From 6b80e49d2bc29080c87d54be2313c16031491db4 Mon Sep 17 00:00:00 2001
From: Bill Zorn <billzorn@cs.washington.edu>
Date: Tue, 17 Nov 2015 00:47:18 -0800
Subject: [PATCH] added some data processing scripts

---
 scripts/distances.py | 81 ++++++++++++++++++++++++++++++++++++++++++++
 scripts/sum.py       | 58 +++++++++++++++++++++++++++++++
 2 files changed, 139 insertions(+)
 create mode 100755 scripts/distances.py
 create mode 100755 scripts/sum.py

diff --git a/scripts/distances.py b/scripts/distances.py
new file mode 100755
index 0000000..4c0fd7c
--- /dev/null
+++ b/scripts/distances.py
@@ -0,0 +1,81 @@
+#!/usr/bin/env python
+import sys
+import os
+
+libdir = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../lib')
+sys.path.append(libdir)
+import utils
+import jdecode
+from namediff import Namediff
+from cbow import CBOW
+
+def main(fname, oname, verbose = True, parallel = True):
+    # may need to set special arguments here
+    cards = jdecode.mtg_open_file(fname, verbose=verbose)
+
+    # this could reasonably be some separate function
+    # might make sense to merge cbow and namediff and have this be the main interface
+    namediff = Namediff()
+    cbow = CBOW()
+
+    if verbose:
+        print 'Computing nearest names...'
+    if parallel:
+        nearest_names = namediff.nearest_par(map(lambda c: c.name, cards), n=1)
+    else:
+        nearest_names = [namediff.nearest(c.name, n=1) for c in cards]
+
+    if verbose:
+        print 'Computing nearest cards...'
+    if parallel:
+        nearest_cards = cbow.nearest_par(cards, n=1)
+    else:
+        nearest_cards = [cbow.nearest(c, n=1) for c in cards]
+
+    for i in range(0, len(cards)):
+        cards[i].nearest_names = nearest_names[i]
+        cards[i].nearest_cards = nearest_cards[i]
+
+    # # unfortunately this takes ~30 hours on 8 cores for a 10MB dump
+    # if verbose:
+    #     print 'Computing nearest encodings by text edit distance...'
+    # if parallel:
+    #     nearest_cards_text = namediff.nearest_card_par(cards, n=1)
+    # else:
+    #     nearest_cards_text = [namediff.nearest_card(c, n=1) for c in cards]
+
+    if verbose:
+        print '...Done.'
+
+    # write to a file to store the data, this is a terribly long computation
+    # we could also just store this same info in the cards themselves as more fields...
+    sep = '|'
+    with open(oname, 'w') as ofile:
+        for i in range(0, len(cards)):
+            card = cards[i]
+            ostr = str(i) + sep + card.name + sep
+            ndist, _ = card.nearest_names[0]
+            ostr += str(ndist) + sep
+            cdist, _ = card.nearest_cards[0]
+            ostr += str(cdist) + '\n'
+            # tdist, _ = nearest_cards_text[i][0]
+            # ostr += str(tdist) + '\n'
+            ofile.write(ostr.encode('utf-8'))
+
+if __name__ == '__main__':
+    
+    import argparse
+    parser = argparse.ArgumentParser()
+    
+    parser.add_argument('infile', #nargs='?'. default=None,
+                        help='encoded card file or json corpus to process')
+    parser.add_argument('outfile', #nargs='?', default=None,
+                        help='name of output file, will be overwritten')
+    parser.add_argument('-v', '--verbose', action='store_true', 
+                        help='verbose output')
+    parser.add_argument('-p', '--parallel', action='store_true', 
+                        help='run in parallel on all cores')
+
+    args = parser.parse_args()
+    main(args.infile, args.outfile, verbose=args.verbose, parallel=args.parallel)
+    exit(0)
diff --git a/scripts/sum.py b/scripts/sum.py
new file mode 100755
index 0000000..947b39d
--- /dev/null
+++ b/scripts/sum.py
@@ -0,0 +1,58 @@
+#!/usr/bin/env python
+import sys
+import os
+
+libdir = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../lib')
+sys.path.append(libdir)
+
+def main(fname):
+    with open(fname, 'rt') as f:
+        text = f.read()
+    
+    cardstats = text.split('\n')
+    nonempty = 0
+    name_avg = 0
+    name_dupes = 0
+    card_avg = 0
+    card_dupes = 0
+
+    for c in cardstats:
+        fields = c.split('|')
+        if len(fields) < 4:
+            continue
+        nonempty += 1
+        idx = int(fields[0])
+        name = str(fields[1])
+        ndist = float(fields[2])
+        cdist = float(fields[3])
+
+        name_avg += ndist
+        if ndist == 1.0:
+            name_dupes += 1
+        card_avg += cdist
+        if cdist == 1.0:
+            card_dupes += 1
+
+    name_avg = name_avg / float(nonempty)
+    card_avg = card_avg / float(nonempty)
+    
+    print str(nonempty) + ' cards'
+    print '-- names --'
+    print 'avg distance:   ' + str(name_avg)
+    print 'num duplicates: ' + str(name_dupes)
+    print '-- cards --'
+    print 'avg distance:   ' + str(card_avg)
+    print 'num duplicates: ' + str(card_dupes)
+    print '----'
+
+if __name__ == '__main__':
+    
+    import argparse
+    parser = argparse.ArgumentParser()
+    
+    parser.add_argument('infile', #nargs='?'. default=None,
+                        help='data file to process')
+
+    args = parser.parse_args()
+    main(args.infile)
+    exit(0)