def load_flu_data():
path = os.path.dirname(__file__)
fn = './data/1000 flu cases no policy.tar.gz'
fn = os.path.join(path, fn)
experiments, outcomes = load_results(fn)
return experiments, outcomes
def load_eng_trans_data():
path = os.path.dirname(__file__)
fn = './data/eng_trans.tar.gz'
fn = os.path.join(path, fn)
experiments, outcomes = load_results(fn)
return experiments, outcomes
return experiments, outcomes
def load_scarcity_data():
path = os.path.dirname(__file__)
fn = './data/1000 runs scarcity.tar.gz'
fn = os.path.join(path, fn)
experiments, outcomes = load_results(fn)
return experiments, outcomes
return experiments, outcomes
def test_load_results(self):
# test for 1d
# test for 2d
# test for 3d
nr_experiments = 10000
experiments = np.recarray((nr_experiments,),
dtype=[('x', float), ('y', float)])
outcome_a = np.zeros((nr_experiments,1))
results = (experiments, {'a': outcome_a})
save_results(results, u'../data/test.tar.gz')
experiments, outcomes = load_results(u'../data/test.tar.gz')
logical = np.allclose(outcomes['a'],outcome_a)
os.remove('../data/test.tar.gz')
# if logical:
# ema_logging.info('1d loaded successfully')
nr_experiments = 1000
nr_timesteps = 100
nr_replications = 10
experiments = np.recarray((nr_experiments,),
dtype=[('x', float), ('y', float)])
outcome_a = np.zeros((nr_experiments,nr_timesteps,nr_replications))
results = (experiments, {'a': outcome_a})
save_results(results, u'../data/test.tar.gz')
experiments, outcomes = load_results(u'../data/test.tar.gz')
logical = np.allclose(outcomes['a'],outcome_a)
os.remove('../data/test.tar.gz')
def test_load_results(self):
# test for 1d
# test for 2d
# test for 3d
nr_experiments = 10000
experiments = np.recarray((nr_experiments, ),
dtype=[('x', float), ('y', float)])
outcome_a = np.zeros((nr_experiments, 1))
results = (experiments, {'a': outcome_a})
save_results(results, u'../data/test.tar.gz')
experiments, outcomes = load_results(u'../data/test.tar.gz')
logical = np.allclose(outcomes['a'], outcome_a)
os.remove('../data/test.tar.gz')
# if logical:
# ema_logging.info('1d loaded successfully')
nr_experiments = 1000
nr_timesteps = 100
nr_replications = 10
experiments = np.recarray((nr_experiments, ),
dtype=[('x', float), ('y', float)])
outcome_a = np.zeros((nr_experiments, nr_timesteps, nr_replications))
results = (experiments, {'a': outcome_a})
save_results(results, u'../data/test.tar.gz')
experiments, outcomes = load_results(u'../data/test.tar.gz')
logical = np.allclose(outcomes['a'], outcome_a)
os.remove('../data/test.tar.gz')
def classify(data):
#get the output for deceased population
result = data['deceased population region 1']
#make an empty array of length equal to number of cases
classes = np.zeros(result.shape[0])
#if deceased population is higher then 1.000.000 people, classify as 1
classes[result[:, -1] > 1000000] = 1
return classes
#load data
fn = r'./data/1000 flu cases.tar.gz'
results = load_results(fn)
experiments, results = results
#extract results for 1 policy
logical = experiments['policy'] == 'no policy'
new_experiments = experiments[ logical ]
new_results = {}
for key, value in results.items():
new_results[key] = value[logical]
results = (new_experiments, new_results)
#perform cart on modified results tuple
cart_alg = cart.setup_cart(results, classify, mass_min=0.05)
cart_alg.build_tree()
def periodDominance(ds):
Y = np.fft.rfft(ds)
n = len(Y)
powerSpect = np.abs(Y)**2
timeStep = 1
freq = np.fft.fftfreq(n, d=timeStep)
print len(freq), len(powerSpect)
for i in range(len(freq) / 2 + 1):
print freq[i], 1 / freq[i], powerSpect[i]
if __name__ == '__main__':
cases, results = util.load_results('PatternSet_Periodic.cpickle')
dataSeries = results.get('outcome')
ds1 = dataSeries[25]
ds2 = dataSeries[26]
print linearFit(ds1)
print quadraticFit(ds1)
print mean(ds1), variance(ds1), stdDev(ds1)
print autoCovariance(ds1, 0)
for k in range(31):
print k, autoCorrelation(ds1, k)
for k in range(31):
print k, crossCorrelation(ds1, ds2, k)
periodDominance(ds1)
default_flow = 2.178849944502783e7
def classify(outcomes):
ooi = 'throughput Rotterdam'
outcome = outcomes[ooi]
outcome = outcome / default_flow
classes = np.zeros(outcome.shape[0])
classes[outcome < 1] = 1
return classes
fn = r'./data/5000 runs WCM.tar.gz'
results = load_results(fn)
prim_obj = prim.setup_prim(results, classify, mass_min=0.05, threshold=0.75)
# let's find a first box
box1 = prim_obj.find_box()
# let's analyze the peeling trajectory
box1.show_ppt()
box1.show_tradeoff()
box1.write_ppt_to_stdout()
# based on the peeling trajectory, we pick entry number 44
box1.select(44)
