sam/pyFTS
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases Wiki Activity

- SeasonalIndexer on sfts

Browse Source
This commit is contained in:
Petrônio Cândido de Lima e Silva 2017-05-21 18:04:10 -03:00
parent d1b18ef5c4
commit 8efd7c38d8
5 changed files with 68 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
benchmarks/distributed_benchmarks.py
View File

@ -438,6 +438,9 @@ def run_ahead(mfts, partitioner, train_data, test_data, steps, resolution, windo
if transformation is not None:
mfts.appendTransformation(transformation)
if mfts.has_seasonality:
mfts.indexer = indexer
try:
_start = time.time()
mfts.train(train_data, partitioner.sets, order=mfts.order)
@ -553,7 +556,7 @@ def ahead_sliding_window(data, windowsize, steps, resolution, train=0.8, inc=0.1
continue
else:
benchmarks_only[m.shortname] = m
job = cluster.submit(m, data_train_fs, train, test, steps, resolution, ct, transformation)
job = cluster.submit(m, data_train_fs, train, test, steps, resolution, ct, transformation, indexer)
job.id = id # associate an ID to identify jobs (if needed later)
jobs.append(job)

1
fts.py
View File

@ -36,6 +36,7 @@ class FTS(object):
self.partitioner = None
self.auto_update = False
self.benchmark_only = False
self.indexer = None
def fuzzy(self, data):
"""

29
models/seasonal/SeasonalIndexer.py
View File

@ -30,23 +30,26 @@ class LinearSeasonalIndexer(SeasonalIndexer):
self.seasons = seasons
def get_season_of_data(self,data):
return self.get_season_by_index(np.arange(0,len(data)))
return self.get_season_by_index(np.arange(0, len(data)).tolist())
def get_season_by_index(self,index):
ret = []
for ix in index:
if self.num_seasons == 1:
season = ix % self.seasons
else:
season = []
for seasonality in self.seasons:
print("S ", seasonality)
tmp = ix // seasonality
print("T ", tmp)
season.append(tmp)
#season.append(rest)
if not isinstance(index, (list, np.ndarray)):
season = (index % self.seasons[0]) + 1
else:
for ix in index:
if self.num_seasons == 1:
season = (ix % self.seasons[0])
else:
season = []
for seasonality in self.seasons:
#print("S ", seasonality)
tmp = ix // seasonality
#print("T ", tmp)
season.append(tmp)
#season.append(rest)
ret.append(season)
ret.append(season)
return ret

29
sfts.py
View File

@ -46,28 +46,24 @@ class SeasonalFTS(fts.FTS):
self.is_high_order = False
def generateFLRG(self, flrs):
flrgs = []
season = 1
for flr in flrs:
flrgs = {}
for ct, flr in enumerate(flrs, start=1):
if len(flrgs) < self.seasonality:
flrgs.append(SeasonalFLRG(season))
season = self.indexer.get_season_by_index(ct)[0]
if season not in flrgs:
flrgs[season] = SeasonalFLRG(season)
#print(season)
flrgs[season-1].append(flr.RHS)
season = (season + 1) % (self.seasonality + 1)
if season == 0: season = 1
flrgs[season].append(flr.RHS)
return (flrgs)
def train(self, data, sets, order=1,parameters=12):
def train(self, data, sets, order=1, parameters=None):
self.sets = sets
self.seasonality = parameters
ndata = self.doTransformations(data)
tmpdata = FuzzySet.fuzzySeries(ndata, sets)
flrs = FLR.generateRecurrentFLRs(tmpdata)
flrs = FLR.generateNonRecurrentFLRs(tmpdata)
self.flrgs = self.generateFLRG(flrs)
def forecast(self, data, **kwargs):
@ -79,13 +75,10 @@ class SeasonalFTS(fts.FTS):
ret = []
for k in np.arange(1, l):
#flrg = self.flrgs[ndata[k]]
season = (k + 1) % (self.seasonality + 1)
season = self.indexer.get_season_by_index(k)[0]
#print(season)
flrg = self.flrgs[season-1]
flrg = self.flrgs[season]
mp = self.getMidpoints(flrg)

