Add possibility to load pretrained embedding models

[egoriyaa]

Before submitting (must do checklist)

• Did you read the contribution guide?
• Did you update the docs? We use Numpy format for all the methods and classes.
• Did you write any new necessary tests?
• Did you update the CHANGELOG?

Proposed Changes

Closing issues

closes #452

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[github-actions]

🚀 Deployed on https://deploy-preview-461--etna-docs.netlify.app

[codecov]

Codecov Report

Attention: Patch coverage is 96.22642% with 2 lines in your changes missing coverage. Please review.

Project coverage is 90.44%. Comparing base (b19507d) to head (d2f2da9).
Report is 1 commits behind head on master.

Files with missing lines	Patch %	Lines
etna/transforms/embeddings/models/ts2vec.py	96.15%	1 Missing ⚠️
etna/transforms/embeddings/models/tstcc.py	96.29%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #461      +/-   ##
==========================================
+ Coverage   90.41%   90.44%   +0.03%     
==========================================
  Files         229      229              
  Lines       15939    15988      +49     
==========================================
+ Hits        14411    14461      +50     
+ Misses       1528     1527       -1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[d-a-bunin]

Line #5.    ts.df_exog = None

Looks strange... Can we avoid doing this?

dE.g. we can recreate tsdataset using to_pandas. I just think it isn't good to show users they can change df_exog this way.

Reply via ReviewNB