17 Commits

Author SHA1 Message Date
70fb848e2a Import matplotlib in a good place 2021-10-29 20:15:45 +02:00
eb754a30e5 Draw graphs 2021-10-29 20:15:14 +02:00
f438ae6c79 Don't invert false positive and true negative. Adapt threshold for better results 2021-10-29 17:50:49 +02:00
9f161adb2f Print true/false positive/negative stats 2021-10-29 17:14:34 +02:00
d767e2029b Print true/false positive/negative stats 2021-10-29 17:00:07 +02:00
57d53a742f Comment code 2021-10-29 16:03:20 +02:00
6eba4961f3 Ensure good values for given similarity threshold 2021-10-29 14:38:57 +02:00
310b43483e Add option --progress to display the progress bar while generating permutations 2021-10-29 14:34:17 +02:00
78efd7fb2a Compute good values for band count and rows count according to given similarity threshold 2021-10-29 14:26:25 +02:00
1d5bd54b4f Compute true Jaccard similarity for candidate pairs 2021-10-28 08:09:56 +02:00
0d9ec8ec1a Implement LSH 2021-10-27 19:45:58 +02:00
769c62ee93 Keep true Jaccard similarity 2021-10-17 11:48:56 +02:00
677ad5e8b7 Compute signature matrix using NumPy 2021-10-17 11:27:45 +02:00
99fada5b52 Compute signature matrix using NumPy 2021-10-17 10:50:50 +02:00
d60653461a Parsing is working 2021-10-15 14:36:47 +02:00
ba7170e91c Simple parser 2021-10-08 15:13:52 +02:00
ad5f1fa58b Sample project 2021-10-08 14:53:40 +02:00