[refactor] Uncertainty streamline naming

[leoniewgnr]

🔬 Background

The forecast data frames gets a new column for every new uncertainty prediction method which leads to a very large data frame.
Fixes issue #1261

🔮 Key changes

The initial uncertainty intervals are overwritten with the new ones when a new uncertainty prediction method is used.

📋 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.

[github-actions]

Model Benchmark

Benchmark	Metric	main	current	diff
AirPassengers	MAE_val	13.0626	13.0626	0.0%	✅
AirPassengers	RMSE_val	15.9453	15.9453	0.0%	✅
AirPassengers	Loss_val	0.00131	0.00131	0.0%	✅
AirPassengers	MAE	9.88156	9.88156	0.0%	✅
AirPassengers	RMSE	11.7354	11.7354	0.0%	✅
AirPassengers	Loss	0.00052	0.00052	0.0%	✅
AirPassengers	time	5.18982	4.92	-5.2%	🎉
PeytonManning	MAE_val	0.58159	0.58159	0.0%	✅
PeytonManning	RMSE_val	0.72216	0.72216	0.0%	✅
PeytonManning	Loss_val	0.01239	0.01239	0.0%	✅
PeytonManning	MAE	0.41671	0.41671	0.0%	✅
PeytonManning	RMSE	0.55961	0.55961	0.0%	✅
PeytonManning	Loss	0.00612	0.00612	0.0%	✅
PeytonManning	time	12.7264	11.96	-6.02%	🎉
YosemiteTemps	MAE_val	1.3442	1.3442	0.0%	✅
YosemiteTemps	RMSE_val	2.00245	2.00245	0.0%	✅
YosemiteTemps	Loss_val	0.00077	0.00077	0.0%	✅
YosemiteTemps	MAE	1.3192	1.3192	0.0%	✅
YosemiteTemps	RMSE	2.13518	2.13518	0.0%	✅
YosemiteTemps	Loss	0.00064	0.00064	0.0%	✅
YosemiteTemps	time	67.5437	61.65	-8.73%	🎉

Model training plots

Model Training

PeytonManning

YosemiteTemps

AirPassengers

[codecov-commenter]

Codecov Report

Merging #1262 (07d1668) into main (209129e) will decrease coverage by 0.05%.
The diff coverage is 96.51%.

📣 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    #1262      +/-   ##
==========================================
- Coverage   89.84%   89.79%   -0.05%     
==========================================
  Files          38       38              
  Lines        5149     5126      -23     
==========================================
- Hits         4626     4603      -23     
  Misses        523      523              

Impacted Files	Coverage Δ
neuralprophet/forecaster.py	87.38% <86.66%> (-0.04%)	⬇️
neuralprophet/plot_forecast_plotly.py	87.36% <92.30%> (+0.05%)	⬆️
neuralprophet/plot_forecast_matplotlib.py	84.47% <100.00%> (-0.81%)	⬇️
neuralprophet/uncertainty.py	98.69% <100.00%> (+1.36%)	⬆️

[leoniewgnr]

Basic user:

method = "naive"  # or "cqr" for a more sophisticated method, see uncertainty tutorial
conformal_forecast = m.conformal_predict(train_df, cal_df, alpha=0.1, method=method)
fig = m.highlight_nth_step_ahead_of_each_forecast(1).plot(conformal_forecast)

--> returns only y, yhat and the updated uncertainty intervals
--> plot shows only the forecast and one uncertainty interval around it

Advanced user:

method = "naive"  # or "cqr" for a more sophisticated method, see uncertainty tutorial
conformal_forecast = m.conformal_predict(train_df, cal_df, alpha=0.1, method=method, show_qr=True)
fig = m.conformal_plot(conformal_forecast, n_highlight =1)

--> returns updated uncertainty intervals (conformal prediction: naive or cqr) and previous quantile regression intervals
--> plot shows previous qr intervals in light blue and additional lines for conformal prediction

changes adressed

[LeonieFreisinger]

LGTM!