Hi Petronio.
Thank you for your quick response to my problem.
I'm coming again to ask about predictions in real future. In you predict method you need a dataset. What if I want to forecast "n" days ahead from today where there is no data. What dataset will I use in predict method when I use all data (until today) for training (it does not matter any test set).
Let's assume we have the model below:

fs = Grid.GridPartitioner(data=all_data, npart=190)
model = hofts.HighOrderFTS(partitioner=fs, order = 4, alpha_cut=.4)
model.fit(all_data.values.flatten())

Let's say I keep the last 4 points from "all_data" to accomodate the order of the model.How can I call model.predict method to forecast future days (until end of August)?

I forgot to write that when I use steps_ahead = n I get n times the same number. If you ask about my dataset, it is public and it is the close price of Bitcoin

Best regards
George

hi @petroniocandido
Following my comment in #1. I have 100 series that need one step ahead forecast. for your information, I have other series that can be used as external information. short description about my data

• each series has different behavior. some of them are stationary, non-stationary, some show strong seasonality, and some show drifting (sudden value jumping). to tackle this complexity, I am thinking to build one model for each series (what do you think?)
• data is monthly data where some series are complete and some series have missing values
• data range is very huge. it can be between negative millions and positive millions

I plan to try different approach both univariate (without any external information) and multivariate (with external information).
question apply for both scenarios :

1. I see there are a lot of FTS model implementation. in order to build robust automatic modeling pipeline for my problem, would you mind mapping what FTS model that work best for what kind of problem or type of series ? is there any model that can be used for any type of series but what I need is to get best hyperparameter setting ?
2. would you mind summarizing which model that work for 1 order and which one that can work with more than 1 order ?
3. does the implementation require complete data (no missing values) ? if yes, I am thinking to input the missing values but I build another series indicating whether the row is missing or not. what do you think ? is it the good practice ?
4. I see there is hyperparam search modul but I couldn't find examples to exercise. do you have examples of it ? my experiments on using FTS for my data showing that type of transformation, order, model impact much to the result. different options give very different result. So, I think, automatic search hyperparam would be very helpful. However, I haven't tried a different partitioner.

question apply for multivariate scenario :

1. how does the multivariate approach work here ? does the other series that act as external information can be used as future information (use t+1 external information to predict target y t+1) ?
2. if I can't use future value of external informations (use t + 0 as the latest external information to predict target y t+1). does the implementation support it ?

please advice,

thank you

Hi! What are the results of the discussion of the issue raised on 12.07.2019 by georgevarelas - the sequel did not follow. And the question is: can the duration be considered normal in 4 hours of processing sets in this Notepad?
Sincerely, Eugene.

great code thanks
may you clarify :
will it work for multivariate time series prediction both regression and classification
1
where all values are continues values
2
or even will it work for multivariate time series where values are mixture of continues and categorical values
for example 2 dimensions have continues values and 3 dimensions are categorical values

color        weight     gender  height  age  

1 black 56 m 160 34
2 white 77 f 170 54
3 yellow 87 m 167 43
4 white 55 m 198 72
5 white 88 f 176 32

I downloaded the notebook and changed cell 9,( after section 1.4 Partitioning) to use the local node (not use distributed setup) and I got exceptions

from pyFTS.partitioners import Grid, Util as pUtil
from pyFTS.benchmarks import benchmarks as bchmk
from pyFTS.models import chen

tag = 'chen_partitioning'
_type = 'point'

for dataset_name in dataset_names:
    dataset = get_dataset(dataset_name)

    bchmk.sliding_window_benchmarks(dataset, 1000, train=0.8, inc=0.2,
                                    methods=[chen.ConventionalFTS],
                                    benchmark_models=False,
                                    transformations=[None],
                                    partitions=np.arange(10,100,2), 
                                    progress=False, type=_type,
                                    distributed=False,# nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
                                    file="benchmarks.db", dataset=dataset_name, tag=tag)

    bchmk.sliding_window_benchmarks(dataset, 1000, train=0.8, inc=0.2,
                                    methods=[chen.ConventionalFTS],
                                    benchmark_models=False,
                                    transformations=[tdiff],
                                    partitions=np.arange(3,30,1), 
                                    progress=False, type=_type,
                                    distributed=False,# nodes=['192.168.0.110', '192.168.0.107', '192.168.0.106'],
                                    file="benchmarks.db", dataset=dataset_name, tag=tag)

EXCEPTION! CFTS 1 Grid 27 Differential(1)
Traceback (most recent call last):
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/benchmarks/benchmarks.py", line 281, in sliding_window_benchmarks
job = experiment_method(deepcopy(model), deepcopy(partitioner), train, test, **kwargs)
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/benchmarks/benchmarks.py", line 367, in run_point
mfts.fit(train_data, **kwargs)
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/common/fts.py", line 384, in fit
self.train(mdata, **kwargs)
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/models/chen.py", line 53, in train
tmpdata = self.partitioner.fuzzyfy(data, method='maximum', mode='sets')
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/partitioners/partitioner.py", line 144, in fuzzyfy
mv = self.fuzzyfy(inst, **kwargs)
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/partitioners/partitioner.py", line 157, in fuzzyfy
tmp = self[ix].membership(data)
File "/home/steve/anaconda3/lib/python3.7/site-packages/pyFTS/partitioners/partitioner.py", line 288, in getitem
raise ValueError("The fuzzy set index must be between 0 and {}.".format(self.partitions))
ValueError: The fuzzy set index must be between 0 and 27.

hello, i want ask you something. You use the upper and lower bounds for universe of discourse by 10% as a default, but i want try different value. how to change it from 10% to another values?

Hi Petrônio,

I am currently working on a real-world problem which is to forecast the next 24-hrs demand. However, when I try to run model.predict(input_data, steps_ahead=24), it only gives me constant values that are not reasonable.

I referred to the article you published and the graph shows the results look quite nice. I am keen to know how to achieve this multi-step forecasting. Are there any pre-processing steps needed for the input test data before predicting？

In addition, I noticed that some of the examples you gave as following:

ax[count].plot(dataset[train_split:train_split+200])
model1 = cUtil.load_obj('model1'+dataset_name+str(order))
forecasts = model1.predict(dataset[train_split:train_split+200])
ax[count].plot(forecasts)

From my understanding, if the input test data is from time t, the forecasts should be starting from time (t+1). We need to use the previous data to predict the next one. Then ax[count].plot(dataset[train_split:train_split+200]) should be changed to ax[count].plot(dataset[train_split+1:train_split+201]), right?

Looking forward to your reply.!
Thank you so much!