Merge branch 'main' into 3phase-1cycle

.github/ISSUE_TEMPLATE/bug_report.md

@@ -13,11 +13,11 @@ about: Create a report to help us improve
       cd neural_prophet
       pip install .
       ```
-    * Checked the Answered Questions on the Github Disscussion board: https://github.com/ourownstory/neural_prophet/discussions
+    * Checked the Answered Questions on the Github Discussion 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.
     * Checked that your issue isn't already filed: https://github.com/ourownstory/neural_prophet/issues
       If you have the same issue but there is a twist to your situation, please add an explanation there.
-    * Considered whether your bug might actually be solveable by getting a question answered: 
+    * Considered whether your bug might actually be solvable by getting a question answered: 
       * Please [post a package use question](https://github.com/ourownstory/neural_prophet/discussions/categories/q-a-get-help-using-neuralprophet)
       * Please [post a forecasting best practice question](https://github.com/ourownstory/neural_prophet/discussions/categories/q-a-forecasting-best-practices)
       * Please [post an idea or feedback](https://github.com/ourownstory/neural_prophet/discussions/categories/ideas-feedback)
@@ -48,7 +48,7 @@ Describe what happens, and how often it happens.
 
 If applicable, add screenshots and console printouts to help explain your problem.
 
-**Environement (please complete the following information):**
+**Environment (please complete the following information):**
 
  - Python environment [e.g. Python 3.8, in standalone venv with no other packages]
  - NeuralProphet version and install method [e.g. 2.7, installed from PYPI with `pip install neuralprophet`]

.github/ISSUE_TEMPLATE/feature_request.md

@@ -7,7 +7,7 @@ about: Suggest an idea for this project
 **Prerequisites**
 
 * [ ] 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
+    * Checked the Answered Questions on the Github Discussion 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.
     * Checked that your issue isn't already filed: https://github.com/ourownstory/neural_prophet/issues
       If you have the same issue but there is a twist to your situation, please add an explanation there.

.github/workflows/metrics.yml

@@ -51,16 +51,12 @@ jobs:
           echo "## Model Training" >> report.md
           echo "### PeytonManning" >> report.md
           cml asset publish tests/metrics/PeytonManning.svg --md >> report.md
-          echo "### PeytonManning_test30" >> report.md
-          cml asset publish tests/metrics/PeytonManning_test30.svg --md >> report.md
           echo "### YosemiteTemps" >> report.md
           cml asset publish tests/metrics/YosemiteTemps.svg --md >> report.md
-          echo "### YosemiteTemps_test20" >> report.md
-          cml asset publish tests/metrics/YosemiteTemps_test20.svg --md >> report.md
           echo "### AirPassengers" >> report.md
           cml asset publish tests/metrics/AirPassengers.svg --md >> report.md
-          echo "### AirPassengers_test30" >> report.md
-          cml asset publish tests/metrics/AirPassengers_test30.svg --md >> report.md
+          echo "### EnergyPriceDaily" >> report.md
+          cml asset publish tests/metrics/EnergyPriceDaily.svg --md >> report.md
           echo "\n</details>" >> report.md
           # Post reports as comments in GitHub PRs
           cml comment update --target=pr report.md # post to PR

README.md

@@ -15,8 +15,8 @@ Please note that the project is still in beta phase. Please report any issues yo
 
 # NeuralProphet: human-centered forecasting
 NeuralProphet is an easy to learn framework for interpretable time series forecasting.
-NeuralProphet is built on PyTorch and combines Neural Network and traditional time-series algorithms, inspired by [Facebook Prophet](https://github.com/facebook/prophet) and [AR-Net](https://github.com/ourownstory/AR-Net).
-- With few lines of code, you can define, customize, visualize, and evaluate your own forecasting models.
+NeuralProphet is built on PyTorch and combines Neural Networks and traditional time-series algorithms, inspired by [Facebook Prophet](https://github.com/facebook/prophet) and [AR-Net](https://github.com/ourownstory/AR-Net).
+- With a few lines of code, you can define, customize, visualize, and evaluate your own forecasting models.
 - It is designed for iterative human-in-the-loop model building. That means that you can build a first model quickly, interpret the results, improve, repeat. Due to the focus on interpretability and customization-ability, NeuralProphet may not be the most accurate model out-of-the-box; so, don't hesitate to adjust and iterate until you like your results.
 - NeuralProphet is best suited for time series data that is of higher-frequency (sub-daily) and longer duration (at least two full periods/years).
 
@@ -31,7 +31,7 @@ We compiled a [Contributing to NeuralProphet](CONTRIBUTING.md) page with practic
 
 ## Community
 #### Discussion and Help
-If you have any question or suggestion, you can participate with [our community right here on Github](https://github.com/ourownstory/neural_prophet/discussions)
+If you have any questions or suggestion, you can participate in [our community right here on Github](https://github.com/ourownstory/neural_prophet/discussions)
 
 #### Slack Chat
 We also have an active [Slack community](https://join.slack.com/t/neuralprophet/shared_invite/zt-sgme2rw3-3dCH3YJ_wgg01IXHoYaeCg). Come and join the conversation!
@@ -100,9 +100,9 @@ pip install .
 
 
 ### Framework features
-* Multiple time series: Fit a global/glocal model with (partially) shared model parameters
+* Multiple time series: Fit a global/local model with (partially) shared model parameters
 * Uncertainty: Estimate values of specific quantiles - Quantile Regression
-* Regularize modelling components
+* Regularize modeling components
 * Plotting of forecast components, model coefficients and more
 * Time series crossvalidation utility
 * Model checkpointing and validation
@@ -111,7 +111,7 @@ pip install .
 ### Coming soon<sup>:tm:</sup>
 
 * Cross-relation of lagged regressors
-* Cross-relation and non-linear modelling of future regressors
+* Cross-relation and non-linear modeling of future regressors
 * Static features / Time series featurization
 * Logistic growth for trend component.
 * Model bias modelling / correction with secondary model
@@ -135,5 +135,5 @@ Please cite [NeuralProphet](https://arxiv.org/abs/2111.15397) in your publicatio
 ```
 
 ## About
-NeuralProphet is and open-source community project, supported by awesome people like you. 
+NeuralProphet is an open-source community project, supported by awesome people like you. 
 If you are interested in joining the project, please feel free to reach out to me (Oskar) - you can find my email on the [NeuralProphet Paper](https://arxiv.org/abs/2111.15397).

docs/source/how-to-guides/feature-guides/hyperparameter-selection.md

@@ -21,7 +21,7 @@ NeuralProphet is fit with stochastic gradient descent - more precisely, with an
 If the parameter `learning_rate` is not specified, a learning rate range test is conducted to determine the optimal learning rate. 
 The `epochs`, `loss_func` and `optimizer` are other parameters that directly affect the model training process. 
 If not defined, `epochs`and `loss_func` are automatically set based on the dataset size. They are set in a manner that controls the total number training steps to be around 1000 to 4000.
-NeuralProphet offers to set two different values for `optimizer`, namely `AdamW` and `SDG` (stochastic gradient decsent).
+NeuralProphet offers to set two different values for `optimizer`, namely `AdamW` and `SDG` (stochastic gradient descent).
 
 If it looks like the model is overfitting to the training data (the live loss plot can be useful hereby), 
 you can reduce `epochs`  and `learning_rate`, and potentially increase the `batch_size`.