def print_point_statistics(data, models, externalmodels = None, externalforecasts = None, indexers=None):
"""
Run point benchmarks on given models and data and print the results
:param data: test data
:param models: a list of FTS models to benchmark
:param externalmodels: a list with benchmark models (façades for other methods)
:param externalforecasts:
:param indexers:
:return:
"""
ret = "Model & Order & RMSE & SMAPE & Theil's U \\\\ \n"
for count,model in enumerate(models,start=0):
_rmse, _smape, _u = Measures.get_point_statistics(data, model, indexers)
ret += model.shortname + " & "
ret += str(model.order) + " & "
ret += str(_rmse) + " & "
ret += str(_smape)+ " & "
ret += str(_u)
#ret += str(round(Measures.TheilsInequality(np.array(data[fts.order:]), np.array(forecasts[:-1])), 4))
ret += " \\\\ \n"
if externalmodels is not None:
l = len(externalmodels)
for k in np.arange(0,l):
ret += externalmodels[k] + " & "
ret += " 1 & "
ret += str(round(Measures.rmse(data, externalforecasts[k][:-1]), 2)) + " & "
ret += str(round(Measures.smape(data, externalforecasts[k][:-1]), 2))+ " & "
ret += str(round(Measures.UStatistic(data, externalforecasts[k][:-1]), 2))
ret += " \\\\ \n"
print(ret)
def print_point_statistics(data,
models,
externalmodels=None,
externalforecasts=None,
indexers=None):
ret = "Model & Order & RMSE & SMAPE & Theil's U \\\\ \n"
for count, model in enumerate(models, start=0):
_rmse, _smape, _u = Measures.get_point_statistics(
data, model, indexers)
ret += model.shortname + " & "
ret += str(model.order) + " & "
ret += str(_rmse) + " & "
ret += str(_smape) + " & "
ret += str(_u)
#ret += str(round(Measures.TheilsInequality(np.array(data[fts.order:]), np.array(forecasts[:-1])), 4))
ret += " \\\\ \n"
if externalmodels is not None:
l = len(externalmodels)
for k in np.arange(0, l):
ret += externalmodels[k] + " & "
ret += " 1 & "
ret += str(round(Measures.rmse(data, externalforecasts[k][:-1]),
2)) + " & "
ret += str(
round(Measures.smape(data, externalforecasts[k][:-1]),
2)) + " & "
ret += str(
round(Measures.UStatistic(data, externalforecasts[k][:-1]), 2))
ret += " \\\\ \n"
print(ret)
def cluster_method(individual, train, test):
from pyFTS.common import Util, Membership
from pyFTS.models import hofts
from pyFTS.partitioners import Grid, Entropy
from pyFTS.benchmarks import Measures
if individual['mf'] == 1:
mf = Membership.trimf
elif individual['mf'] == 2:
mf = Membership.trapmf
elif individual['mf'] == 3 and individual['partitioner'] != 2:
mf = Membership.gaussmf
else:
mf = Membership.trimf
if individual['partitioner'] == 1:
partitioner = Grid.GridPartitioner(data=train, npart=individual['npart'], func=mf)
elif individual['partitioner'] == 2:
npart = individual['npart'] if individual['npart'] > 10 else 10
partitioner = Entropy.EntropyPartitioner(data=train, npart=npart, func=mf)
model = hofts.WeightedHighOrderFTS(partitioner=partitioner,
lags=individual['lags'],
alpha_cut=individual['alpha'],
order=individual['order'])
model.fit(train)
rmse, mape, u = Measures.get_point_statistics(test, model)
size = len(model)
return individual, rmse, size, mape, u
def evaluation1(dataset, individual):
from pyFTS.common import Util
from pyFTS.benchmarks import Measures
try:
results = []
lengths = []
for count, train, test in Util.sliding_window(dataset,
800,
train=.8,
inc=.25):
model = phenotype(individual, train)
if model is None:
return (None)
rmse, _, _ = Measures.get_point_statistics(test, model)
lengths.append(len(model))
results.append(rmse)
_lags = sum(model.lags) * 100
rmse = np.nansum(
[.6 * np.nanmean(results), .4 * np.nanstd(results)])
len_lags = np.nansum([.4 * np.nanmean(lengths), .6 * _lags])
return len_lags, rmse
except Exception as ex:
print("EXCEPTION!", str(ex), str(individual))
return np.inf
from pyFTS.benchmarks import Measures
from pyFTS.partitioners import Grid, Entropy
from pyFTS.models import hofts
from pyFTS.common import Membership
x = [k for k in np.arange(-2 * np.pi, 2 * np.pi, 0.1)]
y = [np.sin(k) for k in x]
rows = []
fig, ax = plt.subplots(nrows=1, ncols=1, figsize=[15, 5])
ax.plot(y, label='Original', color='black')
for npart in np.arange(5, 35, 5):
part = Grid.GridPartitioner(data=y, npart=npart)
