Catboost

Improvements:
- New visualization for parameter tuning. Use `plot=True` parameter in `grid_search` and `randomized_search` methods to show plots in jupyter notebook
- Switched to jemalloc allocator instead of LFalloc in CLI and model interfaces to fix some problems on Windows 7 machines, 881
- Calculation of binary class AUC is faster up to 1.3x
- Added [tutorial](https://github.com/catboost/tutorials/blob/master/convert_onnx_model/tutorial_convert_onnx_models.ipynb) on using fast CatBoost applier with LightGBM models

Bugs fixed:
- Shap values for `MultiClass` objective don't give constant 0 value for the last class in case of GPU training.
Shap values for `MultiClass` objective are now calculated in the following way. First, predictions are normalized so that the average of all predictions is zero in each tree. The normalized predictions produce the same probabilities as the non-normalized ones. Then the shap values are calculated for every class separately. Note that since the shap values are calculated on the normalized predictions, their sum for every class is equal to the normalized prediction
- Fixed bug in rangking tutorial, 955
- Allow string value for `per_float_feature_quantization` parameter, 996

Improvements:
- For metric MAE on CPU default value of `leaf-estimation-method` is now `Exact`
- Speed up `LossFunctionChange` feature strength computation

Bugs fixed:
- Broken label converter in grid search for multiclassification, 993
- Incorrect prediction with monotonic constraint, 994
- Invalid value of `eval_metric` in output of `get_all_params()`, 940
- Train AUC is not computed because hint `skip_train~false` is ignored, 970

Bugs fixed:
- Incorrect estimation of total RAM size on Windows and Mac OS, 989
- Failure when dataset is a `numpy.ndarray` with `order='F'`
- Disable `boost_from_average` when baseline is specified

Improvements:
- Polymorphic raw features storage (2x---25x faster data preparation for numeric features in non-float32 columns as either `pandas.DataFrame` or `numpy.ndarray` with `order='F'`).
- Support AUC metric for `CrossEntropy` loss on CPU
- Added `datasets.rotten_tomatoes()`, a textual dataset
- Usability of `monotone_constraints`, 950

Speedups:
- Optimized computation of `CrossEntropy` metric on CPUs with SSE3

New features:
- Sparse data support
- We've implemented and set to default `boost_from_average` in RMSE mode. It gives a boost in quality especially for a small number of iterations.

Improvements:
- Quantile regression on CPU
- default parameters for Poisson regression

Speedups:
- A number of speedups for training on CPU
- Huge speedups for loading datasets with categorical features represented as `pandas.Categorical`.
Hint: use `pandas.Categorical` instead of object to speed up loading up to 200x.

Breaking changes:
- All metrics except for AUC metric now use weights by default.

New features:
- Added `boost_from_average` parameter for RMSE training on CPU which might give a boost in quality.
- Added conversion from ONNX to CatBoost. Now you can convert XGBoost or LightGBM model to ONNX, then convert it to CatBoost and use our fast applier. Use `model.load_model(model_path, format="onnx")` for that.

Speed ups:
- Training is \~15% faster for datasets with categorical features.

Bug fixes:
- R language: `get_features_importance` with `ShapValues` for `MultiClass`, 868
- NormalizedGini was not calculated, 962
- Bug in leaf calculation which could result in slightly worse quality if you use weights in binary classification mode
- Fixed `__builtins__` import in Python3 in PR 957, thanks to AbhinavanT

Bug fixes:
- Versions 0.16.* had a bug in python applier with categorical features for applying on more than 128 documents.

New features:
- It is now possible to use pairwise modes for datasets without groups

Improvements:
- 1.8x Evaluation speed on asymmetrical trees