58
tests/general.py
View File

@ -19,15 +19,15 @@ from numpy import random
os.chdir("/home/petronio/dados/Dropbox/Doutorado/Codigos/")
enrollments = pd.read_csv("DataSets/Enrollments.csv", sep=";")
enrollments = np.array(enrollments["Enrollments"])
diff = Transformations.Differential(1)
"""
DATASETS
"""
#enrollments = pd.read_csv("DataSets/Enrollments.csv", sep=";")
#enrollments = np.array(enrollments["Enrollments"])
#passengers = pd.read_csv("DataSets/AirPassengers.csv", sep=",")
#passengers = np.array(passengers["Passengers"])
@ -37,8 +37,8 @@ DATASETS
#gauss = random.normal(0,1.0,5000)
#gauss_teste = random.normal(0,1.0,400)
taiexpd = pd.read_csv("DataSets/TAIEX.csv", sep=",")
taiex = np.array(taiexpd["avg"][:5000])
#taiexpd = pd.read_csv("DataSets/TAIEX.csv", sep=",")
#taiex = np.array(taiexpd["avg"][:5000])
#nasdaqpd = pd.read_csv("DataSets/NASDAQ_IXIC.csv", sep=",")
#nasdaq = np.array(nasdaqpd["avg"][0:5000])
@ -52,9 +52,9 @@ taiex = np.array(taiexpd["avg"][:5000])
#sonda = np.array(sondapd["glo_avg"])
#del(sondapd)
#bestpd = pd.read_csv("DataSets/BEST_TAVG.csv", sep=";")
#best = np.array(bestpd["Anomaly"])
#del(bestpd)
bestpd = pd.read_csv("DataSets/BEST_TAVG.csv", sep=";")
best = np.array(bestpd["Anomaly"])
del(bestpd)
#print(lag)
#print(a)
@ -135,36 +135,50 @@ bchmk.interval_sliding_window(sp500, 2000, train=0.8, inc=0.2, #models=[yu.Weigh
dump=True, save=True, file="experiments/sp500_analytic_diff.csv",
nodes=['192.168.0.103', '192.168.0.106', '192.168.0.108', '192.168.0.109']) #, depends=[hofts, ifts])
#"""
"""
bchmk.ahead_sliding_window(taiex, 2000, steps=10, resolution=100, train=0.8, inc=0.1,
"""
bchmk.ahead_sliding_window(best, 4000, steps=10, resolution=100, train=0.8, inc=0.5,
partitioners=[Grid.GridPartitioner],
partitions= np.arange(10,200,step=10),
dump=True, save=True, file="experiments/taiex_ahead_analytic.csv",
nodes=['192.168.0.105', '192.168.0.106', '192.168.0.108', '192.168.0.109']) #, depends=[hofts, ifts])
dump=True, save=True, file="experiments/best_ahead_analytic.csv",
nodes=['192.168.0.106', '192.168.0.108', '192.168.0.109']) #, depends=[hofts, ifts])
bchmk.ahead_sliding_window(taiex, 2000, steps=10, resolution=100, train=0.8, inc=0.1,
bchmk.ahead_sliding_window(best, 4000, steps=10, resolution=100, train=0.8, inc=0.5,
partitioners=[Grid.GridPartitioner],
partitions= np.arange(3,20,step=2), transformation=diff,
dump=True, save=True, file="experiments/taiex_ahead_analytic_diff.csv",
nodes=['192.168.0.105', '192.168.0.106', '192.168.0.108', '192.168.0.109']) #, depends=[hofts, ifts])
dump=True, save=True, file="experiments/best_ahead_analytic_diff.csv",
nodes=['192.168.0.106', '192.168.0.108', '192.168.0.109']) #, depends=[hofts, ifts])
"""
from pyFTS.partitioners import Grid
from pyFTS import pwfts
from pyFTS.models.seasonal import SeasonalIndexer
from pyFTS import sfts
ix = SeasonalIndexer.LinearSeasonalIndexer([10])
#print(ix.get_season_of_data(best[:2000]))
#print(ix.get_season_by_index(45))
diff = Transformations.Differential(1)
fs = Grid.GridPartitioner(taiex[:2000], 10, transformation=diff)
tmp = pwfts.ProbabilisticWeightedFTS("")
fs = Grid.GridPartitioner(best[:2000], 10, transformation=diff)
tmp = sfts.SeasonalFTS("")
tmp.indexer = ix
tmp.appendTransformation(diff)
tmp.train(taiex[:1600], fs.sets, order=1)
#tmp = pwfts.ProbabilisticWeightedFTS("")
x = tmp.forecastInterval(taiex[1600:1610])
#tmp.appendTransformation(diff)
print(taiex[1600:1610])
tmp.train(best[:1600], fs.sets, order=1)
x = tmp.forecast(best[1600:1610])
#print(taiex[1600:1610])
print(x)
#"""