Update models for Ixalan; reorganize files

webapp/build_library.py

@@ -1,12 +1,21 @@
 import gzip
 import json
-
+import os
 import requests
 
+
+DIR_NAME = 'library'
+
 def _get(d, fields):
     return {k:d[k] for k in fields if k in d}
 
 if __name__ == '__main__':
+    try:
+        os.chdir(DIR_NAME)
+    except FileNotFoundError:
+        os.mkdir(DIR_NAME)
+        os.chdir(DIR_NAME)
+
     url = 'https://mtgjson.com/json/AllSetsArray.json.gz'
     resp = requests.get(url)
     sets = json.loads(gzip.decompress(resp.content).decode('utf8'))
@@ -28,9 +37,9 @@ def _get(d, fields):
             card_info['set'] = serie_info
             cards[card['name']] = card_info
 
-    fname = 'card_commander_library.json.gz'
+    fname = 'card_codex_library.json.gz'
     json.dump(list(cards.values()), gzip.open(fname, 'wt'))
 
-    fname = 'card_commander_cardlist.txt'
+    fname = 'card_codex_cardlist.txt'
     with open(fname, 'wt') as f:
         f.write('\n'.join(sorted(cards.keys())))

webapp/build_models.py

@@ -2,6 +2,7 @@
 import gzip
 import itertools
 import json
+import os
 import re
 from operator import itemgetter
 
@@ -10,20 +11,23 @@
 from gensim import corpora, models, similarities
 
 
+LIBRARY_DIR = 'library'
+MODEL_DIR = 'models'
+
+LIBRARY =    os.path.join(LIBRARY_DIR, 'card_codex_library.json.gz')
+DICTIONARY = os.path.join(MODEL_DIR,   'card_text_dictionary.dict')
+CORPUS =     os.path.join(MODEL_DIR,   'card_text_corpus.mm')
+INDEX =      os.path.join(MODEL_DIR,   'card_text_lsi.index')
+TFIDF =      os.path.join(MODEL_DIR,   'card_text_tfidf.model')
+LSI =        os.path.join(MODEL_DIR,   'card_text_lsi.model')
+
 #try:
 #    stopwords = set(nltk.corpus.stopwords.words('english'))
 #except LookupError:
 #    nltk.download('stopwords')
 stopwords = set(nltk.corpus.stopwords.words('english'))
 stemmer = nltk.stem.snowball.SnowballStemmer('english')
 
-LIBRARY = 'card_commander_library.json.gz'
-DICTIONARY = 'card_text_dictionary.dict'
-CORPUS = 'card_text_corpus.mm'
-INDEX = 'card_text_lsi.index'
-TFIDF = 'card_text_tfidf.model'
-LSI = 'card_text_lsi.model'
-
 
 class Similaritron(object):
     # TODO: num_topics is a magic number?
@@ -153,6 +157,9 @@ def tokenize(card):
 
 
 if __name__ == '__main__':
+    if not os.path.isdir(MODEL_DIR):
+        os.mkdir(MODEL_DIR)
+
     cards = json.load(gzip.open(LIBRARY, 'rt'))
 
     card_names = [c['name'] for c in cards]