model = hofts.HighOrderFTS(order=1, partitioner=part)
model.fit(y)
forecasts = model.predict(y)
ax.plot(forecasts[:-1], label=str(npart) + " partitions")
rmse, mape, u = Measures.get_point_statistics(y, model)
rows.append([npart, rmse, mape, u])
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles, labels, loc=2, bbox_to_anchor=(1, 1))
df = pd.DataFrame(rows, columns=['Partitions', 'RMSE', 'MAPE', 'U'])
def run_point(mfts,
partitioner,
train_data,
test_data,
window_key=None,
**kwargs):
"""
Point forecast benchmark function to be executed on cluster nodes
:param mfts: FTS model
:param partitioner: Universe of Discourse partitioner
:param train_data: data used to train the model
:param test_data: ata used to test the model
:param window_key: id of the sliding window
:param transformation: data transformation
:param indexer: seasonal indexer
:return: a dictionary with the benchmark results
"""
import time
from pyFTS.models import yu, chen, hofts, pwfts, ismailefendi, sadaei, song, cheng, hwang
from pyFTS.partitioners import Grid, Entropy, FCM
from pyFTS.benchmarks import Measures, naive, arima, quantreg
from pyFTS.common import Transformations
tmp = [
song.ConventionalFTS, chen.ConventionalFTS, yu.WeightedFTS,
ismailefendi.ImprovedWeightedFTS, cheng.TrendWeightedFTS,
sadaei.ExponentialyWeightedFTS, hofts.HighOrderFTS, hwang.HighOrderFTS,
pwfts.ProbabilisticWeightedFTS
]
tmp2 = [
Grid.GridPartitioner, Entropy.EntropyPartitioner, FCM.FCMPartitioner
]
tmp4 = [naive.Naive, arima.ARIMA, quantreg.QuantileRegression]
tmp3 = [Measures.get_point_statistics]
tmp5 = [Transformations.Differential]
indexer = kwargs.get('indexer', None)
steps_ahead = kwargs.get('steps_ahead', 1)
method = kwargs.get('method', None)
if mfts.benchmark_only:
_key = mfts.shortname + str(
mfts.order if mfts.order is not None else "")
else:
pttr = str(partitioner.__module__).split('.')[-1]
_key = mfts.shortname + " n = " + str(
mfts.order) + " " + pttr + " q = " + str(partitioner.partitions)
mfts.partitioner = partitioner
mfts.append_transformation(partitioner.transformation)
_key += str(steps_ahead)
_key += str(method) if method is not None else ""
_start = time.time()
mfts.fit(train_data, **kwargs)
_end = time.time()
times = _end - _start
_start = time.time()
_rmse, _smape, _u = Measures.get_point_statistics(test_data, mfts,
**kwargs)
_end = time.time()
times += _end - _start
ret = {
'key': _key,
'obj': mfts,
'rmse': _rmse,
'smape': _smape,
'u': _u,
'time': times,
'window': window_key,
'steps': steps_ahead,
'method': method
}
return ret
from pyFTS.data import TAIEX, SP500, NASDAQ, Malaysia
dataset = Malaysia.get_data('temperature')[:1000]
p = Grid.GridPartitioner(data=dataset, npart=20)
print(p)
model = hofts.WeightedHighOrderFTS(partitioner=p, order=2)
model.fit(dataset) #[22, 22, 23, 23, 24])
print(model)
Measures.get_point_statistics(dataset, model)
'''
#dataset = SP500.get_data()[11500:16000]
#dataset = NASDAQ.get_data()
#print(len(dataset))
bchmk.sliding_window_benchmarks(dataset, 1000, train=0.8, inc=0.2,
methods=[chen.ConventionalFTS], #[pwfts.ProbabilisticWeightedFTS],
benchmark_models=False,
transformations=[None],
#orders=[1, 2, 3],
partitions=np.arange(10, 100, 2),
progress=False, type="point",
#steps_ahead=[1,2,4,6,8,10],
distributed=False, nodes=['192.168.0.110', '192.168.0.107', '192.168.0.106'],
model2 = pwfts.ProbabilisticWeightedFTS(partitioner=fs, lags=[1, 2])
#model2.append_transformation(tdiff)
model2.shortname = "2"
#model = pwfts.ProbabilisticWeightedFTS(partitioner=fs, order=2)# lags=[1,2])
model1.fit(train)
model2.fit(train)
#print(model1)
#print(model2)
for model in [model1, model2]:
#forecasts = model.predict(test)
print(model.shortname)
print(Measures.get_point_statistics(test, model))
#handles, labels = ax.get_legend_handles_labels()
#ax.legend(handles, labels, loc=2, bbox_to_anchor=(1, 1))
#print(Measures.get_point_statistics(test,model))
'''
bchmk.sliding_window_benchmarks(train,1000,0.8,
methods=[pwfts.ProbabilisticWeightedFTS], #,ifts.IntervalFTS],
orders=[1,2,3],
partitions=[10])
'''
'''
from pyFTS.common import FLR,FuzzySet,Membership,SortedCollection
taiex_fs1 = Grid.GridPartitioner(data=train, npart=30)