feat: added notebook with GP and NP on M4 time series data

[mamarder]

Hello @dirmeier,

as discussed here is the MR for the M4 time-series notebook.

4 GPs and 1 NP are trained using the past data from 4 time series from the M4 hourly dataset. Then predictions are made for "future" time values. Past data, training data and predictions are visualized.

• The fit on past data and predictions work quite well for GPs.
• For NP the fit does not making much sense. This needs to be improved.

For GPs Periodic and Linear kernels have been introduced. Further addition and multiplication of kernels are possible as + and * operators have been overloaded.

Regards Marco

[codecov[bot]]

Codecov Report

Base: 50.75% // Head: 38.93% // Decreases project coverage by -11.81% :warning:

Coverage data is based on head (9db9c52) compared to base (aa857d6). Patch coverage: 15.93% of modified lines in pull request are covered.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #20 +/- ## =========================================== - Coverage 50.75% 38.93% -11.82% =========================================== Files 21 24 +3 Lines 532 773 +241 =========================================== + Hits 270 301 +31 - Misses 262 472 +210 ``` | [Impacted Files](https://codecov.io/gh/ramsey-devs/ramsey/pull/20?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs) | Coverage Δ | | |---|---|---| | [ramsey/\_src/datasets.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZGF0YXNldHMucHk=) | `0.00% <0.00%> (ø)` | | | [ramsey/\_src/gaussian\_process/gaussian\_process.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy9nYXVzc2lhbl9wcm9jZXNzLnB5) | `29.26% <ø> (-0.97%)` | :arrow_down: | | [ramsey/data.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L2RhdGEucHk=) | `0.00% <0.00%> (ø)` | | | [...ey/\_src/gaussian\_process/train\_gaussian\_process.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy90cmFpbl9nYXVzc2lhbl9wcm9jZXNzLnB5) | `18.00% <4.34%> (-9.59%)` | :arrow_down: | | [ramsey/\_src/gaussian\_process/kernel/stationary.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy9rZXJuZWwvc3RhdGlvbmFyeS5weQ==) | `31.66% <17.24%> (-15.21%)` | :arrow_down: | | [...sey/\_src/gaussian\_process/kernel/non\_stationary.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy9rZXJuZWwvbm9uX3N0YXRpb25hcnkucHk=) | `21.62% <21.62%> (ø)` | | | [...y/\_src/gaussian\_process/sparse\_gaussian\_process.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy9zcGFyc2VfZ2F1c3NpYW5fcHJvY2Vzcy5weQ==) | `21.79% <21.79%> (ø)` | | | [ramsey/\_src/gaussian\_process/kernel/base.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvZ2F1c3NpYW5fcHJvY2Vzcy9rZXJuZWwvYmFzZS5weQ==) | `29.62% <25.00%> (-53.71%)` | :arrow_down: | | [ramsey/\_src/neural\_process/train\_neural\_process.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L19zcmMvbmV1cmFsX3Byb2Nlc3MvdHJhaW5fbmV1cmFsX3Byb2Nlc3MucHk=) | `92.50% <100.00%> (-5.00%)` | :arrow_down: | | [ramsey/covariance\_functions.py](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs#diff-cmFtc2V5L2NvdmFyaWFuY2VfZnVuY3Rpb25zLnB5) | `100.00% <100.00%> (ø)` | | | ... and [2 more](https://codecov.io/gh/ramsey-devs/ramsey/pull/20/diff?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs) | | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ramsey-devs)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[dirmeier]

Hi @mamarder, thanks for the PR. This looks great.