You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Put an X between the brackets on this line if you have done all of the following:
Checked the Answered Questions on the Github Disscussion board: https://github.com/ourownstory/neural_prophet/discussions
If you have the same question but the Answer does not solve your issue, please continue the conversation there.
Considered whether your issue might need further discussing before being defined as a feature request:
Please post an idea or feedback
Is your feature request related to a problem? Please describe.
In the neuralprophet.time_dataset.tabularize_univariate_datetime()method (see test_time_dataset()example of how it's used), it outputs inputs (a dict of keys time and lags) and targets (an ndarray of dim n_rows and n_timesteps). This by itself is not easy to be used.
Describe the solution you'd like
Combine inputs and targets into a dataframe, which is just the original time-series but tabularized. For example, the AIR_FILE is an univariate time-series that only contains ds and y. After tabularization with only n_lags=3, I expect the output to be a dataframe with only the columns ds, y, y-1, y-2, y-3. Using the values from the original time-series without any traces of normalization, standardization, or any other transformations.
Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered:
Prerequisites
If you have the same question but the Answer does not solve your issue, please continue the conversation there.
If you have the same issue but there is a twist to your situation, please add an explanation there.
Please post an idea or feedback
Is your feature request related to a problem? Please describe.
In the
neuralprophet.time_dataset.tabularize_univariate_datetime()
method (seetest_time_dataset()
example of how it's used), it outputsinputs
(a dict of keystime
andlags
) andtargets
(an ndarray of dim n_rows and n_timesteps). This by itself is not easy to be used.Describe the solution you'd like
Combine
inputs
andtargets
into a dataframe, which is just the original time-series but tabularized. For example, the AIR_FILE is an univariate time-series that only containsds
andy
. After tabularization with onlyn_lags=3
, I expect the output to be a dataframe with only the columnsds
,y
,y-1
,y-2
,y-3
. Using the values from the original time-series without any traces of normalization, standardization, or any other transformations.Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered: