def plot_distribution(ax, cmap, probabilitydist, fig, time_from, reference_data=None):
"""
Plot forecasted ProbabilityDistribution objects on a matplotlib axis
:param ax: matplotlib axis
:param cmap: matplotlib colormap name
:param probabilitydist: list of ProbabilityDistribution objects
:param fig: matplotlib figure
:param time_from: starting time (on x axis) to begin the plots
:param reference_data:
:return:
"""
from matplotlib.patches import Rectangle
from matplotlib.collections import PatchCollection
patches = []
colors = []
for ct, dt in enumerate(probabilitydist):
disp = 0.0
if reference_data is not None:
disp = reference_data[time_from+ct]
for y in dt.bins:
s = Rectangle((time_from+ct, y+disp), 1, dt.resolution, fill=True, lw = 0)
patches.append(s)
colors.append(dt.density(y))
scale = Transformations.Scale()
colors = scale.apply(colors)
pc = PatchCollection(patches=patches, match_original=True)
pc.set_clim([0, 1])
pc.set_cmap(cmap)
pc.set_array(np.array(colors))
ax.add_collection(pc)
cb = fig.colorbar(pc, ax=ax)
cb.set_label('Density')
def plot_distribution(ax,
cmap,
probabilitydist,
fig,
time_from,
reference_data=None):
from matplotlib.patches import Rectangle
from matplotlib.collections import PatchCollection
patches = []
colors = []
for ct, dt in enumerate(probabilitydist):
disp = 0.0
if reference_data is not None:
disp = reference_data[time_from + ct]
for y in dt.bins:
s = Rectangle((time_from + ct, y + disp),
1,
dt.resolution,
fill=True,
lw=0)
patches.append(s)
colors.append(dt.density(y))
scale = Transformations.Scale()
colors = scale.apply(colors)
pc = PatchCollection(patches=patches, match_original=True)
pc.set_clim([0, 1])
pc.set_cmap(cmap)
pc.set_array(np.array(colors))
ax.add_collection(pc)
cb = fig.colorbar(pc, ax=ax)
cb.set_label('Density')
def __init__(self, **kwargs):
self.h = kwargs.get('h', .5)
"""Width parameter"""
self.kernel = kwargs.get("kernel", "epanechnikov")
"""Kernel function"""
self.data = kwargs.get("data", None)
self.transf = Transformations.Scale(min=0, max=1)
if self.data is not None:
self.data = self.transf.apply(self.data)
def build(self, data):
diff = Transformations.Differential(1)
data2 = diff.apply(data)
davg = np.abs(np.mean(data2) / 2)
if davg <= 1.0:
base = 0.1
elif 1 < davg <= 10:
base = 1.0
elif 10 < davg <= 100:
base = 10
else:
base = 100
sets = {}
kwargs = {'type': self.type, 'variable': self.variable}
dlen = self.max - self.min
npart = math.ceil(dlen / base)
partition = math.ceil(self.min)
for c in range(npart):
_name = self.get_name(c)
if self.membership_function == Membership.trimf:
sets[_name] = FuzzySet.FuzzySet(
_name, Membership.trimf,
[partition - base, partition, partition + base], partition,
**kwargs)
elif self.membership_function == Membership.gaussmf:
sets[_name] = FuzzySet.FuzzySet(_name, Membership.gaussmf,
[partition, base / 2],
partition)
elif self.membership_function == Membership.trapmf:
sets[_name] = FuzzySet.FuzzySet(_name, Membership.trapmf, [
partition - base, partition - (base / 2), partition +
(base / 2), partition + base
], partition, **kwargs)
partition += base
return sets
def __init__(self,h, kernel="epanechnikov"):
self.h = h
"""Width parameter"""
self.kernel = kernel
"""Kernel function"""
self.transf = Transformations.Scale(min=0,max=1)
