pychronicles 0.0.3

A package for chronicle recognition

PyChronicle package

A chronicle is a specification of the complex temporal behaviors as a temporal constraint graph. It can be used to recognize complex behaviors in sequence the temporal events.

A chronicle is a multiset of events and a set of temporal constraints specifying that occurrences of pairs of events must occurs within a given temporal interval.

The package implements the model of chronicles and an efficient algorithm to recognize it.

Requirements

Use pip install -r requirements.txt to install requirements

• numpy
• scipy
• lazr.restfulclient
• larz.uri

LAZR is used to instantiate chronicles from CRS files (with simple grammar).

Usage

Example of usage:

from pychronicles import *
#define a sequence of events
seq = [3,4,'b','a','a',1,3,'coucou','b','coucou',5,'coucou',5]

#define a chronicle
c=Chronicle()
c.add_event(0,'b')
c.add_event(1,1)
c.add_constraint(1,3, (3,45))
print(c)

#recognize the chronicle in the sequence
occs=c.recognize(seq)
print("occurrences: "+str(occs))

It is possible to specify chronicles using the CRS format. The following code illustrate the syntax for specifying a chronicle in this format.

chronicle C27_sub_0[]()
{
    event(Event_Type1[], t006)
    event(Event_Type1[], t004)
    event(Event_Type2[], t002)
    event(Event_Type3[], t001)

    t004-t006 in [17,25]
    t006-t002 in [-16,-10]
    t002-t001 in [14,29]
    t004-t001 in [27,35]
}

Authorship

Author: Thomas Guyet Institution: AGROCAMPUS-OUEST/IRISA date:10/2019