[Minor] Convert timezones to UTC by default

[christymctse]

🔬 Background

• Fixing issue Add support for timezones #970

🔮 Key changes

• Adding UTC as true in the parameter to convert timezone to UTC timestamp
• Removed warning which stated that NP is not supporting timezone specified dataset

📋 Review Checklist

• I have performed a self-review of my own code.
• I have commented my code, added docstrings and data types to function definitions.
• I have added pytests to check whether my feature / fix works.

Please make sure to follow our best practices in the Contributing guidelines.

[codecov-commenter]

Codecov Report

Merging #1085 (47ee3cb) into main (544a420) will not change coverage.
The diff coverage is 50.00%.

📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

@@           Coverage Diff           @@
##             main    #1085   +/-   ##
=======================================
  Coverage   90.18%   90.18%           
=======================================
  Files          36       36           
  Lines        5066     5066           
=======================================
  Hits         4569     4569           
  Misses        497      497           

Impacted Files	Coverage Δ
neuralprophet/df_utils.py	94.52% <50.00%> (ø)

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[noxan]

While testing with the energy dataset I receive the following issue:

AttributeError                            Traceback (most recent call last)
/var/folders/h5/r0lsf_xx0dgf0y4_7tyr6zx80000gn/T/ipykernel_55050/2978023471.py in <module>
      4 )
      5 
----> 6 metrics = m.fit(df)
      7 
      8 forecast = m.predict(df)

neural_prophet/neuralprophet/forecaster.py in fit(self, df, freq, validation_df, epochs, batch_size, learning_rate, early_stopping, minimal, metrics, progress, checkpointing, continue_training, num_workers)
...
    504             return PeriodProperties(data, orig)
    505 
--> 506         raise AttributeError("Can only use .dt accessor with datetimelike values")

AttributeError: Can only use .dt accessor with datetimelike values

[noxan]

I had a brief look into it, seems https://stackoverflow.com/questions/69020835/attributeerror-can-only-use-dt-accessor-with-datetimelike-values-but-cells-con might be helpful and https://pandas.pydata.org/docs/reference/api/pandas.Series.tz_localize.html

[noxan]

Would also be great to have the new code in place where the old code was, so that all checks and transformations on the ds column are in the same place.

[ourownstory]

@christymctse What's the status on this?

[christymctse]

@christymctse What's the status on this?

Will be working on this next week

[christymctse]

@noxan @ourownstory, sorry about get back late
Just fixed the bug and it should be working fine on the energy dataset now

[ourownstory]

@noxan Can you please give this another review to check whether it is ready for merge? Thank you!

[noxan]

Thanks @christymctse for the adjustments, it works for me now - good job 👍

[github-actions]

Model Benchmark

Benchmark	Metric	main	current	diff
YosemiteTemps	MAE_val	1.72948	1.72949	0.0%	✅
YosemiteTemps	RMSE_val	2.27386	2.27386	0.0%	✅
YosemiteTemps	Loss_val	0.00096	0.00096	0.0%	✅
YosemiteTemps	MAE	1.45189	1.45189	0.0%	✅
YosemiteTemps	RMSE	2.16631	2.16631	0.0%	✅
YosemiteTemps	Loss	0.00066	0.00066	0.0%	✅
YosemiteTemps	time	130.273	100.44	-22.9%	🎉
AirPassengers	MAE_val	15.4077	15.4077	-0.0%	✅
AirPassengers	RMSE_val	19.5099	19.5099	-0.0%	✅
AirPassengers	Loss_val	0.00196	0.00196	-0.0%	✅
AirPassengers	MAE	9.86947	9.86947	0.0%	✅
AirPassengers	RMSE	11.7222	11.7222	0.0%	✅
AirPassengers	Loss	0.00057	0.00057	0.0%	✅
AirPassengers	time	5.50433	4.34	-21.15%	🎉
PeytonManning	MAE_val	0.64636	0.64636	0.0%	✅
PeytonManning	RMSE_val	0.79276	0.79276	0.0%	✅
PeytonManning	Loss_val	0.01494	0.01494	0.0%	✅
PeytonManning	MAE	0.42701	0.42701	0.0%	✅
PeytonManning	RMSE	0.57032	0.57032	0.0%	✅
PeytonManning	Loss	0.00635	0.00635	0.0%	✅
PeytonManning	time	16.0501	12.48	-22.24%	🎉

Model training plots

Model Training

PeytonManning

YosemiteTemps

AirPassengers