#!/usr/bin/python # -*- coding: utf8 -*- import os import numpy as np import matplotlib.pylab as plt #from mpl_toolkits.mplot3d import Axes3D import pandas as pd from pyFTS.common import Transformations tdiff = Transformations.Differential(1) from pyFTS.data import TAIEX, SP500, NASDAQ dataset = TAIEX.get_data() #dataset = SP500.get_data()[11500:16000] #dataset = NASDAQ.get_data() #print(len(dataset)) from pyFTS.partitioners import Grid, Util as pUtil partitioner = Grid.GridPartitioner(data=dataset[:800], npart=10, transformation=tdiff) from pyFTS.common import Util as cUtil from pyFTS.benchmarks import benchmarks as bchmk, Util as bUtil, Measures, knn, quantreg, arima, naive from pyFTS.models import pwfts, song, chen, ifts, hofts from pyFTS.models.ensemble import ensemble model = chen.ConventionalFTS(partitioner=partitioner)
from pyFTS.data import TAIEX as tx
from pyFTS.common import Transformations
from pyFTS.data import SONDA
df = SONDA.get_dataframe()
train = df.iloc[0:578241] #three years
test = df.iloc[1572480:2096640] #one year
del df
from pyFTS.partitioners import Grid, Util as pUtil
from pyFTS.common import Transformations, Util
from pyFTS.models.multivariate import common, variable, mvfts
from pyFTS.models.seasonal import partitioner as seasonal
from pyFTS.models.seasonal.common import DateTime
bc = Transformations.BoxCox(0)
tdiff = Transformations.Differential(1)
np = 10
model = mvfts.MVFTS("")
fig, axes = plt.subplots(nrows=5, ncols=1, figsize=[15, 10])
sp = {
'seasonality':
DateTime.day_of_year,
'names': [
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct',
'Nov', 'Dec'
]
def SelecaoSimples_MenorRMSE(original, parameters, modelo):
ret = []
errors = []
forecasted_best = []
print("Série Original")
fig = plt.figure(figsize=[20, 12])
fig.suptitle("Comparação de modelos ")
ax0 = fig.add_axes([0, 0.5, 0.65, 0.45]) # left, bottom, width, height
ax0.set_xlim([0, len(original)])
ax0.set_ylim([min(original), max(original)])
ax0.set_title('Série Temporal')
ax0.set_ylabel('F(T)')
ax0.set_xlabel('T')
ax0.plot(original, label="Original")
min_rmse = 100000.0
best = None
for p in parameters:
sets = Grid.GridPartitioner(data=original, npart=p).sets
fts = modelo(str(p) + " particoes")
fts.train(original, sets=sets)
# print(original)
forecasted = fts.forecast(original)
forecasted.insert(0, original[0])
# print(forecasted)
ax0.plot(forecasted, label=fts.name)
error = Measures.rmse(np.array(forecasted), np.array(original))
print(p, error)
errors.append(error)
if error < min_rmse:
min_rmse = error
best = fts
forecasted_best = forecasted
handles0, labels0 = ax0.get_legend_handles_labels()
ax0.legend(handles0, labels0)
ax1 = fig.add_axes([0.7, 0.5, 0.3, 0.45]) # left, bottom, width, height
ax1.set_title('Comparação dos Erros Quadráticos Médios')
ax1.set_ylabel('RMSE')
ax1.set_xlabel('Quantidade de Partições')
ax1.set_xlim([min(parameters), max(parameters)])
ax1.plot(parameters, errors)
ret.append(best)
ret.append(forecasted_best)
# Modelo diferencial
print("\nSérie Diferencial")
difffts = Transformations.differential(original)
errors = []
forecastedd_best = []
ax2 = fig.add_axes([0, 0, 0.65, 0.45]) # left, bottom, width, height
ax2.set_xlim([0, len(difffts)])
ax2.set_ylim([min(difffts), max(difffts)])
ax2.set_title('Série Temporal')
ax2.set_ylabel('F(T)')
ax2.set_xlabel('T')
ax2.plot(difffts, label="Original")
min_rmse = 100000.0
bestd = None
for p in parameters:
sets = Grid.GridPartitioner(data=difffts, npart=p)
fts = modelo(str(p) + " particoes")
fts.train(difffts, sets=sets)
forecasted = fts.forecast(difffts)
forecasted.insert(0, difffts[0])
ax2.plot(forecasted, label=fts.name)
error = Measures.rmse(np.array(forecasted), np.array(difffts))
print(p, error)
errors.append(error)
if error < min_rmse:
min_rmse = error
bestd = fts
forecastedd_best = forecasted
handles0, labels0 = ax2.get_legend_handles_labels()
ax2.legend(handles0, labels0)
ax3 = fig.add_axes([0.7, 0, 0.3, 0.45]) # left, bottom, width, height
ax3.set_title('Comparação dos Erros Quadráticos Médios')
ax3.set_ylabel('RMSE')
ax3.set_xlabel('Quantidade de Partições')
ax3.set_xlim([min(parameters), max(parameters)])
ax3.plot(parameters, errors)
ret.append(bestd)
ret.append(forecastedd_best)
return ret
import os import numpy as np import matplotlib.pylab as plt import pandas as pd from pyFTS.common import Util as cUtil, FuzzySet from pyFTS.partitioners import Grid, Entropy, Util as pUtil, Simple from pyFTS.benchmarks import benchmarks as bchmk, Measures from pyFTS.models import chen, yu, cheng, ismailefendi, hofts, pwfts, tsaur, song, sadaei, ifts from pyFTS.models.ensemble import ensemble from pyFTS.common import Membership, Util from pyFTS.benchmarks import arima, quantreg, BSTS, gaussianproc, knn from pyFTS.common import Transformations tdiff = Transformations.Differential(1) boxcox = Transformations.BoxCox(0) from pyFTS.data import Enrollments, AirPassengers ''' data = AirPassengers.get_data() roi = Transformations.ROI() #plt.plot(data) _roi = roi.apply(data) #plt.plot(_roi)
def __init__(self, h, kernel="epanechnikov"):
self.h = h
self.kernel = kernel
self.transf = Transformations.Scale(min=0, max=1)
from pyFTS.partitioners import Grid
from pyFTS.models import chen
from pyFTS.benchmarks import Measures
from pyFTS.common import Util as cUtil, fts
import pandas as pd
import numpy as np
import os
from pyFTS.common import Transformations
from copy import deepcopy
from pyFTS.nonstationary import flrg, util, honsfts, partitioners
from pyFTS.models.nonstationary import nsfts
bc = Transformations.BoxCox(0)
import dispy
import dispy.httpd
os.chdir("/home/petronio/Dropbox/Doutorado/Codigos/")
def evaluate_individual_model(model, partitioner, train, test, window_size, time_displacement):
import numpy as np
from pyFTS.partitioners import Grid
from pyFTS.benchmarks import Measures
try:
model.train(train, sets=partitioner.sets, order=model.order, parameters=window_size)
forecasts = model.forecast(test, time_displacement=time_displacement, window_size=window_size)
_rmse = Measures.rmse(test[model.order:], forecasts[:-1])
_mape = Measures.mape(test[model.order:], forecasts[:-1])
_u = Measures.UStatistic(test[model.order:], forecasts[:-1])
train_split = 1000
test_length = 200
from pyFTS.common import Transformations
from pyFTS.benchmarks import naive
from pyFTS.models.incremental import TimeVariant, IncrementalEnsemble
from pyFTS.models.nonstationary import common, perturbation, partitioners as nspart
from pyFTS.models.nonstationary import nsfts, util as nsUtil
from pyFTS.partitioners import Grid
from pyFTS.models import hofts, pwfts
from pyFTS.benchmarks import Measures
from pyFTS.common import Transformations, Util as cUtil
diff = Transformations.Differential(lag=1)
train = dataset[:1000]
test = dataset[1000:]
#grid = Grid.GridPartitioner(data=train, transformation=diff)
#model = pwfts.ProbabilisticWeightedFTS(partitioner=grid)
#model.append_transformation(diff)
model = naive.Naive()
model.fit(train)
for ct, ttrain, ttest in cUtil.sliding_window(test, 1000, .95, inc=.5):
if model.shortname not in ('PWFTS', 'Naive'):
model.predict(ttrain)
