Rework of halfnarp and fullnarp into a self contained repository. Still WIP

1 files changed, 50 insertions, 0 deletions

diff --git a/scripts/create_corr_array_pretalx.py b/scripts/create_corr_array_pretalx.py
new file mode 100644
index 0000000..dd9221d
--- /dev/null
+++ b/scripts/create_corr_array_pretalx.py
@@ -0,0 +1,50 @@
+#!venv/bin/python
+
+# convert halfnarp's output into the correlation array that can later
+# be served by halfnarp to show clusters of talks by your audience's
+# preferences
+#
+# Run this script with a single parameter, a file containing the output
+# of halfnarp2.py -e and place this script's output in a file that is
+# being served statically, e.g. corr_array_38c3.json
+
+import json
+import sys
+import itertools
+from collections import defaultdict
+
+# load in list of talk preferences, which is list of strings with talk ids
+with open(sys.argv[1]) as data_file:
+    corr = json.load(data_file)
+
+all_sums = dict(defaultdict())
+all_events = {}
+l = len(corr)
+
+for arr in corr:
+
+    for x in arr:
+        all_events[x] = 1
+
+    for x, y in itertools.combinations_with_replacement(sorted(arr), 2):
+        if x in all_sums.keys():
+            all_sums[x][y] = 1 + all_sums[x].get(y, 1)
+        else:
+            all_sums[x] = defaultdict()
+
+all_events = sorted(set(all_events))
+
+out_strings = defaultdict(str)
+
+for x, y in itertools.combinations(all_events, 2):
+    xyc = all_sums[x].get(y, 0)
+    xc  = all_sums[x].get(x, 0)
+    yc  = all_sums[y].get(y, 0)
+#   print (x, y, both, xcount, ycount)
+    xy_corr = 4.0 * l * xyc * xyc * (xc + yc) / (xc*xc*yc*yc) if xc * yc > 0 else 0
+    if xy_corr > 9:
+        xy_corr = 9
+    out_strings[x] += str(int(xy_corr))
+
+out_dict = { 'event_ids': all_events, 'event_corrs': list(out_strings.values()) }
+print (json.dumps(out_dict, separators=(',', ':')))