''' Created on Jul 8, 2014 @author: [email protected] ''' import matplotlib.pyplot as plt from util import ema_logging from util.util import load_results from analysis.plotting import envelopes from analysis.plotting_util import KDE ema_logging.log_to_stderr(ema_logging.INFO) file_name = r'./data/1000 flu cases.tar.gz' results = load_results(file_name) # the plotting functions return the figure and a dict of axes fig, axes = envelopes(results, group_by='policy', density=KDE, fill=True) # we can access each of the axes and make changes for key, value in axes.iteritems(): # the key is the name of the outcome for the normal plot # and the name plus '_density' for the endstate distribution if key.endswith('_density'): value.set_xscale('log') plt.show()
.. codeauthor:: jhkwakkel <j.h.kwakkel (at) tudelft (dot) nl>
gonengyucel
'''
import matplotlib.pyplot as plt
from analysis.clusterer import cluster
from util import ema_logging
from util.util import load_results
ema_logging.log_to_stderr(ema_logging.INFO)
#load the data
data = load_results(r'..\examples\100 flu cases no policy.cPickle')
# specify the number of desired clusters
# note: the meaning of cValue is tied to the value for cMethod
cValue = 5
#perform cluster analysis
dist, clusteraloc, runlog, z = cluster(data=data,
outcome='deceased population region 1',
distance='gonenc',
interClusterDistance='complete',
cMethod = 'maxclust',
cValue = cValue,
plotDendrogram=False,
plotClusters=False,
groupPlot=False,
'''
Constructor
'''
self.no = cluster_no
self.indices = all_ds_indices
self.sample = int(sample_ds_index)
self.size = self.indices.size
self.runLogs = runLogs
self.distances = dist_clust
def error(self):
return self.sample
if __name__ == '__main__':
from util.util import load_results
results = load_results(
'../sandbox/cluster/datasets/PatternSet_Basics.cPickle')
distance, liste, obekler, kosulog, zet = cluster(results,
'outcome',
cMethod='distance',
cValue=1,
groupPlot=True,
plotDendrogram=False)
#clusters = np.array([3, 1, 2, 2, 1,2])
#dRow = np.array([1,2,3,6,2,1,0,3,9,6,2,1,3,2,1])
#samples = pick_cSamples(clusters, dRow)
#print "ornekler", samples
Created on 20 sep. 2011
.. codeauthor:: jhkwakkel <j.h.kwakkel (at) tudelft (dot) nl>
'''
import numpy as np
import matplotlib.pyplot as plt
from analysis.pairs_plotting import pairs_lines, pairs_scatter, pairs_density
from util.util import load_results
from util import ema_logging
ema_logging.log_to_stderr(level=ema_logging.DEFAULT_LEVEL)
# load the data
fh = r'.\data\1000 flu cases no policy.tar.gz'
experiments, outcomes = load_results(fh)
# transform the results to the required format
# that is, we want to know the max peak and the casualties at the end of the
# run
tr = {}
# get time and remove it from the dict
time = outcomes.pop('TIME')
for key, value in outcomes.items():
if key == 'deceased population region 1':
tr[key] = value[:, -1] #we want the end value
else:
# we want the maximum value of the peak
max_peak = np.max(value, axis=1)
Constructor
'''
self.no = cluster_no
self.indices = all_ds_indices
self.sample = int(sample_ds_index)
self.size = self.indices.size
self.runLogs = runLogs
self.distances = dist_clust
def error(self):
return self.sample
if __name__ == '__main__':
from util.util import load_results
results = load_results('../sandbox/cluster/datasets/PatternSet_Basics.cPickle')
distance, liste, obekler, kosulog, zet = cluster(results, 'outcome',cMethod='distance', cValue=1, groupPlot=True, plotDendrogram=False)
#clusters = np.array([3, 1, 2, 2, 1,2])
#dRow = np.array([1,2,3,6,2,1,0,3,9,6,2,1,3,2,1])
#samples = pick_cSamples(clusters, dRow)
#print "ornekler", samples
Created on 20 sep. 2011
.. codeauthor:: jhkwakkel <j.h.kwakkel (at) tudelft (dot) nl>
"""
import numpy as np
import matplotlib.pyplot as plt
from analysis.pairs_plotting import pairs_lines, pairs_scatter, pairs_density
from util.util import load_results
from util import ema_logging
ema_logging.log_to_stderr(level=ema_logging.DEFAULT_LEVEL)
# load the data
fh = r".\data\1000 flu cases no policy.tar.gz"
experiments, outcomes = load_results(fh)
# transform the results to the required format
# that is, we want to know the max peak and the casualties at the end of the
# run
tr = {}
# get time and remove it from the dict
time = outcomes.pop("TIME")
for key, value in outcomes.items():
if key == "deceased population region 1":
tr[key] = value[:, -1] # we want the end value
else:
# we want the maximum value of the peak
max_peak = np.max(value, axis=1)
return var
def periodDominance(ds):
Y = np.fft.rfft(ds)
n = len(Y)
powerSpect = np.abs(Y)**2
timeStep = 1
freq = np.fft.fftfreq(n, d=timeStep)
print len(freq), len(powerSpect)
for i in range(len(freq)/2+1):
print freq[i], 1/freq[i], powerSpect[i]
if __name__ == '__main__':
cases, results = util.load_results('PatternSet_Periodic.cpickle')
dataSeries = results.get('outcome')
ds1 = dataSeries[25]
ds2 = dataSeries[26]
print linearFit(ds1)
print quadraticFit(ds1)
print mean(ds1), variance(ds1), stdDev(ds1)
print autoCovariance(ds1,0)
for k in range(31):
print k,autoCorrelation(ds1,k)
for k in range(31):
print k, crossCorrelation(ds1,ds2,k)
periodDominance(ds1)