#!/usr/bin/env python3 #-*- mode: Python;-*- import sys import os import time import random import statistics import functools import argparse import pprint import json VERSION = "{DEVELOPMENT}" if VERSION == "{DEVELOPMENT}": script_dir = '.' try: script_dir = os.path.dirname(os.path.realpath(__file__)) except: try: script_dir = os.path.dirname(os.path.abspath(sys.argv[0])) except: pass sys.path.append("%s/../lib" % script_dir) from nanownlib import * import nanownlib.storage from nanownlib.stats import boxTest,multiBoxTest,subsample,bootstrap,bootstrap2,trimean,midhinge,midhingeTest,samples2Distributions,samples2MeanDiffs from nanownlib.parallel import WorkerThreads parser = argparse.ArgumentParser( description="") #parser.add_argument('-c', dest='cases', type=str, default='{"short":10000,"long":1010000}', # help='JSON representation of echo timing cases. Default: {"short":10000,"long":1010000}') parser.add_argument('session_data', default=None, help='Database file storing session information') options = parser.parse_args() def trainBoxTest(db, unusual_case, greater, subseries_size): def trainAux(low,high,num_trials): estimator = functools.partial(multiBoxTest, {'low':low, 'high':high}, greater) estimates = bootstrap3(estimator, db, 'train', unusual_case, subseries_size, num_trials) null_estimates = bootstrap3(estimator, db, 'train_null', unusual_case, subseries_size, num_trials) bad_estimates = len([e for e in estimates if e != 1]) bad_null_estimates = len([e for e in null_estimates if e != 0]) false_negatives = 100.0*bad_estimates/num_trials false_positives = 100.0*bad_null_estimates/num_trials return false_positives,false_negatives #start = time.time() wt = WorkerThreads(2, trainAux) num_trials = 200 width = 1.0 performance = [] for low in range(0,50): wt.addJob(low, (low,low+width,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) #print(time.time()-start) num_trials = 200 lows = [p[1] for p in performance[0:5]] widths = [w/10.0 for w in range(5,65,5)] performance = [] for width in widths: false_positives = [] false_negatives = [] for low in lows: wt.addJob(low,(low,low+width,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors false_negatives.append(fn) false_positives.append(fp) #print(width, false_negatives) #print(width, false_positives) #performance.append(((statistics.mean(false_positives)+statistics.mean(false_negatives))/2.0, # width, statistics.mean(false_negatives), statistics.mean(false_positives))) performance.append((abs(statistics.mean(false_positives)-statistics.mean(false_negatives)), width, statistics.mean(false_negatives), statistics.mean(false_positives))) performance.sort() #pprint.pprint(performance) good_width = performance[0][1] #print("good_width:",good_width) num_trials = 500 performance = [] for low in lows: wt.addJob(low, (low,low+good_width,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) best_low = performance[0][1] #print("best_low:", best_low) num_trials = 500 widths = [good_width+(x/100.0) for x in range(-60,75,5) if good_width+(x/100.0) > 0.0] performance = [] for width in widths: wt.addJob(width, (best_low,best_low+width,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) best_width=performance[0][1] #print("best_width:",best_width) #print("final_performance:", performance[0][0]) wt.stop() params = json.dumps({"low":best_low,"high":best_low+best_width}) return {'algorithm':"boxtest", 'params':params, 'sample_size':subseries_size, 'num_trials':num_trials, 'trial_type':"train", 'false_positives':performance[0][3], 'false_negatives':performance[0][2]} def trainMidhinge(db, unusual_case, greater, subseries_size): def trainAux(distance, threshold, num_trials): estimator = functools.partial(midhingeTest, {'distance':distance,'threshold':threshold}, greater) estimates = bootstrap3(estimator, db, 'train', unusual_case, subseries_size, num_trials) null_estimates = bootstrap3(estimator, db, 'train_null', unusual_case, subseries_size, num_trials) bad_estimates = len([e for e in estimates if e != 1]) bad_null_estimates = len([e for e in null_estimates if e != 0]) false_negatives = 100.0*bad_estimates/num_trials false_positives = 100.0*bad_null_estimates/num_trials return false_positives,false_negatives #determine expected delta based on differences mean_diffs = [s['unusual_case']-s['other_cases'] for s in db.subseries('train', unusual_case)] threshold = trimean(mean_diffs)/2.0 #print("init_threshold:", threshold) wt = WorkerThreads(2, trainAux) num_trials = 500 performance = [] for distance in range(1,50): wt.addJob(distance, (distance,threshold,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) good_distance = performance[0][1] #print("good_distance:",good_distance) num_trials = 500 performance = [] for t in range(50,154,4): wt.addJob(threshold*(t/100.0), (good_distance,threshold*(t/100.0),num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) good_threshold = performance[0][1] #print("good_threshold:", good_threshold) num_trials = 500 performance = [] for d in [good_distance+s for s in range(-4,5) if good_distance+s > -1]: wt.addJob(d, (d,good_threshold,num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) best_distance = performance[0][1] #print("best_distance:",best_distance) num_trials = 500 performance = [] for t in range(90,111): wt.addJob(good_threshold*(t/100.0), (best_distance,good_threshold*(t/100.0),num_trials)) wt.wait() while not wt.resultq.empty(): job_id,errors = wt.resultq.get() fp,fn = errors performance.append(((fp+fn)/2.0, job_id, fn, fp)) performance.sort() #pprint.pprint(performance) best_threshold = performance[0][1] #print("best_threshold:", best_threshold) wt.stop() params = json.dumps({'distance':best_distance,'threshold':best_threshold}) return {'algorithm':"midhinge", 'params':params, 'sample_size':subseries_size, 'num_trials':num_trials, 'trial_type':"train", 'false_positives':performance[0][3], 'false_negatives':performance[0][2]} classifiers = {'boxtest':{'train':trainBoxTest, 'test':multiBoxTest}, 'midhinge':{'train':trainMidhinge, 'test':midhinge}} db = nanownlib.storage.db(options.session_data) import cProfile def trainClassifier(db, unusual_case, greater, trainer): threshold = 5.0 # in percent size = 4000 result = None while size < db.populationSize('train')/5: size = min(size*2, int(db.populationSize('train')/5)) result = trainer(db,unusual_case,greater,size) error = statistics.mean([result['false_positives'],result['false_negatives']]) print("subseries size: %d | error: %f | false_positives: %f | false_negatives: %f" % (size,error,result['false_positives'],result['false_negatives'])) if error < threshold: break if result != None: db.addClassifierResults(result) return result start = time.time() unusual_case,unusual_diff = findUnusualTestCase(db) greater = (unusual_diff > 0) print("unusual_case:", unusual_case) print("unusual_diff:", unusual_diff) end = time.time() print(":", end-start) for c,funcs in classifiers.items(): start = time.time() print("Training %s..." % c) result = trainClassifier(db, unusual_case, greater, funcs['train']) print("%s result:" % c) pprint.pprint(result) print("completed in:", time.time()-start) sys.exit(0) start = time.time() results = trainBoxTest(db, unusual_case, greater, 6000) #db.addClassifierResults(results) print("multi box test result:") pprint.pprint(results) print(":", time.time()-start)