
+import keyword_stats
+
+
+if __name__ == '__main__':
+    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_stats.keyword_count('cubes/' + filename)
+            output_file.write(f"{filename.strip('json')},{len(k_dict)}\n")
+            print(filename, len(k_dict))
+    output_file.close()
+

keyword_stats.py

@@ -0,0 +1,38 @@
+import json
+
+def get_keywords(card):
+    if 'keywords' in card.keys():
+        return card['keywords']
+    elif 'card_faces' in card:
+        keywords = []
+        for face in card['card_faces']:
+            if 'keywords' in face:
+                keywords += face['keywords']
+        return keywords
+    else:
+        return []
+
+
+def keyword_count(filename):
+    # json file must contain a list of Scryfall card objects
+    f = open(filename, encoding='utf8')
+    d = json.load(f)
+    keywords = []
+    for card in d:
+        keywords += get_keywords(card)
+    f.close()
+    k_unique = set(keywords)
+    k_dict = {}
+    for keyword in k_unique:
+        k_dict[keyword] = keywords.count(keyword)
+    return k_dict
+
+
+def keyword_report(k_dict):
+    k_lists = []
+    for keyword in k_dict:
+        k_lists += [[k_dict[keyword], keyword]]
+    k_lists = sorted(k_lists, reverse=True)
+    for n, keyword in k_lists:
+        print(keyword, n)
+    print(f'\nTotal unique keywords: {len(k_dict)}')